TECHNICAL FIELD:

The present invention generally relates to optimization systems and more particularly to systems and methods for optimizing supply chain by providing improvements in search methodology applied to logistics optimization in supply chain technology.

BACKGROUND OF THE DISCLOSURE:

The following description of the related art is intended to provide background information pertaining to the field of the disclosure. This section may include certain aspects of the art that may be related to various features of the present disclosure. However, it should be appreciated that this section is used only to enhance the understanding of the reader with respect to the present disclosure, and not as admissions of the prior art.

An optimization system helps to achieve the best solution for a set of prioritized criteria or constraints. With an advancement in the digital technologies, not only the optimization systems are enhanced to a great extent but also, various new technologies have been developed time to time. Genetic system and algorithms were introduced as a method for finding an optimum solution to complicated problems. In this algorithm, an emulated chromosomal data structure is Initially designed to represent a candidate or trial solution. A plurality of n-bit chromosomes of that data structure are then randomly generated. A plurality of the generated chromosomes are registered in groups or populations. A plurality of the parent chromosomes are selected from this population of generated chromosomes according to a given algorithm. Each generated chromosome is assigned a unique problem-specific fitness which differs from other chromosomes in the population identifying a solution quality of the chromosome. The problem- specific fitness is expressed by a fitness value. The chromosomes are selected from the population of chromosomes in proportion to their fitness values with more-fit chromosomes having a higher probability of being selected. When a pair of parent chromosomes are selected from the population, the parent chromosomes are combined with a probabilistically generated cut point. In the case of having no cut point generated, either of the parent chromosomes is simply copied to provide a new chromosome as a child chromosome. Thus, a child chromosome is created as output. The child chromosome, therefore, contains portions of each parent or the whole portion of a parent. The child chromosome is then mutated. The mutation is performed with a low probability. The mutation is performed through inversion of a bit in the child chromosome. The bit is selected randomly across ail genes in the child chromosome. The mutation helps in making a solution to a problem move out of local convergence and ensuring a global search. A mutated child chromosome is then evaluated to be assigned its fitness value. An evaluated child chromosome along with its fitness value is stored as a member of the next generation in the population. After repeated iteration of this process, the general fitness of chromosomes in the population improves. Thus, the solution to the problem emerges in the population. The solution to the problem is acquired with highly fit chromosomes concentrated in the population. One example, where this algorithm is a useful method for finding optimum solutions is the Traveling Salesman Problem described by Grefenstette, The Serial Genetic algorithm (GA) operators such as selection, crossover, mutation and fitness function calculations are expensive, therefore, implementation of the GA on any optimization problem with serial GA operators escalates the cost for optimization.

Also, one another technology developed over a period of time is a generative adaptive network (GAN). The generative adaptive network (GAN) is a class of machine learning where given a training set, this technique learns to generate new data with the same statistics as the training set. For example, a GAN trained on photographs can generate new photographs that look at least superficially authentic to human observers, having many realistic characteristics. Though originally proposed as a form of generative mode! for unsupervised learning, GANs have also proven useful for semi-supervised learning, fully supervised learning, and reinforcement learning.

Also, a Gaussian process is a stochastic process (a collection of random variables indexed by time or space), such that every finite collection of those random variables has a multivariate normal distribution, i.e. every finite linear combination of them is normally distributed. The distribution of a Gaussian process is the joint distribution of all those (infinitely many) random variables, and as such, it is a distribution over functions with a continuous domain, e.g. time or space. A machine-learning algorithm that involves a Gaussian process uses lazy learning and a measure of the similarity between points (the kernel function) to predict the value for an unseen point from training data. The prediction is not just an estimate for that point, but also has uncertainty irsformation--it is a one-dimensional Gaussian distribution (which is the marginal distribution at that point). For multi- output predictions, multivariate Gaussian processes are used, for which the multivariate Gaussian distribution is the marginal distribution at each point.

Furthermore, artificial intelligence, cognitive modeling, and neural networks are information processing paradigms inspired by the way biological neural systems process data. Artificial intelligence and cognitive modeling try to simulate some properties of biological neural networks. In the artificial intelligence field, artificial neural networks have been applied successfully to speech recognition, image analysis and adaptive control. A neural network (NN), in the case of artificial neurons called artificial neural network (ANN) or simulated neural network (SNN), is an interconnected group of natural or artificial neurons that uses a mathematical or computational model for information processing based on a connectionist approach to computation, in most cases, an ANN is an adaptive system that changes its structure based on external or internal information that flows through the network. In more practical terms neural networks are non-linear statistical data modeling or decision-making tools. They can be used to model complex relationships between inputs and outputs or to find patterns in data.

Further, a supply chain is a system of various subsystems where organizations, people, activities, information, and resources are involved in supplying a product or service to another organization or directly to consumer(s). Supply chain activities involve the transformation of raw materials, natural resources, and other semi-finished components into a finished product that is delivered to organization(s) or end customer(s). A supply chain seeks to match demand with supply and do so with minimal inventory. The supply chain management iSCM) is the need to integrate the key business processes, from end-user through original suppliers. The original suppliers are those that provide products, services, and information that add value for customers and other stakeholders. The basic idea behind this is that companies and corporations involve themselves in a supply chain by exchanging information about market fluctuations and production capabilities. If ail relevant information is accessible to any relevant company, every company in the supply chain has the ability to help optimize the entire supply chain rather than to sub-optimize based on local optimization. The primary objective is to fulfil customer demands through the most efficient use of resources, including distribution capacity, inventory, and labor. Further, various aspects of optimizing the supply chain include sourcing strategically to strike a balance between lowest material cost and transportation, liaising with suppliers to eliminate bottlenecks, Implementing just-in-time techniques to optimize manufacturing flow, maintaining the right mix and location of factories and warehouses to serve customer markets, and using location-allocation, vehicle routing analysis, dynamic programming, and traditional logistics optimization to maximize the efficiency of distribution etc.

Allocation traditionally led to orders and order lines being sent to the distribution center for fulfilment. With omni-channel capabilities being implemented, allocation becomes more complex. As omni-channel models are adopted and offer their customers different ways to obtain product, their supply chain network becomes more complex. The distribution center is no longer the only means for fulfilment. A robust Order Management System allows to configure allocation rules based on business objectives. For example, if an organization has a smaller store footprint with less room for inventory, it may make more sense to ship most of the product from the distribution center. In contrast, if a larger store footprint is operated with the bandwidth to ship from stores, it may be more cost-effective and quicker to ship directly from stores to customers. This could create a competitive advantage for the fulfilment network and reduce overall transportation costs. Allocation planning supports the process of distributing a finite amount of resources (for example, a number of products) to a given number of business partners (for example, retail outlets). Many companies today are embarking on fulfilment network analysis initiatives to try and understand customer demand and optimize where they are holding inventory. This analysis helps to alleviate the pressures of allocation, ensuring that inventory is available in the right locations the majority of the time. That being said, allocation strategy is still vital to understand where to fulfil orders from and what to do when first option is unavailable. Used correctly, a strategy can fulfil customer orders effectively and efficiently. The allocation complexity usually results in unwanted costs seen as the price of servicing a customer in today's landscape. However, there Is a way to minimize these costs and still serve the customer at the required levels to compete in the industry. Allocation strategies can not only eliminate costs, but also create a competitive advantage for the supply chain. Further, distribution refers to the process of the movement of goods from supplier or manufacturer to point of sale. It refers to numerous activities and processes such as packaging, inventory, warehousing, supply chain, and logistics. Distribution management is critical to a company's financial success and corporate longevity. The larger a corporation, or the greater the number of supply points a company has, the more it will need to rely on automation to effectively manage the distribution process. There are basically two types of distribution: commercial distribution (commonly known as sales distribution) and physical distribution (better known as logistics). Distribution involves diverse functions such as customer service, shipping, warehousing, inventory control, private trucking-fleet operations, packaging, receiving, materials handling, along with plant, warehouse and store location planning and the integration of information. The goal is to achieve ultimate efficiency in delivering raw materials and parts, both partially and completely finished products to the right place and time in the proper condition. Physical distribution planning should align with the overall channel strategy.

Further, optimization is a process of determination of a set of values for design parameters that solves a maximization or minimization function of a set of objectives derived from quantities of interests (G.OIs). The optimization of a complex system Involves determination of optimum values for a set of design parameters in order to meet a specific set of objectives concerning the quantities of interest (Q.OI) in which the design parameters are a subset of the input parameters and the QQIs are determined from the output parameters. The system can be an experiment or a computational model. Particularly, when the parameter space is large, optimization necessitates a significant number of executions of the system to obtain a desired solution in tolerance limits.

