Algorithm-driven electric power storage and supply and demand matching optimization method and system

Abstract

The invention discloses an algorithm-driven electric power storage and supply and demand matching optimization method and system, and relates to the technical field of intelligent optimization scheduling, and the method comprises the following steps: 1, obtaining the material information of storage, the material information comprising the type and number of materials; step 2, constructing a storage optimization algorithm model with the goal of maximizing revenue and meeting balance of material demands of users, and calculating the stock quantity of materials at a set time point in the future according to the storage optimization algorithm model; 3, comparing the stock quantity of the materials at the future set time point with the existing quantity in the material information, and determining the purchase quantity of the materials according to the difference; and step 4, generating a purchase order according to the purchase type, the purchase quantity and the required purchase completion time, and performing material purchase according to the purchase order. According to the scheme, the stock quantity of the materials at the set time point in the future can be accurately calculated in real time through the storage optimization algorithm model, manual intervention and subjective judgment are greatly reduced, and the efficiency and accuracy of material purchasing are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent optimization scheduling, in particular to an algorithm-driven power warehousing and supply-demand matching optimization method and system. BACKGROUND

[0002] In the material management and warehousing operation of power enterprises, ensuring the timely supply of materials and reasonable inventory level is crucial for maintaining the stability of production operation and improving economic efficiency. However, in the current warehousing management practice, there are some problems that need to be solved, which limit the efficiency and benefit of material management of power enterprises.

[0003] Firstly, the traditional supply-demand matching method often relies on simple inventory monitoring and manual experience judgment. This method is not capable of dealing with complex and variable market demand and supply chain environment. For example, seasonal fluctuations in market demand, sudden demand surges caused by unexpected events, and the substitution and correlation between different materials, all of these factors will pose a serious challenge to the traditional manual procurement supply-demand matching method. Due to the lack of scientific prediction and planning, enterprises often have difficulty in accurately grasping the demand for materials and the timing of procurement, leading to problems such as inventory accumulation, excessive capital occupation, or material shortage.

[0004] Secondly, although the existing material warehousing management system can realize real-time monitoring and recording of inventory, it still has deficiencies in the optimization of material allocation and procurement decision-making. These systems often lack the support of optimization algorithms and cannot comprehensively consider factors such as the depreciation cost of materials, warehousing cost, future demand, and the time value of funds, so as to develop the optimal warehousing and procurement strategy. For example, in the case of high material depreciation cost, enterprises may need to reduce inventory to reduce depreciation loss; while in the case of low warehousing cost, enterprises can appropriately increase inventory to reduce procurement frequency and cost. However, the existing material warehousing management system often cannot accurately assess the impact of these factors on material management and economic efficiency, leading to the inability of enterprises to make optimal decisions.

[0005] Finally, if enterprises only focus on revenue in the process of material procurement and ignore the diversity of market demand and the difference of user demand, it is likely to lead to the problem of single material variety. This single procurement strategy, although it may seem to reduce procurement cost and management difficulty in the short term, actually hides huge risks. Because user demand is diverse and constantly changing, different user groups have different requirements for the type, specification, and performance of materials. If enterprises only focus on revenue and ignore these differentiated demands, it will lead to a serious disconnection between material supply and actual user demand. SUMMARY

[0006] The present application aims to overcome the defects in the prior art that the procurement of materials relies on simple inventory monitoring and manual experience judgment, which cannot accurately match the procurement demand with the storage situation, increases the cost of material procurement, reduces the efficiency of material procurement, and the material procurement strategy is relatively single. The present application provides an algorithm-driven power storage and supply-demand matching optimization method and system, which determines the material inventory quantity at a future set time through a storage optimization algorithm model, and then matches the procurement quantity of materials, thereby improving the procurement efficiency of materials.

