Power material demand allocation method, device, terminal equipment and storage medium
By constructing abstract expressions of preprocessing and allocation schemes for power material data, combined with two-stage optimization of multi-objective evolution algorithm and genetic algorithm, the problem of singleness and inefficiency of power material demand allocation methods in the existing technology is solved, and the problem of inefficiency of power material demand allocation methods is realized. More efficient allocation scheme generation.
Patent Information
- Application Number
- CN202111289442.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-11-02
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2041-11-02
AI Technical Summary
The existing power material demand allocation method has a single calculation process, strong limitations, low computing efficiency, and cannot meet the needs of rapid response.
By preprocessing the power material data, abstract expressions of the distribution scheme are constructed, and combined optimization of multi-objective evolution algorithm and genetic algorithm is performed based on the objective function and constraints, and the calculation is divided into two stages to improve efficiency.
It reduces the amount of data and calculation complexity, improves the flexibility and optimization effect of the algorithm, and improves the response speed and efficiency of power material demand allocation.
Smart Images

Figure CN114021950B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power material demand allocation, and in particular to a power material demand allocation method, device, terminal equipment and storage medium. Background Art
[0002] With the development of the power material supply chain, higher and higher requirements are put forward for the response time, response speed and response plan of power material allocation. It is time-consuming and labor-intensive to carry out material allocation based solely on historical subjective experience. Therefore, seeking to reasonably and efficiently allocate a variety of power materials to various cities with demand under the existing material level by using modern intelligent optimization theory is the core link to improve the development of the power material supply chain.
[0003] At present, when performing multi-objective allocation of materials, the main method is to construct a two-dimensional allocation scheme matrix to represent the allocation amount of different materials and different demand points, and use the second-generation Pareto evolutionary algorithm to generate the allocation scheme, and then calculate the fitness function value of the allocation scheme. And on the basis of each calculation result, the allocation scheme is selected, crossed and mutated with a certain probability. After updating the allocation scheme, the fitness function value continues to be calculated, and the historical best fitness function value and its corresponding allocation scheme are updated at the same time until the iteration converges or the maximum number of iterations is reached. However, this method often has the following shortcomings: First, the calculation process of this method is relatively simple, and there are problems of strong limitations and small scope of application; second, this method has a large number of complex data processing processes, so the calculation efficiency is low, and it cannot meet the needs of rapid response to power material allocation requests. Summary of the invention
[0004] The purpose of the present invention is to provide a method, device, terminal equipment and storage medium for allocating power material demand, so as to solve the problems existing in the prior art of allocating power material demand, such as single calculation method, large calculation amount and low calculation efficiency.
[0005] To achieve the above object, the present invention provides a method for allocating power material demand, comprising:
[0006] Preprocessing the electric power material data information; the electric power material data information includes electric power material demand data and contract data;
[0007] According to the preprocessing results, construct an abstract expression of the allocation scheme;
[0008] constructing an objective function and constraints using an abstract expression of the allocation scheme;
[0009] An algorithm optimization is performed based on the objective function and constraint conditions to generate a result of the distribution of power material demand.
[0010] Furthermore, the preprocessing of the electric power material data information includes:
[0011] The demand for electric power materials is processed by marking the urgency of demand, downgrading the urgency, clustering, decomposing clusters, batch marking or rapid supply marking.
[0012] Furthermore, constructing an abstract expression of the allocation scheme according to the preprocessing result includes:
[0013] Divide the aggregated power material demand into different decision variables;
[0014] Different value ranges are set for the decision variables, and the decision variables are matched with the contracts according to the value ranges to generate a supply relationship.
[0015] Furthermore, the algorithm optimization based on the objective function and the constraint conditions includes:
[0016] The optimization process is divided into a first stage and a second stage; wherein, in the first stage, a multi-objective evolutionary algorithm is used for calculation, and in the second stage, a genetic algorithm is used for calculation.
[0017] The present invention also provides a power material demand distribution device, comprising:
[0018] A preprocessing unit, used to preprocess the power material data information; the power material data information includes the reported quantity of power material demand, current inventory materials and contract remaining materials;
[0019] A pre-allocation unit, used to construct an abstract expression of the allocation scheme according to the pre-processing result;
[0020] A function construction unit, used to construct an objective function and constraint conditions using an abstract expression of the allocation scheme;
[0021] The algorithm optimization unit is used to perform algorithm optimization based on the objective function and constraint conditions to generate a power material demand allocation result.