For instance, various aspects of the supply chain are explained below for the petroleum industry. In the petroleum industry, crude oil and natural gas are the raw materials used for production of petrochemicals and other oil derivatives. The crude oil undergoes a distillation process after the extraction of crude oil is completed from oil reserves located deep underground or in sea beds. With distillation of crude, various fractions of the crude oil are produced, such as fuel gas, liquefied petroleum gas (LPG), kerosene, and naphtha. The output of the distillation process is then provided to refineries as feedstocks. These feedstocks are first processed through cracking operations before they are supplied to petrochemical plants. Once the cracking process is complete, new products are obtained that serve as the building blocks of the petrochemical industry, such as olefins (i.e., mainly ethylene, propylene, and the so-called Carbon (C) derivatives, including butadiene) and aromatics, which include benzene, toluene, and the xylenes. After the cracking process, petrochemical products such as ethylene, propylene, butadiene, benzene, toluene, and the xylenes are then used at petrochemical plants to produce even more specialized products, such as plastics, soaps and detergents, healthcare products (such as aspirin), synthetic fibers for clothes and furniture, rubbers, paints, and insulating materials. Specific modes of transportation such as pipelines, vessels or tankers, and railroads may be required for commodities such as oil, gas, and petrochemicals. The demand for these commodities is from all over the globe since they represent an essentia! source of energy and raw material for a large number of other industries although they are produced in specific and limited regions of the world only.

The supply chain of the petroleum and chemical industry is divided into two different, yet closely related, major segments: the upstream and downstream supply chains. The upstream supply chain involves the acquisition of crude oil, which is the specialty of the oil companies. The upstream process includes the exploration, forecasting, production, and logistics management of delivering crude oil from remotely located oil wells to refineries. The downstream supply chain starts at the refinery, where the crude oil is manufactured into the consumable products that are the specialty of refineries and petrochemical companies. The downstream supply chain involves the process of forecasting, production, and the logistics management of delivering crude oil derivatives to customers around the globe.

An exemplary, demand-supply flow of scheduling, allocation and distribution of the materials between the manufacturers, the depots and the customers is illustrated in the Figure 1. At [102] Figure 1 shows the flow of material allocation and at [104] Figure 1 shows the flow of the demand. The material flow is attributed and tracked by allocation of material(s) at destination (Depot [108] and Customer [110]) on a daily basis, every month in advance. The demand flow relates to finding the optimal allocation to the depots [108] and the customers [110] knowing the demand in advance.

Furthermore, in the petroleum and chemical industry there are challenges and opportunities existing in both the upstream and downstream supply chains. The lead-time of several weeks from the shipping point to the final customers' location is very common in this type of industry. For example, it takes several weeks for the Persian Gulfs oil to make its way to the US and up to another few weeks for it to he processed and delivered. The opening of new production sites or distribution centers closer to dispersed customers is one way to reduce the lead time and transportation costs. However, the acquisition of such facilities in the oil and petrochemical Industries, if feasible, is typically very costly and often results in higher inventory and operating costs. These factors are pushing oil and petrochemicals companies to either absorb the increase in costs or pass the costs on to customers who are already facing increasing prices. Therefore, improved supply chain efficiencies represent a huge area for cost savings, specifically in the logistics area. Despite the importance of the petroleum industry in our daily life and the operational challenges, it involves, unfortunately, this topic has received very little attention for innovation for improved operations and supply chain management.

Every point in logistic network, therefore, represents a major challenge which is highly inflexible, arises from the production capabilities of crude oil suppliers, long transportation lead times, and the limitations of modes of transportation. These commodities and products are transferred between global locations that are— in many cases— continents apart and long distance between supply chain partners and slow modes of transportation induce not only high transportation costs and in-transit inventory, but also high inventory carrying costs in terms of safety stocks at the final customer location. The great distances between supply chain partners present a high variability of transportation times that can hurt suppliers in terms of service levels and final customers in terms of safety stock costs. Moreover, the transportation process is carried out either by ships, trucks, pipelines, or railroads. In many instances, a shipment has to exploit multiple transportation modes before reaching the final customer's location. Such constraints on transportation modes in this type of industry induce long lead times from the shipping point to the final customers' location compared to other industries. Hence, considering the amount of inflexibility involved, meeting the broadening prospect of oil demand and its derivates while maintaining high service-levels and efficiency is a major challenge in the petroleum industry.

The logistics function is only one of many areas that affect supply chain performance in the petroleum industry, integrated process management, information systems and information sharing, organizational restructuring, and cultural reorientation are as equally important. The need for integrated processes all the way from the procurement of raw materials to the delivery of the final product is crucial for a company's success. The industry lags in using integrated planning across the supply chain. This type of disintegration in the supply chain can increase the cost of acquiring crude oil, which will eventually affect gas prices for consumers. Also, due to the globalization of the petroleum industry supply chain, sophisticated information technology is essential for smooth information flow considering the complexity of the logistics network in such an industry. Companies' relationships in supply chain networks are directly related to the effective use of information technology. Sophisticated information technology is also essential for petroleum industries due to security needs. Petroleum companies ship a great deal of hazardous products, and supply chain partners (suppliers and customers) must be aware of the locations of each shipment at any point in time. This industry is already using wireless technology to track their shipments. The use of sophisticated information technology has been saving companies millions of dollars in the petroleum industry's supply chain yet has not received the optimized supply chain to cut the cost further.

The PetChem Industry processes petroleum products and is faced with the ongoing problem of continually scheduling the delivery, allocation and distribution, unloading, and temporary storage of petroleum products to its suppliers. Usually, the delivery of the products is by road transport such as oil tankers, trucks, etc. The distribution and allocation of petroleum products, usually from PetChem facilities, and the unloading and transfer is through a conduit system to storage warehouses to maintain inventory. Each vehicle has an arrival date, a specified number of days for unloading, and a demurrage charge if the unloading period is extended. Furthermore, each vehicle may be of a different size and carrying a different amount of products, and the composition of the products itself varies from vehicle to vehicle. The schedule for vehicle is further defined by the number of available vehicles in the market, the size of the berths and the transportation conduits and equipment available at each of the berths.

Many have attempted to solve scheduling, distribution and allocation problems using processes involving linear programming algorithms, in another attempt, to optimize this operation, a mixed-integer optimization model has been used which relies on time discretization. The problem involved bilinear equations due to mixing operations, however, the linearity in the form of a mixed-integer program has been maintained by replacing the bilinear terms with individual component flows. The linear programming-based branch and the bound method was applied to solve the model and several techniques such as priority branching and bounding and special ordered sets were implemented to reduce computation time. Further in coal industry, scheduling the delivery of coal to a series of incoming coal trains using a genetic algorithm has been provided in some solutions, where each of the coal trains corresponds to a coal recipient having different premium and penalty rates for energy yield, and contaminate specifications. The method is applied to a coal facility having a plurality of bins where the coal is of varying quality at the various bins and where the bins are grouped so that loading into trains must be done in succession. Also, genetic algorithms are known and multiple specific variations exist. Genetic algorithms have been employed in a number of applications which describes managing the development of oil or gas reserves using a neural network and genetic algorithm program to define a neural network topology. Drilling, completion, and stimulation of the reservoir is determined and applied based on hypothetical alternatives input to the topology and resulting outputs. Also, some of the known solutions provides supply optimization implementing genetic algorithm with serial operators for scheduling plan. Some of the other known solution provides supply optimization implementing genetic algorithm with serial operators for scheduling, routing and supply plan for crude supply to refinery. Further, some of the known solutions provide production optimization implementing genetic and ant colony optimization logic with distributed operators for production plan for equipment manufacturing. in the present problem of pet chem supply chain for scheduling, allocation and distribution, the problems dealing with incoming supply are at least semi- optimized using a serial genetic algorithm to arrive at a suitable feasible solution. The use of serial genetic algorithms allows for acceptable solutions to be generated in the typical time frame available to manufacturers. Currently, there is no solution available for distributed optimization, the problem to be solved involves optimized supply chain of scheduling, allocating, loading, unloading, transfer of the products from factory to end-users to minimize inventory holding cost as well as to maintain minimum supply at distributors end. Another limitation in the current technology is, there is no solution to determine the optimal day- wise product-wise depot/customer allocation information, along with the transportation mode and the desired quantity such that, the total cost comprising of freight and inventory is minimized and the desired serviceable quantity is met. Also a limitation in the current technology is, there is no solution to search for a better optimal solution that resulted in better savings in terms of cost. Another limitation in the current technology is, there is no alternate solution to the serial genetic algorithm (GA) operators such as selection, crossover, mutation and fitness function calculations which are expensive, therefore, implementation of the serial GA on any optimization problem with serial GA operators escalates the cost for optimization. Further a limitation in the current technology is that currently no solution can handle multi-type variable space including binary, continuous and integers to solve the optimization problem with increasing execution complexity. Therefore, to overcome such limitations there is a need in the art to provide a solution for optimizing supply chain efficiently and effectively.