[0007] The present application aims to overcome the defects in the prior art that the procurement of materials relies on simple inventory monitoring and manual experience judgment, which cannot accurately match the procurement demand with the storage situation, increases the cost of material procurement, reduces the efficiency of material procurement, and the material procurement strategy is relatively single. The present application provides an algorithm-driven power storage and supply-demand matching optimization method and system, which determines the material inventory quantity at a future set time through a storage optimization algorithm model, and then matches the procurement quantity of materials, thereby improving the procurement efficiency of materials. The present application aims to overcome the defects in the prior art that the procurement of materials relies on simple inventory monitoring and manual experience judgment, which cannot accurately match the procurement demand with the storage situation, increases the cost of material procurement, reduces the efficiency of material procurement, and the material procurement strategy is relatively single. The present application provides an algorithm-driven power storage and supply-demand matching optimization method and system, which determines the material inventory quantity at a future set time through a storage optimization algorithm model, and then matches the procurement quantity of materials, thereby improving the procurement efficiency of materials. Step 1, obtaining the material information of the storage, the material information including the type and quantity of the materials; Step 2, constructing a storage optimization algorithm model with the goal of maximizing the revenue and balancing the demand of users for materials, and calculating the inventory quantity of materials at a future set time point according to the storage optimization algorithm model; Step 3, comparing the inventory quantity of materials at the future set time point with the existing quantity in the material information, and determining the procurement quantity of materials according to the difference; Step 4, generating a procurement order for the procurement type, procurement quantity and demand procurement completion time, and performing material procurement according to the procurement order.

[0008] The materials need to be stored in the warehouse after procurement, and the cost of the materials also needs to consider the cost of storage and the cost of depreciation of the materials over time; at the same time, the total capacity of the warehouse is fixed, and the capacity of the storage also needs to be considered when the materials are procured. Therefore, the present application designs a storage optimization algorithm model with the goal of maximizing the revenue, which can calculate the warehouse inventory quantity at a future set time point, and relevant personnel can perform material procurement according to the warehouse inventory quantity to ensure efficient operation and cost control of the storage.

[0009] As a preferred embodiment, step 2 is specifically: obtaining the depreciation cost, storage cost and demand quantity of the materials at a future set time point; constructing a target function with the goal of maximizing the revenue based on the depreciation cost, storage cost and demand quantity of the materials at a future set time point; solving the target function to determine the inventory quantity of the materials at a future set time point; determining whether the inventory quantity of the materials at a future set time point meets the demand of users for materials, if yes, jumping to step 3, if not, re-solving the target function until the demand of users for materials is met.

[0010] In the design of the present solution, the warehouse optimization algorithm model considers three parameters: the depreciation cost of the materials, the warehouse cost, and the demand for the materials at a future set time point. The value of the materials will depreciate over time, and the warehouse cost will also increase over time. The demand for the materials at a future set time point can be predicted based on historical data. By adjusting the warehouse optimization algorithm model through the three parameters, the warehouse optimization algorithm can be more logical and maximize the revenue value.

[0011] The demand for the materials of the user at a future set time point can also be obtained through a prediction model based on historical data. For time-varying material demand, a time series model can be used to accurately calculate it. For non-time-varying material demand, the future demand can also be obtained based on the historical trend of material demand.

[0012] When solving the warehouse optimization algorithm model, it is easy to cause a conflict between the revenue and the user's material demand. Therefore, when solving the objective function again, it can be appropriately considered that not all user material demands are met, or the satisfaction degree of the user's material demand is greater than a set threshold.

[0013] As a preferred embodiment, the algorithm-driven power warehouse and supply-demand matching optimization method also obtains the time value of the funds, and the parameter of the objective function also includes the time value of the funds.

[0014] As a preferred embodiment, the objective function satisfies an inventory quantity constraint, and the inventory quantity constraint is that the inventory quantity of the materials does not exceed the maximum inventory capacity of the materials, and the total inventory quantity of all materials does not exceed the maximum capacity of the warehouse.