[0022] Furthermore, the pre-processing unit comprises:
[0023] The demand urgency identification module is used to identify the demand urgency of power material demand;
[0024] The emergency demand downgrade module is used to downgrade the current power material demand when the contract materials cannot supply the power material demand;
[0025] The demand clustering module is used to cluster the demand according to the type of power material demand and the region where it is reported;
[0026] A cluster decomposition module, used to decompose the aggregate quantity exceeding a preset value into multiple aggregate quantities;
[0027] Batch marking module, used to mark current inventory materials and contract materials according to time period priority;
[0028] The fast delivery marking module is used to divide manufacturer contracts according to the priority of delivery speed and match the division results with different urgency requirements.
[0029] Furthermore, the pre-allocation unit is also used for:
[0030] Divide the aggregated power material demand into different decision variables;
[0031] Different value ranges are set for the decision variables, and the decision variables are matched with the contracts according to the value ranges to generate a supply relationship.
[0032] Furthermore, the algorithm optimization unit is also used for:
[0033] The optimization process is divided into a first stage and a second stage; wherein, in the first stage, a multi-objective evolutionary algorithm is used for calculation, and in the second stage, a genetic algorithm is used for calculation.
[0034] The present invention also provides a terminal device, comprising:
[0035] one or more processors;
[0036] A memory, coupled to the processor, for storing one or more programs;
[0037] When the one or more programs are executed by the one or more processors, the one or more processors implement the power material demand allocation method as described in any one of the above items.
[0038] The present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for allocating power material demand as described in any one of the above items is implemented.
[0039] Compared with the prior art, the beneficial effects of the present invention are:
[0040] 1) In the data preprocessing stage, the demands for the same type of materials in the same city are aggregated, and the aggregated quantity is controlled within 15 units. While reducing the data level, the size of the aggregated data will not affect the effect of the algorithm. Through the emergency demand downgrade module, the smooth implementation of the allocation algorithm is guaranteed in extreme cases.
[0041] 2) The present invention compresses the high-dimensional decision variable matrix into a one-dimensional array by constructing decision variables. By setting multiple sets of different upper and lower limits, it ensures that the evolutionary algorithm can achieve multi-material and multi-objective optimization, solves the constraint that the number of elements in each row and column of the two-dimensional decision variable matrix is equal, and has greater flexibility in dealing with practical problems.
[0042] 3) In combination with the actual business situation, based on the operating principles of actual allocation, we refined and summarized, and set four goals for the allocation scheme evolutionary algorithm. In the actual calculation process, the evolutionary algorithm seeks the Pareto solution set of the four goals, rather than treating the four goals as a whole to solve, which greatly improves the optimization effect of the algorithm.
[0043] 4) This algorithm is designed to solve practical allocation problems. During its construction, the algorithm's optimization process is divided into two stages (the first stage uses an algorithm with lower computational complexity and faster iterative optimization, and the second stage uses an algorithm with higher computational complexity and better optimization effect). The advantages of the two stages are effectively combined, thereby effectively improving the algorithm's execution efficiency and better meeting the needs of executors in actual production. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solution of the present invention, the drawings required for use in the implementation mode will be briefly introduced below. Obviously, the drawings described below are only some implementation modes of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0045] Figure 1 It is a flowchart of a method for allocating power material demand provided by a certain embodiment of the present invention;
[0046] Figure 2 It is a schematic diagram of the functional modules of the preprocessing unit and the relationship between them provided in one embodiment of the present invention;
[0047] Figure 3 It is a schematic diagram of the principle of an abstract expression of a construction allocation scheme provided by a certain embodiment of the present invention;
[0048] Figure 4 It is a schematic diagram of the selection and relationship of the methods of each stage of algorithm optimization provided by a certain embodiment of the present invention;
[0049] Figure 5 is a flowchart of a result generation process provided by an embodiment of the present invention;
[0050] Figure 6 It is a flow chart of a method for allocating power material demand provided by another embodiment of the present invention;
[0051] Figure 7 It is a structural schematic diagram of a power material demand distribution device provided by a certain embodiment of the present invention;
[0052] Figure 8 yes Figure 7 The structural diagram of the pre-processing unit 01;
[0053] Fig. 9 It is a schematic diagram of the structure of a terminal device provided by a certain embodiment of the present invention. DETAILED DESCRIPTION
[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0055] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.