The foregoing examples of the related art and limitations related therewith are intended to be illustrative and not exclusive. Other limitations of the related art will become apparent to those of skill in the art upon a reading of the specification and a study of the figures. Also, the limitation is not subject to the Petroleum and refining industry as this is only an illustrative example, this may be applicable to any similar industry where the scheduling, allocation and distribution problem in supply chain optimization exists.

SUMMARY OF THE DISCLOSURE

This section is provided to introduce certain objects and aspects of the present invention in a simplified form that are further described below in the detailed description. This summary is not intended to identify the key features or the scope of the claimed subject matter.

In order to overcome at least some of the drawbacks mentioned in the previous section and those otherwise known to persons skilled in the art, an object of the present invention is to provide a method and system for optimizing a supply chain. Another, object of the present invention is to provide method and system that can provide solution for distributed optimization, to optimize the supply chain of at least one of scheduling, allocating, loading, unloading and transfer of product(s) from factory to end-users etc., to minimize inventory holding cost as well as to maintain minimum supply at distributors end. Also, an object of the present invention is to provide method and system to intelligently identify solution to determine the optimal day-wise and/or product-wise depot/customer allocation information, along with transportation mode and desired quantity such that, the total cost comprising of freight and inventory is minimized and the desired serviceable quantity is met. Another object of the present invention is to provide solution that can help to search for a better optimal solution as compared to the current linear programming (LP) method savings in terms of cost. Also, an object of the present invention is to provide an alternate solution to serial GA (Genetic algorithm) operators such as selection, crossover, mutation and fitness function calculations which are expensive, therefore, implementation of the serial GA on any optimization problem with serial GA operators escalates the cost for optimization. Another object of the present invention is to provide a solution that can handle multi-type variable space including binary, continuous and integers to solve the optimization problem with increasing execution complexity. Also, an another object of the present invention is to provide a seamless enhancement of optimization analysis to provide informative output for precision and decision services on wireless network including but not limited to 5G/4G/3G/EV-Do/eHRPD capable technology. Another object of the present invention is to provide a seamless enhancement of optimization analysis to provide informative output for precision and decision services in user device(s) independent of whether a user device is 5G/4G/3G/EV-Do/eHRPD capable technology. Yet, another object of the present invention is to provide value-added services to manufacturers by improving the supply chain and saving cost.

Furthermore, in order to achieve the aforementioned objectives, the present invention provides a method and system for optimizing supply chain.

A first aspect of the present invention relates to the method for optimizing supply chain. The method comprises receiving, at a transceiver unit, a raw data for the supply chain. Further the method encompasses randomly generating, by a processing unit, a set of random networks based on the raw data. The method thereafter leads to determining, by the processing unit, a fitness score associated with each network of the set of random networks based at least on the raw data. Further the method encompasses selecting, by the processing unit, a first set of networks from the set of random networks based on the fitness score associated with the each network of the set of random networks. The method thereafter comprises performing, by the processing unit, at least one of a crossover technique on the first set of networks and a mutation technique on the set of random networks. The method further comprises generating, by the processing unit, a second set of networks based on performing at least one of the crossover technique and the mutation technique. Further the method encompasses analysing, by the processing unit, a change in an average fitness score of the second set of networks. The method thereafter encompasses identifying, by the processing unit, the second set of networks as a set of optimum networks based on the analysis of the change in the average fitness score of the second set of networks. Further the method comprises optimising, by the processing unit, the supply chain based on the set of optimum networks.

Another aspect of the present invention relates to a system for optimizing supply chain. The system comprises a transceiver unit, configured to receive, a raw data for the supply chain. The system further comprises a processing unit, configured to randomly generate, a set of random networks based on the raw data. The processing unit is further configured to determine, a fitness score associated with each network of the set of random networks based at least on the raw data. Further the processing unit is configured to select, a first set of networks from the set of random networks based on the fitness score associated with the each network of the set of random networks. The processing unit is thereafter configured to perform, at least one of a crossover technique on the first set of networks and a mutation technique on the set of random networks. Further the processing unit is configured to generate, a second set of networks based on performing at least one of the crossover technique and the mutation technique. The processing unit is thereafter configured to analyse, a change in an average fitness score of the second set of networks. Thereafter, the processing unit is configured to identify, the second set of networks as a set of optimum networks based on the analysis of the change in the average fitness score of the second set of networks. The processing unit is further configured to optimise, the supply chain based on the set of optimum networks.

BR!EF DESCRIPTION OF DRAWINGS The accompanying drawings, which are incorporated herein, and constitute a part of this disciosure, illustrate exemplary embodiments of the disclosed methods and systems in which like reference numerals refer to the same parts throughout the different drawings. Components in the drawings are not necessarily to scale, emphasis instead being placed upon clearly illustrating the principles of the present disclosure. Some drawings may indicate the components using block diagrams and may not represent the internal circuitry of each component. It will be appreciated by those skilled in the art that disciosure of such drawings includes disclosure of electrical components, electronic components or circuitry commonly used to implement such components.

Figure 1 iliustrates an exemplary, demand-supply flow of scheduling, allocation and distribution of the materials between manufacturers, depots and customers.

Figure 2 iliustrates an exemplary block diagram of a system [200] for optimizing supply chain, in accordance with exemplary embodiments of the present invention.

Figure 3 illustrates an exemplary method flow diagram [300], for optimizing supply chain, in accordance with exemplary embodiments of the present invention.

Figure 4 illustrates an exemplary distribution network for optimizing supply chain, in accordance with exemplary embodiments of the present invention.

The foregoing shall be more apparent from the following more detailed description of the disclosure.

DESCRIPTION OF THE INVENTION In the following description, for the purposes of explanation, various specific details are set forth in order to provide a thorough understanding of embodiments of the present disclosure. It will be apparent, however, that embodiments of the present disclosure may be practiced without these specific details. Several features described hereafter can each be used independently of one another or with any combination of other features. An individual feature may not address all of the problems discussed above or might address only some of the problems discussed above. Some of the problems discussed above might not be fully addressed by any of the features described herein.

The ensuing description provides exemplary embodiments only, and is not intended to limit the scope, applicability, or configuration of the disclosure. Rather, the ensuing description of the exemplary embodiments will provide those skilled in the art with an enabling description for implementing an exemplary embodiment. It should be understood that various changes may be made in the function and arrangement of elements without departing from the spirit and scope of the invention as set forth.

Also, it is noted that individual embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a sequence diagram, a data flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be re-arranged. A process is terminated when its operations are completed but could have additional steps not included in a figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc. When a process corresponds to a function, its termination can correspond to a return of the function to the calling function or the main function. Furthermore, embodiments may be implemented by hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. When implemented in software, firmware, middleware or microcode, the program code or code segments to perform the necessary tasks (e,g,, a computer-program product) may be stored in a machine-readable medium. A processorfs) may perform the necessary tasks.

The term "machine-readable storage medium'· ^' or "computer-readable storage medium" includes, but is not limited to, portable or non-portable storage devices, optical storage devices, and various other mediums capable of storing, containing, or carrying instruction(s) and/or data. A machine-readable medium may include a non-transitory medium in which data can be stored and that does not include carrier waves and/or transitory electronic signals propagating wirelessly or over wired connections. Examples of a non-transitory medium may include, but are not limited to, a magnetic disk or tape, optical storage media such as compact disk (CD) or digital versatile disk (DVD), flash memory, memory or memory devices. A computer-program product may include code and/or machine-executable instructions that may represent a procedure, a function, a subprogram, a program, a routine, a subroutine, a module, a software package, a class, or any combination of instructions, data structures, or program statements. A code segment may be coupled to another code segment or a hardware circuit by passing and/or receiving information, data, arguments, parameters, or memory contents. Information, arguments, parameters, data, etc. may be passed, forwarded, or transmitted via any suitable means including memory sharing, message passing, token passing, network transmission, etc.

The word "exemplary" and/or "demonstrative" is used herein to mean serving as an example, instance, or illustration. For the avoidance of doubt, the subject matter disclosed herein is not limited by such examples. In addition, any aspect or design described herein as "exemplary" and/or "demonstrative" is not necessarily to be construed as preferred or advantageous over other aspects or designs, nor is it meant to preclude equivalent exemplary structures and techniques known to those of ordinary skill in the art. Furthermore, to the extent that the terms "includes," "has," "contains," and other similar words are used in either the detailed description or the claims, such terms are intended to be inclusive— in a manner similar to the term "comprising" as an open transition word— without precluding any additional or other elements.

Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items. The terms “first", "second", "primary" and "secondary" are used to distinguish one element, set, data, object, step, process, function, activity or thing from another, and are not used to designate relative position, or arrangement in time or relative importance, unless otherwise stated explicitly. The terms "coupled", "coupled to", and "coupled with" as used herein each mean a relationship between or among two or more devices, apparatus, files, circuits, elements, functions, operations, processes, programs, media, components, networks, systems, subsystems, and/or means, constituting any one or more of (a) a connection, whether direct or through one or more other devices, apparatus, files, circuits, elements, functions, operations, processes, programs, media, components, networks, systems, subsystems, or means, (b) a communications relationship, whether direct or through one or more other devices, apparatus, files, circuits, elements, functions, operations, processes, programs, media, components, networks, systems, subsystems, or means, and/or (c) a functional relationship in which the operation of any one or more devices, apparatus, files, circuits, elements, functions, operations, processes, programs, media, components, networks, systems, subsystems, or means depends, in whole or in part, on the operation of any one or more others thereof.

The terms "communicate," and "communicating" and as used herein include both conveying data from a source to a destination, and delivering data to a communications medium, system, channel, network, device, wire, cable, fiber, circuit and/or link to be conveyed to a destination and the term "communication" as used herein means data so conveyed or delivered. The term "communications" as used herein includes one or more of a communications medium, system, channel, network, device, wire, cable, fiber, circuit and link. Moreover, terms like "user equipment" (LIE), "electronic device", "mobile station", "user device", "mobile subscriber station," "access terminal," "terminal," "smartphone," "smart computing device," "smart device", "device", "handset," and similar terminology refers to any electrical, electronic, electro-mechanical equipment or a combination of one or more of the above devices. Smart computing devices may include, voice and non-voice capable devices such as including but not limited to, a mobile phone, smart phone, virtual reality (VR) devices, augmented reality (AR) devices, pager, laptop, a general-purpose computer, desktop, personal digital assistant, tablet computer, mainframe computer, smart set top box (STB), smart speaker, smart fitness band, smart watches, or any other computing device as may be obvious to a person skilled in the art and required to implement the features of the present invention. In general, a smart computing device is a digital, user configured, computer networked device that can operate autonomously. A smart computing device is one of the appropriate systems for storing data and other private/sensitive information. The said device may operate at all the seven levels of ISO reference model, but the primary function is related to the application layer along with the network, session and presentation layer with any additional features of a touch screen, apps ecosystem, physical and biometric security, etc. Further, a 'smartphone' is one type of "smart computing device" that refers to the mobility wireless cellular connectivity device that allows end-users to use services on 2G, 3G, 4G, 5G and/or the like mobile broadband Internet connections with an advanced mobile operating system which combines features of a personal computer operating system with other features useful for mobile or handheld use. These smartphones can access the internet, have a touchscreen user interface, can run third-party apps including the capability of hosting online applications, music players and are camera phones possessing high-speed mobile broadband 4G LTE internet with video calling, hotspot functionality, motion sensors, mobile payment mechanisms and enhanced security features with alarm and alert in emergencies. Mobility devices may include smartphones, wearable devices, smart-watches, smart bands, wearable augmented devices, etc. For the sake of specificity, we will refer to the mobility device to both feature phone and smartphones in this disclosure but will not limit the scope of the disclosure and may extend to any mobility device in implementing the technical solutions. The above smart devices including the smartphone as well as the feature phone including !oT and the like devices enable the communication on the devices. Furthermore, the foregoing terms are utilized interchangeably in the subject specification and related drawings.

As used herein, a "processor" or "processing unit" includes one or more processors, wherein processor refers to any logic circuitry for processing instructions. A processor may be a general-purpose processor, a special -purpose processor, a conventional processor, a digital signal processor, a plurality of microprocessors, one or more microprocessors in association with a DSP core, a controller, a microcontroller, a low-end microcontroller, Application Specific Integrated Circuits, Field Programmable Gate Array circuits, any other type of integrated circuits, etc. Furthermore, the term “processor" as used herein includes, but is not limited to one or more computers, hardwired circuits, signal modifying devices and systems, devices and machines for controlling systems, centra! processing units, programmable devices and systems, systems on a chip, systems comprised of discrete elements and/or circuits, state machines, virtual machines, data processors, processing facilities and combinations of any of the foregoing. The processor may perform signal coding data processing, input/output processing, and/or any other functionality that enables the working of the system according to the present disclosure. More specifically, the processor or processing unit is a hardware processor. The term "processor" as used herein means processing devices, apparatus, programs, circuits, components, systems and subsystems, whether implemented in hardware, tangibly-embodied software or both, and whether or not programmable.

As used herein, "memory unit", "storage unit" and/or "memory" refers to a machine or computer-readable medium including any mechanism for storing information in a form readable by a computer or similar machine. For example, a computer-readable medium includes read-only memory ("ROM"), random access memory ("RAM"), magnetic disk storage media, optical storage media, flash memory devices or other types of machine-accessible storage media. The memory unit as used herein is configured to retain data, whether on a temporary or permanent basis, and to provide such retained data to various units to perform their respective functions.

As used herein the "Transceiver Unit" may include but not limited to a transmitter to transmit data to one or more destinations and a receiver to receive data from one or more sources. Further, the Transceiver Unit may include any other similar unit required to implement the features of the present invention. The transceiver unit may convert data or information to signals and vice versa for the purpose of transmitting and receiving respectively.

As disclosed in the background section the existing technologies have many limitations and in order to overcome at least some of the limitations of the prior known solutions, the present disclosure provides a solution for optimizing supply chain. More particularly, the present invention provides a solution that helps for distributed optimization, to optimize supply chain of at least one of a scheduling, allocating, loading, unloading, transfer of product(s) from factory to end-users to minimize inventory holding cost as well as to maintain minimum supply at distributors end. The present invention also provides improvements in optimization search methodologies applied to logistics optimization in supply chain technology for various application in domain of petrochemical agriculture, health and other allied industry. Furthermore, Gaussian Theorem references and Genetic Algorithm and system references may be taken for implementation of the features of the present invention. Furthermore, to optimize the supply chain, in an implementation, the present solutions encompasses receiving a raw data associated with at least one of a scheduling, allocation and distribution (i.e, the supply chain to be optimized). Thereafter such raw data is categorized as an entity data, in an implementation the entity data may include but not limited to a production data, a transportation related data such as rake and ship availability and cost etc. Also, in an implementation the entity data comprises a product level and a time level demand information, such as a freight cost from a source to a destination by each mode of transportation, dispatch capacities towards a DRC (the DRC indicates a duster of destination locations) on every day, a turnaround time (TAT), minimum and maximum trips in a month, capacity details, a last day position of a rake, a loading time of each rake, a transit Information form a source to a destination by each mode, a maximum capacity of each depot, a product level demand from a source to a destination on each day, an opening inventory data, a target month end dosing Inventory data, a target month end transit inventory data, a warehouse dispatch capacities on each day, a ship's departure schedule at each source, a product level production at each source on each day and the like information. Further this entity data is processed in parallel to provide an output for optimized planning solution. In an implementation, the present invention comprises of scenario, where a dynamic data and a few metadata tables are received as an input and the present solution thereafter generates optimized planning solution (such as dashboards, plots and CSV files) as output for stakeholders to analyze and take planning decisions.

Furthermore, the present invention provides optimization of supply chain at least by determining at least one of an optimal day-wise and/or product-wise depot/customer allocation information, transportation mode information and desired quantity such that, the total cost comprising of freight and inventory is minimized and the desired serviceable quantity is met. Also, the present invention provides technical advancement over the known solutions at least by proving an alternate solution to the serial GA and LP based operators such as selection, crossover, mutation and fitness function calculations which are expensive with an alternate solution proposed with the cost for optimization that can handle multitype variable space including binary, continuous and integers to solve the optimization problem with increasing execution complexity.

Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present disclosure.

Referring to Figure 2, an exemplary block diagram of a system [200] for optimizing supply chain is shown. The system [200] comprises at least one transceiver unit [202], at least one processing unit [204] and at least one storage unit [206], Also, all of the components/ units of the system [200] are assumed to be connected to each other unless otherwise indicated below. Also, in Fig. 2 only a few units are shown, however, the system [200] may comprise multiple such units or the system [200] may comprise any such number of said units, as required to implement the features of the present disclosure. Further, in an implementation, the system [200] may be present in a server device to implement the features of the present invention.