[0015] As a preferred embodiment, the objective function is solved by a genetic algorithm, specifically: Initialize the population, define a coding method for each possible combination of the inventory quantity of the materials, and randomly generate several solutions as the initial population; Calculate the fitness value of each individual in the objective function according to the objective function, and select parent individuals for mating according to the fitness value of the individual; Perform a cross operation on the selected parent individuals to generate child individuals; Replace some or all of the parent individuals with child individuals to form a new generation population; Repeat the selection, cross, and mutation operations until a preset number of iterations is reached or a convergence condition is met; In the last generation population, select the individual with the highest fitness value as the optimal solution, and decode the coding method of the optimal solution to obtain the solution to the objective function.

[0016] As preferred, after the process of cross operation on the selected parent individual to generate offspring individual, mutation operation is further performed on the offspring individual to change its gene value at a set probability, so as to introduce new solution space.

[0017] As preferred, the algorithm-driven power warehouse and supply-demand matching optimization method solves the objective function by an annealing algorithm, specifically: An initial temperature and a temperature reduction rate are set, and then an initial solution is randomly generated, the initial solution being an initial inventory quantity configuration of the future set tongue tip point material; The yield value of the objective function corresponding to the initial solution is calculated; The inventory quantity of the material is randomly adjusted to generate a new solution, and then the yield value of the objective function corresponding to the new solution is calculated, if the yield value of the objective function corresponding to the new solution is better than that of the initial solution, the new solution is accepted as the current solution, if the yield value of the objective function corresponding to the new solution is not better than that of the initial solution, the new solution is accepted with a simulated annealing acceptance probability; The current temperature is reduced by the set temperature reduction rate, and then a new acceptance probability is generated; The new solution is repeatedly generated until the temperature is reduced to a certain preset termination temperature or a preset iteration number is reached, and the optimal solution encountered in the iteration process is recorded and updated, the optimal solution being the demand quantity of the material at the future set time point.

[0018] As preferred, the acceptance probability is , wherein, is the difference between the objective function values of the new and old solutions, T is the current temperature.

[0019] An algorithm-driven power warehouse and supply-demand matching optimization system, comprising: A material information acquisition module for acquiring material information of the warehouse, the material information including the type and quantity of the material; A warehouse optimization algorithm model construction module for constructing a warehouse optimization algorithm model with the highest yield as the target, and calculating the inventory quantity of the material at the future set time point according to the warehouse optimization algorithm model; A purchase quantity determination module for comparing the inventory quantity of the material at the future set time point with the existing quantity in the material information, and determining the purchase quantity of the material according to the difference; A purchase order generation and execution module for generating a purchase order of the purchase type, purchase quantity and demand completion time of the purchase, and purchasing the material according to the purchase order.

[0020] As preferred, the warehouse optimization algorithm model construction module specifically comprises: A cost and demand quantity acquisition unit for acquiring the depreciation cost, warehouse cost and demand quantity of the material at the future set time point; The objective function construction unit is used to construct an objective function with the goal of maximizing profits, based on the depreciation cost of materials, storage costs, and the demand for materials at a future set time point. The objective function solving unit is used to solve the objective function and determine the inventory quantity of materials at a future set time point.

[0021] The beneficial effects of this invention are: this solution can calculate the quantity of material inventory at a future set time point in real time and accurately through the warehouse optimization algorithm model, which greatly reduces manual intervention and subjective judgment, and improves the efficiency and accuracy of material procurement. This solution aims to balance maximizing profits with meeting users' material needs. By constructing and solving an objective function, the optimal inventory level can be determined. This avoids excessive inventory buildup and capital tied up, while ensuring timely supply of materials and meeting users' actual needs. Attached Figure Description

[0022] Figure 1 This is a flowchart of the present invention. Detailed Implementation

[0023] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0024] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0025] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0026] Example: An algorithm-driven optimization method for power storage and supply-demand matching, such as Figure 1 As shown, it includes the following steps: Step 1: Obtain information on the stored materials, including the type and quantity of materials. Step 2: Construct a warehouse optimization algorithm model with the goal of maximizing profits and balancing user material needs, and calculate the inventory quantity of materials at a future set time point based on the warehouse optimization algorithm model. Step 3: Compare the inventory quantity of materials at the future set time point with the existing quantity in the material information, and determine the purchase quantity of materials based on the difference. Step 4: Generate a purchase order by specifying the type of purchase, quantity, and required completion time, and then procure materials based on the purchase order.