[0056] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.
[0057] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0058] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.
[0059] See also Figure 1 , a certain embodiment of the present invention provides a method for allocating power material demand. Figure 1 As shown, the method for allocating power material demand includes steps S10 to S40. The specific steps are as follows:
[0060] S10. Preprocessing the electric power material data information; the electric power material data information includes electric power material demand data and contract data.
[0061] This step mainly involves data processing operations to pre-process the reported quantities of various power material demands from multiple municipal power supply units, as well as the pre-processing of current inventory materials and contract surplus materials; pre-processing specifically refers to demand urgency identification, urgency downgrade, demand clustering, cluster decomposition, batch marking or rapid delivery marking of power material demands.
[0062] Specifically, in data processing, the following methods are mainly used: Figure 7 The preprocessing unit 01 shown in the figure is executed, wherein the preprocessing unit 01 further includes a demand urgency identification module 011, an emergency demand downgrade module 012, a demand clustering module 013, a cluster decomposition module 014, a batch marking module 015, and a fast supply marking module 016. Figure 8 The functional relationship of each module is shown as follows. Figure 2 As shown, specifically:
[0063] The demand urgency identification module 011 is mainly used to make a judgment based on the required arrival date of the demand submitted by the demand unit. When the date minus the algorithm operation date is less than or equal to a certain threshold (the threshold can be flexibly set according to the actual situation, such as 20 days), the demand is marked as urgent demand and needs to be matched with a manufacturer with faster supply speed;
[0064] The emergency demand downgrading module 012 is used to downgrade some demands marked as urgent to ordinary demands when the total remaining quantity of all signed supply contracts of all manufacturers with faster supply cannot meet the demand of all current emergency demands; in an optional embodiment, the emergency demand downgrading module is used to deal with extreme cases where the total remaining quantity of contracts of manufacturers with faster supply is less than the total demand of all emergency demands. By screening the submission dates of all emergency demands, arranging them from front to back according to time, and satisfying them in order of arrangement, the remaining unmet demands need to be downgraded to normal demands and supplied by suppliers with average supply speed. This module can prevent algorithm errors in extreme cases and enhance the robustness of the allocation algorithm.
[0065] The demand clustering module 013 is mainly used to aggregate the reported quantities of the same power material and the same city unit to achieve the goal of reducing the amount of data and the running time of the algorithm;
[0066] The cluster decomposition module 014 is used to decompose a large number of aggregates into multiple smaller aggregates. A large aggregate will result in too few choices of matching supply ends, which will affect the final calculation result.
[0067] In an optional embodiment, the combined use of the demand clustering module 013 and the clustering decomposition module 014 can achieve the effect of reducing the amount of data and maintaining the overall aggregated quantity within a certain range, which will not interfere with the operation of the algorithm. Among them, the demand clustering module clusters the demand details of the same reporting unit and the same reporting material, while the clustering decomposition module uses a heuristic algorithm to decompose a larger aggregated quantity into multiple smaller aggregated quantities. For example, a certain city has 7 demand details for a certain material A, and its demand quantities are: 1, 2, 3, 4, 5, 6, 7, and its total aggregated quantity is 28. If no further processing is performed, it can only match contracts with a remaining quantity of more than 28 units. Therefore, according to the needs of the actual situation, with the minimum standard deviation of the multiple aggregated values after re-aggregation as the goal, the clustering decomposition module is used to re-cluster them into 2 categories (SUM (1 + 2 + 3 + 4 + 5 + 6 + 7) / / 10) to ensure that each cluster value does not exceed 15 units, making its allocation more flexible.