The system [200] is configured to optimize supply chain, with the help of the interconnection between the components/units of the system [200],

The transceiver unit [202] is configured to receive, a raw data for the supply chain to optimize the supply chain. The supply chain is related to at least one of scheduling, allocation and distribution. Therefore, the transceiver unit [202] is configured to receive, a raw data related to at least one of the scheduling, allocation and distribution in order to further optimize said at least one of the scheduling, allocation and distribution for the supply chain optimization. In an example, the transceiver unit [202] may configured to receive a data related to delivery of a product from a source A to a destination B as a raw data, wherein said data may further include but not limited to details of routes, details of delivery vehicle, schedule of delivery, load details and the like data associated with the delivery of said product. The transceiver unit [202] is configured to provide this data to the processing unit [204],

The processing unit [204] is configured to randomly generate, a set of random networks based on the raw data. In an implementation, each network of the set of random networks may comprise one or more parameters such as at least one of a stock-keeping unit [SKU)/a product, a source, a destination, a mode and a schedule (such as a day) associated with the raw data. Also, the processing unit [204] is configured to generated the set of random networks based on all the possible combination of the at least one of the stock-keeping unit (SKU)/the product, the source, the destination, the mode and the schedule. In an implementation the set of random networks is generated by firstly generating an initial set of random networks comprising one or more networks, wherein the initial set of random networks Is generated based on a linear solver. Thereafter, one or more new networks are randomly generated by adding a random noise to the one or more networks of the initial set of random networks, wherein the random noise may include an information associated with one or more networks that are similar to the one or more networks of the initial set of random networks and are in proximity to the one or more networks of the initial set of random networks. The set of random networks comprises the initial set of random networks and/or said randomly generated one or more new networks. Also, processing unit [204] is configured to identify a feasibility of the each network of the set of random networks based on one or more constraints. More particularly, feasibility of a network is measured based on its adherence to the one or more constraints of the supply chain to be optimized. In an implementation, the one or more constraints are driven by one or more required parameters and can be a mathematical translation of requirement constraints. A few exemplary constraints are provided as follows:

1. Rake capacity: The load capacity of rakes. The rakes are containers in a rail network. In an implementation the constraints associated with the rake capacity are that the rakes should be full, a partially filled rake/container cannot be shipped.

2. Closing stock constraints: The closing stock in a location on a specific day should be less than or equal to a target closing stock

3. Transit stock constraints: The transit stock in a location on a specific day should be less than or equal to a target transit stock

4. A parameter on percentage of allocation to domestic and export consumers. For instance, in an implementation, some product quantity is exported to international consumers and the rest is consumed domestically. In such implementation the constraints are to give preference to domestic consumers even though a transportation cost is higher as compared to international consumers.

5. Capacity constraints in the depots

6. Weekly and daily demand parameters and the customer satisfaction level

7. Limits in the maximum number of vehicles transiting on a particular day

8. Closing stock in depots should be positive

9. Limits in term of allocation quantity in destination

10. Closing stock constraints/limits in the plan/production units Further, once the feasibility of the each network of the set of random networks based on the one or more constraints is identified, the processing unit [204] is further configured to identify if the feasibility of one or more networks of the set of random networks is less than a feasibility threshold value. The processing unit [204] is thereafter configured to update the one or more networks of the set of random networks in an event if the feasibility of said one or more networks is less than the feasibility threshold value to make said one or more networks more feasible. Further, the processing unit [204] is configured to update the one or more networks with the feasibility less than the feasibility threshold value, by updating the one or more parameters (i.e. at least one of the (SKU)/the product, the source, the destination, the mode and the schedule) of said one or more networks to make said one or more networks more feasible.

Further, the processing unit [204] is configured to determine a fitness score associated with each network of the set of random networks based at least on the raw data. The fitness score encompasses a score indicating an associated cost of the each network, such that higher the fitness score lower will be the cost associated. Therefore, the processing unit [204] is configured to determine a cost associated with each network of the set of random networks based at least on the raw data. The fitness score/cost is further associated with at least one of a freight cost, an inventory cost and a transit cost. The freight cost associated with the each network of the set of random networks is based on at least one of a distance between a source and a destination and a mode of transport associated with said each network of the set of random networks. In an implementation, the freight cost may be directly proportional to the distance between the source and the destination. Also, in an implementation, one mode of transport (such as a road transport) may be associated with a lesser freight cost as compared to another mode of transport (such as a rail transport) for delivery of a specific good. The inventory/ inventory carrying cost associated with the each network of the set of random networks is based on at least one of a closing stock in a depot, a source produced materia! quantity and an interest rate incurred due to keeping an inventory. For instance, in an implementation, the inventory carrying cost may be directly proportional to at least one of the closing stock in the depot, the source produced material quantity and the interest rate incurred due to keeping the inventory. Further, the transit cost associated with the each network of the set of random networks is based on at least one of a transit quantity, a mode of transport, a transit time, a production quantity and an interest rate. For instance, in an implementation the transit cost may be directly proportional to at least one of the transit quantity, the transit time, the production quantity and the interest rate. Also, in another implementation, one mode of transport may be associated with a higher transit cost as compared to another mode of transport for delivery of a specific good. Furthermore, the fitness score/cost indicates a quality measure of a network such that a network that has a high cost (i.e. low fitness score) has a lower quality measure. Hence, the processing unit [204] helps in searching for a solution that renders most minimal cost.

The processing unit [204] is thereafter configured to select, a first set of networks from the set of random networks based on the fitness score associated with the each network of the set of random networks. Further, to select the first set of networks from the set of random networks, the processing unit [204] is firstly configured to select, a set of top N networks from the set of random networks based on the fitness score/cost associated with the each network of the set of random networks and thereafter the processing unit [204] is configured to generate, the first set of networks based on the set of top N networks. The set of top N networks comprises one or more networks from the set of random networks that are associated with high quality measure i.e. the set of fop N networks comprises the one or more networks with low cost (i.e. high fitness score). In an implementation, the processing unit [204] is configured to select the first set of networks from the set of random networks based on a combination of tournament and ranking selection methods where the one or more networks of the set of random networks are ranked based on their corresponding fitness score/cost in a manner that lower the cost (or higher the fitness score), higher is the rank. Further, considering an example, where if a set of random networks encompasses 1000 networks, the processing unit [204] in the given instance may be configured to rank said 1000 networks based on their fitness score/cost in a manner that lower the cost associated with a network higher is the rank of said network. Further, the processing unit [204] may be configured to select top 10 networks from the 1000 ranked networks (i.e. the 10 networks from the 1000 networks associated with lowest cost), as the first set of networks.

Also, the processing unit [204] is further configured to identify the feasibility of each network of the first set of networks based on the one or more constraints. The feasibility of the each network of the first set of networks is measured based on its adherence to the one or more constraints of the supply chain to be optimized. In an implementation, the feasibility of the each network of the first set of networks may be measured in a similar manner as that of measuring of the feasibility of the each network of the set of random networks. Also, in an implementation, once the feasibility of the each network of the first set of networks based on the one or more constraints is identified, the processing unit [204] is further configured to identify if the feasibility of one or more networks of the first set of networks is less than the feasibility threshold value. The processing unit [204] is thereafter configured to update the one or more networks of the first set of networks in an event if the feasibility of said one or more networks of the first set of networks is less than the feasibility threshold value, to make said one or more networks of the first set of networks more feasible. Furthermore, the processing unit [204] is configured to update the one or more networks of the first set of networks with the feasibility less than the feasibility threshold value, by updating one or more parameters (i.e. at least one of (SKU)/product, source, destination, mode and schedule) of said one or more networks, to make said one or more networks of the first set of networks more feasible.