[0027] After procurement, materials need to be stored in a warehouse. The cost of these materials must consider both storage costs and the depreciation of the materials over time. Furthermore, the total warehouse capacity is fixed, and this capacity must also be considered during procurement. Therefore, this solution designs a warehouse optimization algorithm model with the goal of maximizing profitability. This model can calculate the warehouse inventory at a predetermined future time, allowing relevant personnel to procure materials based on this inventory level, ensuring efficient warehouse operation and cost control.

[0028] Step 2 specifically includes: The depreciation cost of acquiring resources, storage costs, and the demand for resources at a predetermined future time. Construct an objective function with the goal of maximizing profits, taking into account the depreciation cost of goods, storage costs, and the demand for goods at a predetermined future time. Solve the objective function to determine the inventory quantity of materials at a future set time point; Determine whether the inventory quantity of materials at a future set time point meets the user's material needs. If it does, proceed to step 3. If not, recalculate the objective function until the user's material needs are met.

[0029] In this design, the warehousing optimization algorithm model considers three parameters: the depreciation cost of goods, warehousing cost, and the demand for goods at a future set time point. The value of goods depreciates over time, while warehousing costs also increase over time. The demand for goods at a future set time point can be predicted based on historical data. Adjusting the warehousing optimization algorithm model by these three parameters makes the algorithm more logical and maximizes the profit value.

[0030] The material needs of users at a future set time point can also be derived from historical data through prediction models. Material needs that change over time can be accurately calculated through time-series models, while material needs that do not change over time can be derived from the historical trends of material needs to predict future needs.

[0031] In this embodiment, the time series model can be calculated using an ARIMA model or an LSTM model. Historical material demand data is used as input, and by training and optimizing the time series model, a model that can accurately predict future material demand can be obtained.

[0032] When solving the warehouse optimization algorithm model, it is easy to cause a contradiction between revenue and user material needs. Therefore, when resolving the objective function, it is appropriate to consider not satisfying all user material needs, or satisfying user material needs to a degree greater than a set threshold.

[0033] The algorithm-driven optimization method for power storage and supply-demand matching also obtains the time value of money, and the parameters of the objective function also include the time value of money parameter.

[0034] The objective function satisfies the inventory constraint, which states that the inventory of a material does not exceed its maximum inventory capacity, and the total inventory of all materials does not exceed the maximum storage capacity.

[0035] The objective function is solved using a genetic algorithm, specifically as follows: Initialize the population by defining an encoding method for each possible combination of inventory quantities of materials, and randomly generate several solutions as the initial population. The fitness value of each individual within the objective function is calculated based on the objective function, and parent individuals are selected for mating based on the individual's fitness value. Perform a crossover operation on the selected parent individuals to generate child individuals; A new generation of individuals is formed by replacing some or all of the parent individuals with offspring. Repeat the selection, crossover, and mutation operations until the preset number of iterations is reached or the convergence condition is met; In the last generation of the population, the individual with the highest fitness is selected as the optimal solution, and decoding the encoding of the optimal solution is the solution to the objective function.

[0036] After performing a crossover operation on the selected parent individuals to generate offspring individuals, a mutation operation is also performed on the offspring individuals to change their gene values ​​with a set probability, thereby introducing a new solution space.

[0037] Specifically, in this embodiment, the warehouse contains three types of materials: A, B, and C. Currently, the quantities of these three materials in the warehouse are 100 units, 150 units, and 200 units, respectively. The maximum capacity of the warehouse is 1000 units. The predicted demand for these three materials in the next month is 120 units, 180 units, and 250 units, respectively. The depreciation cost of the materials, the storage cost, and the time value of money are known.