Further the processing unit [204] is configured to perform, at least one of a crossover technique on the first set of networks and a mutation technique on the set of random networks. The processing unit [204] is further configured to generate, a second set of networks based on performing at least one of the crossover technique and the mutation technique. Furthermore, to generate the second set of networks based on performing the crossover technique, the processing unit [204] is configured to generate the second set of networks based on at ieast two networks of the first set of networks. In an example, to generate the second set of networks based on performing the crossover technique, the processing unit [204] is firstly configured to select at ieast two networks of the first set of networks and thereafter, the processing unit [204] generates at least one network based at Ieast on the one or more parameters of the at ieast two networks selected from the first set of networks. Further, the processing unit [204] is configured to generate the second set of networks based at Ieast on the at ieast one network generated based at ieast on the one or more parameters of the at ieast two networks selected from the first set of networks. More particularly, in the given example, the second set of networks encompasses at !east one or more networks generated based at Ieast on the one or more parameters of the at least two networks selected from the first set of networks. Also, each network of the second set of networks that is generated based on the at least two networks of the first set of networks have inherited one or more properties from said at Ieast two networks of the first set of networks. Furthermore, in an implementation the processing unit [204] is configured to generate one or more new networks from the at ieast two networks of the first set of networks based on performing one or more cross over operations on the at least two networks of the first set of networks, where each network from the at least two networks of the first set of networks is a combination of binary and real-valued parameter(s). And therefore, the processing unit [204] is configured to perform separate one or more cross over operations for the binary parameter(s) and the real-valued parameter(s) of the each network of the at least two networks of the first set of networks. In an implementation, the real-valued parameter(s) are crossed over using a combination of linear and blend methods and the binary parameter(s) are crossed over using a single point single bit cross over. Also, to generate the second set of networks based on performing the mutation technique, the processing unit [204] is configured to generate the second set of networks based on adding a random noise to one or more networks of the set of random networks. In an implementation, to generate the second set of networks based on adding the random noise to the one or more networks of the set of random networks, the processing unit [204] is firstly configured to take the one or more networks of the set of random networks as an input and thereafter the processing unit [204] adds random noise to the input features, to generate one or more new networks. Further, in the given implementation, the second set of networks is generated based at least on said one or more new networks generated based on addition of the random noise. More particularly, in the given implementation, the second set of networks encompasses at least the one or more new networks generated based on the addition of the random noise. The noise helps in capturing the variability of the input space, making the generation of the second set of networks based on mutation technique generalize and concentrate on a global solution instead of a local one.

Also, the processing unit [204] is further configured to identify the feasibility of each network of the second set of networks based on the one or more constraints. The feasibility of the each network of the second set of networks is measured based on its adherence to the one or more constraints of the supply chain to be optimized. In an implementation, the feasibility of the each network of the second set of networks may be measured in a similar manner as that of measuring of the feasibility of the each network of the set of random networks. Also, in an implementation, once the feasibility of the each network of the second set of networks based on the one or more constraints is identified, the processing unit [204] is further configured to identify if the feasibility of one or more networks of the second set of networks is less than the feasibility threshold value. The processing unit [204] is thereafter configured to update the one or more networks of the second set of networks in an event if the feasibility of said one or more networks of the second set of networks is less than the feasibility threshold value, to make said one or more networks of the second set of networks more feasible. Furthermore, the processing unit [204] is configured to update the one or more networks of the second set of networks with the feasibility less than the feasibility threshold value, by updating one or more parameters (i.e. at least one of (SKU)/product, source, destination, mode and schedule) of said one or more networks, to make said one or more networks of the second set of networks more feasible.

Furthermore, the processing unit [204] is also configured to generate the second set of networks based on the feasibility of the each network of the second set of networks. More particularly, each network of the second set of networks is associated with a feasibility equal to or greater than the feasibility threshold value, in an Implementation the processing unit [204] is configured to generate the second set of networks based on at least one of the one or more networks generated based on performing at least one of the crossover technique and the mutation technique, wherein such one or more networks generated based on performing at least one of the crossover technique and the mutation technique are associated with a feasibility equal to or greater than the feasibility threshold value. Once the second set of networks is generated, the processing unit [204] is configured to analyse, a change in an average fitness score of the second set of networks. Further to analyse the change in the average fitness score of the second set of networks, the processing unit [204], is firstly configured to generate, an average fitness score of the first set of networks and thereafter the processing unit [204] is configured to generate the average fitness score of the second set of networks. Thereafter the processing unit [204] is configured to analyse, the change in the average fitness score of the second set of networks based on a comparison of the average fitness score of the second set of networks with the average fitness score of the first set of networks. The processing unit [204] is thereafter configured to identify, the second set of networks as a set of optimum networks based on the analysis of the change in the average fitness score of the second set of networks. More particularly, the processing unit [204] is configured to identify the second set of networks as the set of optimum networks based on an identification of the change in the average fitness score of the second set of networks below a threshold level. The change in the average fitness score of the second set of networks below the threshold level indicates that average of all networks of the second set of networks does not change significantly as compared to that of the first set of networks. Therefore, in such instances where the average fitness score of the second set of networks is below the threshold level as compared to the first set of networks, the second set of networks is not changed significantly as compared to the first set of networks and therefore in said instances the second set of networks is the set of optimum networks.

Once the second set of networks is identified as the set of optimum networks, the processing unit [204] is configured to optimise, the supply chain based on the set of optimum networks. More particularly, the processing unit [204] is configured to optimize at least one of the scheduling, the allocation and the distribution based on the set of optimum networks. Further, processing unit [204] is configured to perform at least one action based on the optimisation of the supply chain. In an implementation the processing unit [204] is configured to provide an information based on the set of optimum networks, wherein said information is provided in at least one of one or more dashboards, one or more plots, one or more CSV files and such other format(s), to optimise the supply chain. Further the processing unit [204] is configured to perform at least one action based on the information encompassed in at least one of the one or more dashboards, the one or more plots, the one or more CSV files and the other such format(s). In an exemplary scenario, the one or more actions may include but not limited to at least one of maximizing coastal movement, minimizing the number of stockouts and maximizing margin by minimizing an inventory carrying cost and the freight cost. In one another scenario, the one or more actions may include but not limited to at least one of maximizing rail transport, minimizing the number of stockouts and maximizing the margin by minimizing the inventory carrying cost and the freight cost.

Also, in an implementation, prior to identifying the second set of networks as the set of optimum networks and in an event of an identification of the change in the average fitness score of the second set of networks above the threshold level, the processing unit [204] is configured to perform an iterative procedure to generate the set of optimum networks. More particu!ar!y, in the given implementation the processing unit [204] is configured to select, a first updated set of networks from the second set of networks based on a fitness score associated with each network of the second set of networks. In an implementation the first updated set of networks from the second set of networks is selected in a similar manner as that of the selection of the first set of networks from the set of random networks. Further the processing unit [204] is configured to perform, at least one of the crossover technique on the first updated set of networks and the mutation technique on the set of random networks. The processing unit [204] is then configured to generate, a second updated set of networks based on performing at least one of the crossover technique on the first updated set of networks and the mutation technique on the set of random networks. In an implementation the crossover technique on the first updated set of networks to generate the second updated set of networks is performed in a similar manner as that of performing the crossover technique on the first set of networks to generate the second set of networks. Also, the processing unit [204] is configured to identify, the feasibility of each network of the second updated set of networks based on the one or more constraints, in an implementation the second updated set of networks encompasses only network(s) which are associated with a feasibility equal to or greater than the feasibility threshold value. Further, the processing unit [204] is configured to identify if the second updated set of networks is the set of optimum networks, wherein in an implementation the identification of the second updated set of networks as the set of optimum networks is done in an similar manner as that of the identification of the second set of networks as the set of optimum networks. Also, in an event if the second updated set of networks is not identified as the set of optimum networks, the processing unit [204] is configured to continue the iteration to generate the set of optimum networks. Also, if the second updated set of networks is identified as the set of optimum networks, the processing unit [204] is configured to optimise, the supply chain based on the set of optimum networks. Also, the processing unit [204] is further configured to perform the at least one action based on the optimisation of the supply chain.

Referring to Figure 3 an exemplary method flow diagram [300], for optimizing supply chain, in accordance with exemplary embodiments of the present invention is shown. In an implementation the method is performed by the system [300], Further, in an implementation, the system [300] may be present in a server device to implement the features of the present invention. Also, as shown in Figure 3, the method starts at step [302],

At step [304] the method comprises receiving, at a transceiver unit [202], a raw data for the supply chain. The supply chain is related to at least one of scheduling, allocation and distribution. Therefore, the method encompasses receiving at the transceiver unit [202], a raw data related to at least one of the scheduling, allocation and distribution in order to further optimize said at least one of the scheduling, allocation and distribution for the supply chain optimization, in an example, the method may comprises receiving at the transceiver unit [202], a data related to delivery of a product A from a source X to a destination Y as a raw data, wherein said data may further include but not limited to details of mode of transportation, details of delivery vehicle, schedule of delivery, load details, production details and the like data associated with the delivery of said product A.

Next at step [306] the method comprises randomly generating, by a processing unit [204], a set of random networks based on the raw data. In an implementation, each network of the set of random networks may comprise one or more parameters such as at least one of a stock-keeping unit (SKU)/a product, a source, a destination, a mode and a schedule (such as a day) associated with the raw data. Also, the method encompasses generating by the processing unit [204], the set of random networks based on all the possible combination of the at least one of the stock-keeping unit (SKU)/the product, the source, the destination, the mode and the schedule. In an implementation the set of random networks is generated by firstly generating an initial set of random networks comprising one or more networks, wherein the initial set of random networks is generated based on a linear solver. Thereafter, one or more new networks are randomly generated by adding a random noise to the one or more networks of the initial set of random networks, wherein the random noise may include an information associated with one or more networks that are similar to the one or more networks of the initial set of random networks and are in proximity to the one or more networks of the initial set of random networks. The set of random networks comprises the initial set of random networks and/or said randomly generated one or more new networks.