[0038] The specific steps for solving the objective function using a genetic algorithm are as follows: Using real number encoding, the inventory quantity of each material is used as a gene, and the inventory quantities of three materials form an individual, i.e. a solution. 50 individuals are randomly generated, and the gene value (i.e. inventory quantity) of each individual is randomly selected within a reasonable range.

[0039] The fitness value of each individual is calculated based on the objective function. The objective function considers the depreciation cost of goods, storage costs, future demand, and the time value of money, and its specific form is as follows: Fitness=Revenue−Depreciation Cost−Storage Cost−Opportunity Cost Where Fitness is the objective function, Revenue is sales revenue (calculated based on future demand and current market price), Depreciation Cost is the cost of material depreciation, Storage Cost is the cost of warehousing, and Opportunity Cost is the time value of money.

[0040] The roulette wheel selection strategy is adopted, and parent individuals are selected for mating based on their fitness values. A single-point crossover method is used, where a crossover point is randomly selected, and gene segments of two parent individuals are exchanged. A certain gene value of an individual is randomly changed with a certain probability, and the parent individual with the lowest fitness value is replaced by the offspring individual to form a new generation of population.

[0041] The algorithm is considered to have converged and the iteration count is set to 100. If the fitness value of the best individual does not change by more than 1% in 10 consecutive iterations, the algorithm stops iterating. In the last generation of the population, the individual with the highest fitness value is selected as the optimal solution. The optimal solution is the optimal combination of inventory quantities for each type of material in the next month.

[0042] The optimal solution obtained through the genetic algorithm is as follows: the inventory quantity of material A is 110 units, the inventory quantity of material B is 175 units, and the inventory quantity of material C is 240 units. Given that the user's material requirements are 100 units of material A, 170 units of material B, and 220 units of material C, the optimal solution satisfies the user's material requirements.

[0043] In some embodiments, if the inventory quantity of materials at a future set time point does not meet the user's material needs, the objective function is re-solved, and a new optimal solution is calculated by adjusting the weights of depreciation cost and storage cost, and then it is determined whether the new optimal solution meets the user's material needs; alternatively, other solutions in the genetic algorithm iteration process can be used as the new optimal solution.

[0044] If, after multiple attempts, the objective function still fails to meet the user's material needs, then it is determined whether the satisfaction level of the user's material needs exceeds a set threshold. If it exceeds the set threshold, it is the optimal solution for the objective function. The satisfaction level is derived from the material's satisfaction rate combined with the material's importance coefficient; the more important the material, the higher the threshold for its satisfaction level.

[0045] When considering satisfaction levels, the demand for the material at the next point in time can be calculated to determine the demand trend. If the demand trend is increasing or remains at a high level, the satisfaction level should be appropriately increased; if the demand trend is decreasing, the satisfaction level should also be appropriately increased. This approach maximizes revenue while ensuring the existence of an optimal solution to the objective function.

[0046] An algorithm-driven power storage and supply-demand matching optimization system includes: The material information acquisition module is used to acquire material information in the warehouse, including the type and quantity of materials. The warehouse optimization algorithm model building module is used to build a warehouse optimization algorithm model with the goal of maximizing profits, and to calculate the inventory quantity of materials at a future set time point based on the warehouse optimization algorithm model. The procurement quantity determination module is used to compare the inventory quantity of materials at a future set time point with the existing quantity in the material information, and determine the procurement quantity of materials based on the difference. The purchase order generation and execution module is used to generate purchase orders by specifying the type of purchase, quantity of purchase, and required completion time of purchase, and to procure materials based on the purchase orders.

[0047] The warehouse optimization algorithm model construction module specifically includes: The cost and demand acquisition unit is used to acquire the depreciation cost of materials, storage costs, and the demand for materials at a future set time point. The objective function construction unit is used to construct an objective function with the goal of maximizing profits, based on the depreciation cost of materials, storage costs, and the demand for materials at a future set time point. The objective function solving unit is used to solve the objective function and determine the inventory quantity of materials at a future set time point.