The method further comprises identifying a feasibility of the each network of the set of random networks based on one or more constraints. More particularly, the method encompasses measuring feasibility of a network based on its adherence to the one or more constraints of the supply chain to be optimized. In an implementation, the one or more constraints are driven by one or more required parameters and can be a mathematical translation of requirement constraints. A few exemplary constraints are rake capacity constraints, closing stock constraints, transit stock constraints, a parameter on percentage of allocation to domestic and export consumers, dosing stock constraints/limits in plan/production units, limits in term of allocation quantity in destination, weekly and daily demand parameters, customer satisfaction level and the like parameters. After identifying feasibility of the each network of the set of random networks, the method encompasses identifying by the processing unit [204], if the feasibility of one or more networks of the set of random networks is less than a feasibility threshold value. Further the method comprises updating the one or more networks of the set of random networks in an event if the feasibility of said one or more networks is less than the feasibility threshold value to make said one or more networks more feasible. Furthermore the method encompasses updating the one or more networks with the feasibility less than the feasibility threshold value, by updating by the processing unit [204] the one or more parameters (i.e. at least one of the {SKU)/tbe product, the source, the destination, the mode and the schedule) of said one or more networks to make said one or more networks more feasible Further, at step [308] the method comprises determining, by the processing unit [204], a fitness score associated with each network of the set of random networks based at least on the raw data. The fitness score encompasses a score indicating an associated cost of the each network, such that higher the fitness score lower will be the cost associated. Therefore, the method encompasses determining by the processing unit [204], a cost associated 'with each network of the set of random networks based at least on the raw data. The fitness score/cost is further associated with at least one of a freight cost, an inventory cost and a transit cost. The freight cost associated with the each network of the set of random networks is based on at least one of a distance between a source and a destination and a mode of transport associated with said each network of the set of random networks. In an implementation, the freight cost may be directly proportional to the distance between the source and the destination. Also, in an implementation, one mode of transport may be associated with a lesser freight cost as compared to another mode of transport for delivery of a specific good. The inventory/ inventory carrying cost associated with the each network of the set of random networks is based on at least one of a dosing stock in a depot, a source produced material quantity and an interest rate incurred due to keeping an inventory. For instance, in an implementation, the inventory carrying cost may be directly proportional to at least one of the dosing stock in the depot, the source produced materia! quantity and the interest rate incurred due to keeping the inventory. Further, the transit cost associated with the each network of the set of random networks is based on at least one of a transit quantity, a mode of transport, a transit time, a production quantity and an interest rate. For instance, in an implementation the transit cost may be directly proportional to at least one of the transit quantity, the transit time, the production quantity and the interest rate. Also, in another implementation, one mode of transport may be associated with a higher transit cost as compared to another mode of transport for delivery of a specific good. Furthermore, the fitness score/cost indicates a quality measure of a network such that a network that has a high cost (i.e. low fitness score) has a lower quality measure. Therefore, the method helps in searching for a solution that renders most minimal cost.

Next, at step [310] the method comprises selecting, by the processing unit [204], a first set of networks from the set of random networks based on the fitness score associated with the each network of the set of random networks. Furthermore, the process of selecting, by the processing unit [204], a first set of networks from the set of random networks firstly comprises selecting, by the processing unit [204], a set of top N networks from the set of random networks based on the fitness score associated with the each network of the set of random networks. Thereafter said process further leads to generating, by the processing unit [204], the first set of networks based on the set of top N networks.

The set of top N networks comprises one or more networks from the set of random networks that are associated with high quality measure i.e. the set of top N networks comprises the one or more networks with low cost (i.e. high fitness score), in an implementation, the method encompasses selecting by the processing unit [204], the first set of networks from the set of random networks based on a combination of tournament and ranking selection methods, where the one or more networks of the set of random networks are ranked based on their corresponding fitness score/cost in a manner that lower the cost for higher the fitness score) of a network, higher is the rank of said network. Further, considering an example, where if a set of random networks encompasses 5000 networks, the method in the given instance may comprises ranking by the processing unit [204] said 5000 networks based on their fitness score/cost in a manner that lower the cost associated with a network higher is the rank of said network. Further, the method may comprises selecting by the processing unit [204], top 15 networks from the 5000 ranked networks (i.e. the 15 networks from the 5000 networks associated with lowest cost), as the first set of networks.

Also, the method further comprises identifying the feasibility of each network of the first set of networks based on the one or more constraints. The feasibility of the each network of the first set of networks is measured based on its adherence to the one or more constraints of the supply chain to be optimized. In an implementation, the feasibility of the each network of the first set of networks may be measured in a similar manner as that of measuring of the feasibility of the each network of the set of random networks. Also, in an implementation, once the feasibility of the each network of the first set of networks based on the one or more constraints is identified, the method further encompasses identifying by the processing unit [204], if the feasibility of one or more networks of the first set of networks is less than the feasibility threshold value. The method thereafter encompasses updating by the processing unit [204] the one or more networks of the first set of networks in an event if the feasibility of said one or more networks of the first set of networks is less than the feasibility threshold value, to make said one or more networks of the first set of networks more feasible. Furthermore, the method encompasses updating by the processing unit [204], the one or more networks of the first set of networks with the feasibility less than the feasibility threshold value, by updating one or more parameters (i.e. at least one of (SKU)/product, source, destination, mode and schedule) of said one or more networks, to make said one or more networks of the first set of networks more feasible.

Thereafter, at step [312] the method comprises performing, by the processing unit [204], at least one of a crossover technique on the first set of networks and a mutation technique on the set of random networks. Next, at step [314] the method comprises generating, by the processing unit [204], a second set of networks based on performing at least one of the crossover technique and the mutation technique. Also, the process of generating, by the processing unit [204], a second set of networks based on performing the crossover technique further comprising generating the second set of networks based on at least two networks of the first set of networks. In an example, to generate the second set of networks based on performing the crossover technique, the method firstly encompasses selecting by the processing unit [204], at least two networks of the first set of networks and thereafter, the method leads to generating by the processing unit [204], at least one network based at least on the one or more parameters of the at least two networks selected from the first set of networks. Further, the method encompasses generating by the processing unit [204], the second set of networks based at least on the at ieast one network generated based at least on the one or more parameters of the at least two networks selected from the first set of networks. More particularly, in the given example, the second set of networks encompasses at least one or more networks generated based at Ieast on the one or more parameters of the at Ieast two networks selected from the first set of networks. Also, each network of the second set of networks that is generated based on the at Ieast two networks of the first set of networks have inherited one or more properties from said at least two networks of the first set of networks. Furthermore, in an implementation the method encompasses generating by the processing unit [204], one or more new networks from the at least two networks of the first set of networks based on performing one or more cross over operations on the at least two networks of the first set of networks, where each network from the at least two networks of the first set of networks is a combination of binary and real-valued paramefer(s). And therefore, the method encompasses performing separately by the processing unit [204], one or more cross over operations for the binary parameter(s) and the real-valued parameter(s) of the each network of the at least two networks of the first set of networks. In an implementation, the real-valued parameter(s) are crossed over using a combination of linear and blend methods and the binary parameter(s) are crossed over using a single point single bit cross over.

Furthermore, the process of generating, by the processing unit [204], a second set of networks based on performing the mutation technique further comprises generating the second set of networks based on adding a random noise to one or more networks of the set of random networks. In an implementation, to generate the second set of networks based on adding the random noise to the one or more networks of the set of random networks, the method firstly encompasses taking by the processing unit [204], the one or more networks of the set of random networks as an input and thereafter the method via the processing unit [204] adds random noise to the input features, to generate one or more new networks. Further, in the given implementation, the second set of networks is generated based at least on said one or more new networks generated based on addition of the random noise. More particularly, in the given implementation, the second set of networks encompasses at least the one or more new networks generated based on the addition of the random noise. The noise helps in capturing the variability of the input space, making the generation of the second set of networks based on mutation technique generalize and concentrate on a global solution instead of a local one.