[0048] Example 2: An algorithm-driven optimization method for power warehousing and supply-demand matching is proposed. Its principle and implementation are basically the same as in Example 1, except that the algorithm-driven optimization method for power warehousing and supply-demand matching solves the objective function using an annealing algorithm. Specifically: Set the initial temperature and cooling rate, and then randomly generate an initial solution. The initial solution is the initial inventory quantity configuration of the future food supplies. Calculate the payoff value of the objective function corresponding to the initial solution; Randomly adjust the inventory quantity of materials to generate a new solution. Then calculate the profit value of the objective function corresponding to the new solution. If the profit value of the objective function corresponding to the new solution is better than the initial solution, the new solution is accepted as the current solution. If the profit value of the objective function corresponding to the new solution is not better than the initial solution, the new solution is accepted with the acceptance probability of simulated annealing. The set cooling rate lowers the current temperature, and then a new acceptance probability is generated; New solutions are generated repeatedly until the temperature drops to a preset termination temperature or the preset number of iterations is reached. During the iteration process, the best solution encountered is recorded and updated. The best solution is the required amount of materials at a future set time point.

[0049] The acceptance probability is ,in, It is the difference between the objective function values ​​of the old and new solutions. T This is the current temperature.

[0050] In this embodiment, the initial temperature is set to 1000, the cooling rate α = 0.95, the termination temperature is Tf = 1, and the number of iterations is set to 1000.

[0051] The warehouse contains three types of materials: A, B, and C. The current inventory quantities are 100 units, 150 units, and 200 units, respectively. An initial solution is randomly generated, with the inventory quantity of material A being 110 units, material B being 160 units, and material C being 230 units.

[0052] Calculate the revenue value corresponding to the initial solution based on the objective function, and then randomly adjust the inventory quantity of one or more materials to generate a new solution: adjust the inventory quantity of material A to 115 units, keep material B unchanged, and adjust material C to 225 units. Calculate the revenue value corresponding to the new solution and compare it with the revenue value of the initial solution. If the revenue of the new solution is better than that of the initial solution, the new solution is directly accepted as the current solution. If the revenue of the new solution is not better than that of the initial solution, the acceptance probability is calculated. If the randomly generated number is less than the acceptance probability P, the new solution is accepted.

[0053] The current temperature is reduced by the cooling rate α, and a new acceptance probability is generated. A new solution is generated and evaluated. The new solution is accepted or the current solution is kept. The iterative process continues until the temperature is reduced to the preset termination temperature Tf or the preset number of iterations is reached.

[0054] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the methods according to the embodiments of this application.

[0055] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein.

[0056] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. An algorithm-driven optimization method for power storage and supply-demand matching, characterized in that, Includes the following steps: Step 1: Obtain information on the stored materials, including the type and quantity of materials. Step 2: Construct a warehouse optimization algorithm model with the goal of maximizing profits and balancing user material needs, and calculate the inventory quantity of materials at a future set time point based on the warehouse optimization algorithm model. Step 3: Compare the inventory quantity of materials at the future set time point with the existing quantity in the material information, and determine the purchase quantity of materials based on the difference. Step 4: Generate a purchase order by specifying the type of purchase, quantity, and required completion time, and then procure materials based on the purchase order.

2. The algorithm-driven power storage and supply-demand matching optimization method according to claim 1, characterized in that, Step 2 specifically includes: The depreciation cost of acquiring resources, storage costs, and the demand for resources at a predetermined future time. Construct an objective function with the goal of maximizing profits, taking into account the depreciation cost of goods, storage costs, and the demand for goods at a predetermined future time. Solve the objective function to determine the inventory quantity of materials at a future set time point; Determine whether the inventory quantity of materials at a future set time point meets the user's material needs. If it does, proceed to step 3. If not, recalculate the objective function until the user's material needs are met.