Thereafter, the method comprises identifying the feasibility of each network of the second set of networks based on the one or more constraints. The feasibility of the each network of the second set of networks is measured based on its adherence to the one or more constraints of the supply chain to be optimized. In an implementation, the feasibility of the each network of the second set of networks may be measured in a similar manner as that of measuring of the feasibility of the each network of the set of random networks. Also, in an implementation, once the feasibility of the each network of the second set of networks based on the one or more constraints is identified, the method further encompasses identifying by the processing unit [204], if the feasibility of one or more networks of the second set of networks is less than the feasibility threshold value. The method thereafter encompasses updating by the processing unit [204] the one or more networks of the second set of networks in an event if the feasibility of said one or more networks of the second set of networks is less than the feasibility threshold value, to make said one or more networks of the second set of networks more feasible. Furthermore, the method encompasses updating by the processing unit [204], the one or more networks of the second set of networks associated with the feasibility less than the feasibility threshold value, by updating one or more parameters (i.e. at least one of (SKU)/product, source, destination, mode and schedule) of said one or more networks, to make said one or more networks of the second set of networks more feasible.

Furthermore, the process of generating, by the processing unit [204], the second set of networks also comprises generating the second set of networks based on the feasibility of the each network of the second set of networks. More particularly, each network of the second set of networks is associated with a feasibility equal to or greater than the feasibility threshold value. In an implementation the method encompasses generating by the processing unit [204], the second set of networks based on at least one of the one or more networks generated based on performing at least one of the crossover technique and the mutation technique, wherein such one or more networks generated based on performing at least one of the crossover technique and the mutation technique are associated with a feasibility equal to or greater than the feasibility threshold value.

Next, once the second set of networks is generated, at step [316] the method comprises analysing, by the processing unit [204], a change in an average fitness score of the second set of networks. Also, the process of analysing, by the processing unit [204], a change in an average fitness score of the second set of networks firstly comprises generating, by the processing unit [204], an average fitness score of the first set of networks and thereafter the method/process leads to generating, by the processing unit [204], the average fitness score of the second set of networks. The process thereafter encompasses analysing, by the processing unit [204], the change in the average fitness score of the second set of networks based on a comparison of the average fitness score of the second set of networks with the average fitness score of the first set of networks.

Next, at step [318] the method comprises identifying, by the processing unit [204], the second set of networks as a set of optimum networks based on the analysis of the change in the average fitness score of the second set of networks. More particularly, the process of identifying, by the processing unit [204], the second set of networks as a set of optimum networks is based on an identification of the change in the average fitness score of the second set of networks below a threshold level. The change in the average fitness score of the second set of networks below the threshold level indicates that average of ail networks of the second set of networks does not change significantly as compared to that of the first set of networks. Therefore, in such instances where the average fitness score of the second set of networks is below the threshold level as compared to the first set of networks, the second set of networks is not changed significantly as compared to the first set of networks and therefore in said instances the second set of networks is the set of optimum networks.

Once the second set of networks is identified as the set of optimum networks, at step [320] the method comprises optimising, by the processing unit [204], the supply chain based on the set of optimum networks. More particularly, the method encompasses optimising, by the processing unit [204], at least one of the scheduling, the allocation and the distribution based on the set of optimum networks. Also, method further comprises performing by the processing unit [204], at least one action based on the optimisation of the supply chain. In an implementation the method comprises providing by the processing unit [204], an information based on the set of optimum networks, wherein said information is provided in at least one of one or more dashboards, one or more plots, one or more CSV files and such other format(s), to optimise the supply chain. Further the method encompasses performing by the processing unit [204], at least one action based on the information encompassed in at least one of the one or more dashboards, the one or more plots, the one or more CSV files and the other such format(s). In an exemplary scenario, the one or more actions may include but not limited to at least one of determination of ideal depot capacity, minimizing the number of stockouts and minimizing the cost.

Also, in an implementation, prior to identifying, by the processing unit [204], the second set of networks as the set of optimum networks and in an event of an identification of the change in the average fitness score of the second set of networks above the threshold level the method comprises performing an iterative procedure to generate the set of optimum networks. More particularly, in the given implementation the method encompasses selecting, by the processing unit [204], a first updated set of networks from the second set of networks based on a fitness score associated with each network of the second set of networks. In an implementation the first updated set of networks from the second set of networks is selected in a similar manner as that of the selection of the first set of networks from the set of random networks. The method thereafter leads to performing, by the processing unit [204], at least one of the crossover technique on the first updated set of networks and the mutation technique on the set of random networks. Further the method comprises generating, by the processing unit [204], a second updated set of networks based on performing at least one of the crossover technique on the first updated set of networks and the mutation technique on the set of random networks. In an implementation the crossover technique on the first updated set of networks to generate the second updated set of networks is performed in a similar manner as that of performing the crossover technique on the first set of networks to generate the second set of networks. The method thereafter encompasses identifying, by the processing unit [204], the feasibility of each network of the second updated set of networks based on the one or more constraints. In an implementation the second updated set of networks encompasses only network(s) which are associated with a feasibility equal to or greater than the feasibility threshold value. Further, the method encompasses Identifying by the processing unit [204], identify if the second updated set of networks is the set of optimum networks, wherein in an implementation the identification of the second updated set of networks as the set of optimum networks is done in an similar manner as that of the identification of the second set of networks as the set of optimum networks. Also, in an event if the second updated set of networks is not identified as the set of optimum networks, the method comprises continuing by the processing unit [204], the iteration to generate the set of optimum networks. Also, if the second updated set of networks is identified as the set of optimum networks, the method comprises optimizing by the processing unit [204], the supply chain based on the set of optimum networks. Also, the method further comprises performing by the processing unit [2.04], the at least one action based on the optimisation of the supply chain.

Thereafter, the method terminates at step [322],

Furthermore, an exemplary use case for optimizing a supply chain in a secondary distribution network of PetChem industry based on the implementation of the features of the present invention is provided as below: In an implementation, the supply chain of the PetChem industry which is to be optimized may be associated with a network for 5 plants, 50 depots and 70 customers spanning across 150 stock-keeping units (SKUs), wherein the SKUs belong to any one of the categories: Polyethylene (PE), Polypropylene (PP) and Polyvinyl Chloride (PVC). Also, an exemplary distribution network is shown in figure 4, where at [402] and [404], two sources/p!ants i.e. Plant 1 and Plant 2 are depicted, respectively. Thereafter, a depot is depicted at [406] and [408], wherein at depot [406] a storage [410] and at depot [408] a storage [412] is also depicted. Also, at each block of blocks Cl- C8, figure 4 depicts a customer. Further, at [414 A] to [414 M], figure 4 depicts various modes of transports to provide connectivity between different units (i.e. Plant(s), depot(s)/storage(s) and customer(s)) of the exemplary distribution network. Further, in an implementation for optimizing the supply chain, solution and objectives involves calculation of finer allocation at stock-keeping unit (5KU) level as compared to current coarser allocation of stocks in depot that should incorporate constraints related to ship and rail freight and truck limits.

Further, in an implementation the formulation (optimization of the supply chain) based on the features of the present invention involves a detailed definition of ail variahies/parameters, mathematical representation of constraint(s) and an objective function, wherein the variables may be as follows:

Also, the objective function may be as follows:

The objective is to minimize the overall cost. The cost is the fitness score of the network. The fitness score is given by C _tot . Therefore:

in the above constraint, 0.75 is considered as in an implementation at least 75% of a demand at a destination should be met.

● Max Number Rakes form a source(p!ant) on specific day in the above constraint, < 1 indicates that from a single source number of rails can be dispatched is either 0 or 1 on a given day, i.e. either no rakes get dispatched or only one rail gets dispatched on a single day at a single source.

● TAT is Turn Around Time (TAT) Constraint in the above constraint, < 1 indicates that once a rake is allocated from a source to a destination then till the TAT days, no other rake is allocated for that source destination combination. Therefore, it is either zero or one. Zero indicates on a day for a source destination combination no rake is allotted and one indicates a rake is allotted. ● NCR 2Days Constraint (where NCR indicates a region having a special relaxation for rakes, it has a two days of loading period, therefore no other rakes are allotted for two days)

Thus, the present invention provides a novel solution for optimizing supply chain. More particularly, the present invention provides a solution that helps for distributed optimization, to optimize supply chain of at least one of a scheduling, allocating, loading, unloading, transfer of product(s) from factory to end-users to minimize inventory holding cost as well as to maintain minimum supply at distributors end. The present invention also provides optimization of supply chain at least by determining at least one of an optimal day-wise and/or product-wise depot/customer allocation information, transportation mode information and desired quantity such that, the total cost comprising of freight and inventory is minimized and the desired serviceable quantity is met. Also, the present invention provides technical advancement over the known solutions at least by proving an alternate solution to the serial GA and S.P based operators such as selection, crossover, mutation and fitness function calculations which are expensive with an alternate solution proposed with the cost for optimization that can handle multitype variable space including binary, continuous and integers to solve the optimization problem with increasing execution complexity.

While considerable emphasis has been placed herein on the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the invention. These and other changes in the preferred embodiments of the invention will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter to be implemented merely as illustrative of the invention and not as limitation.