3. The algorithm-driven power storage and supply-demand matching optimization method according to claim 2, characterized in that, It also obtains the time value of money, and the parameters of the objective function also include the time value of money parameter.

4. The algorithm-driven power storage and supply-demand matching optimization method according to claim 2 or 3, characterized in that, The objective function satisfies the inventory constraint, which states that the inventory of a material does not exceed its maximum inventory capacity, and the total inventory of all materials does not exceed the maximum storage capacity.

5. The algorithm-driven power storage and supply-demand matching optimization method according to claim 2, characterized in that, The objective function is solved using a genetic algorithm, specifically as follows: Initialize the population by defining an encoding method for each possible combination of inventory quantities of materials, and randomly generate several solutions as the initial population. The fitness value of each individual within the objective function is calculated based on the objective function, and parent individuals are selected for mating based on the individual's fitness value. Perform a crossover operation on the selected parent individuals to generate child individuals; A new generation of individuals is formed by replacing some or all of the parent individuals with offspring. Repeat the selection, crossover, and mutation operations until the preset number of iterations is reached or the convergence condition is met; In the last generation of the population, the individual with the highest fitness is selected as the optimal solution, and decoding the encoding of the optimal solution is the solution to the objective function.

6. The algorithm-driven power storage and supply-demand matching optimization method according to claim 5, characterized in that, After performing a crossover operation on the selected parent individuals to generate offspring individuals, a mutation operation is also performed on the offspring individuals to change their gene values ​​with a set probability, thereby introducing a new solution space.

7. The algorithm-driven power storage and supply-demand matching optimization method according to claim 2, characterized in that, The objective function is solved using the annealing algorithm, specifically as follows: Set the initial temperature and cooling rate, and then randomly generate an initial solution. The initial solution is the initial inventory quantity configuration of the future food supplies. Calculate the payoff value of the objective function corresponding to the initial solution; Randomly adjust the inventory quantity of materials to generate a new solution. Then calculate the profit value of the objective function corresponding to the new solution. If the profit value of the objective function corresponding to the new solution is better than the initial solution, the new solution is accepted as the current solution. If the profit value of the objective function corresponding to the new solution is not better than the initial solution, the new solution is accepted with the acceptance probability of simulated annealing. The set cooling rate lowers the current temperature, and then a new acceptance probability is generated; New solutions are generated repeatedly until the temperature drops to a preset termination temperature or the preset number of iterations is reached. During the iteration process, the best solution encountered is recorded and updated. The best solution is the required amount of materials at a future set time point.

8. The algorithm-driven power storage and supply-demand matching optimization method according to claim 7, characterized in that, The acceptance probability is ,in, It is the difference between the objective function values ​​of the old and new solutions. T This is the current temperature.

9. An algorithm-driven power storage and supply-demand matching optimization system, characterized in that, include: The material information acquisition module is used to acquire material information in the warehouse, including the type and quantity of materials. The warehouse optimization algorithm model building module is used to build a warehouse optimization algorithm model with the goal of maximizing profits, and to calculate the inventory quantity of materials at a future set time point based on the warehouse optimization algorithm model. The procurement quantity determination module is used to compare the inventory quantity of materials at a future set time point with the existing quantity in the material information, and determine the procurement quantity of materials based on the difference. The purchase order generation and execution module is used to generate purchase orders by specifying the type of purchase, quantity of purchase, and required completion time of the purchase, and to procure materials based on the purchase orders.

10. The algorithm-driven power storage and supply-demand matching optimization system according to claim 9, characterized in that, The warehouse optimization algorithm model construction module specifically includes: The cost and demand acquisition unit is used to acquire the depreciation cost of materials, storage costs, and the demand for materials at a future set time point. The objective function construction unit is used to construct an objective function with the goal of maximizing profits, based on the depreciation cost of materials, storage costs, and the demand for materials at a future set time point. The objective function solving unit is used to solve the objective function and determine the inventory quantity of materials at a future set time point.

Images