[0068] The batch marking module 015 is used to mark the current inventory and contracts according to the time period. When matching, the contracts with earlier signing time are matched first according to the value;
[0069] The fast delivery marking module 016 is mainly used to distinguish between contracts of manufacturers with faster delivery speed and those with average delivery speed. When matching, ordinary demand can match contracts of manufacturers with fast delivery speed and those with average delivery speed, while urgent demand can only match contracts of manufacturers with faster delivery speed.
[0070] S20. Construct an abstract expression of the allocation plan according to the preprocessing result.
[0071] In this step, the abstract expression of the allocation scheme is mainly used to construct the range and value mode (integer or real number) of the decision variable according to the practical meaning. The principle of constructing the abstract expression of the allocation scheme is as follows: Figure 3 As shown. Specifically, when constructing the abstract expression of the allocation plan, it mainly includes two steps: A) dividing the aggregated power material demand into different decision variables; B) setting different value ranges for the decision variables, and matching the decision variables with the contract according to the value ranges to generate a supply relationship. As a preferred embodiment, the abstract expression of the allocation plan in this embodiment takes the algorithm operation efficiency and implementation as the primary principle, constructs the decision variable sequence, and its construction method is as follows Figure 3 As shown. Figure 3As shown in the figure, all the pre-processed aggregates are expanded in one dimension, and different value ranges are set for different decision variables (demand 1 to demand 10), whose values represent the matching of demand with the Nth contract to establish a supply relationship. Therefore, the abstract expression of the allocation scheme plays a role in reducing the data dimension by setting an independent value range for the decision variable (demand N), so that the decision variable can effectively distinguish the types of power materials and emergency / non-emergency demands in the state of one-dimensional expansion, thereby achieving the allocation effect of multiple types of materials.
[0072] S30: construct an objective function and constraint conditions using the abstract expression of the allocation scheme.
[0073] This step mainly converts the allocation principle during manual allocation into an abstract mathematical expression to characterize the pros and cons of the allocation scheme. It is a metric function for judging the allocation scheme - the fitness function, while the constraint conditions are the basis for each matching relationship.
[0074] In a specific embodiment, the objective function is constructed based on an abstract mathematical relationship established according to the actual matching rules. For example, according to the division of five batch segments, namely, 0-3 months, 3-6 months, 6-9 months, 9-12 months, and 12 months and above, the difference between the current node and the contract signing time falls in which interval, and then the contract belongs to which batch, and the five batch intervals are assigned a value of 5 to 1 at a time. In this embodiment, multiple goals are established: 1. After the allocation, the execution ratio (matched quantity / total quantity) of each contract in the same batch should be as balanced as possible; 2. Consume the remaining amount of contracts in earlier batches first; 3. The number of global suppliers is the least; 4. The number of suppliers corresponding to each city is the least. The specific formula is as follows:
[0075] Objective function 1:
[0076]
[0077] Among them, x i represents the value of the i-th decision variable; b xi Indicates the xth i The batch coefficient corresponding to each contract.
[0078] Objective function 2:
[0079] minf2=std(ratio1,ratio2,...,ratio n );
[0080] Among them, ratio n It represents the execution ratio of each contract after the allocation is completed, that is, (matched quantity + this matching quantity) / total number of contracts; std represents the execution ratio of all contracts and calculates their standard deviation.
[0081] Objective function 3:
[0082]
[0083] in, Indicates the xth i The supplier corresponding to each contract; unique means to deduplicate the sequence.
[0084] Objective function 4:
[0085]
[0086] Among them, org n Indicates which city company the nth decision variable (demand) belongs to; Indicates the corresponding city company org n Is it the kth city? If yes, the value is 1 / org n , otherwise the value is 0; Indicates the xth i The supplier corresponding to each contract; unique means to deduplicate the sequence.
[0087] S40, performing algorithm optimization based on the objective function and constraint conditions to generate a power material demand allocation result.
[0088] In this step, the optimization process is divided into the first stage and the second stage; wherein, the multi-objective evolutionary algorithm is used for calculation in the first stage, and the genetic algorithm is used for calculation in the second stage. The two stages of the optimization process are as follows: Figure 4 shown.
[0089] It should be noted that the optimization process of the allocation scheme is divided into two stages. The first stage uses a multi-objective evolutionary algorithm based on decomposition with a faster search speed. This algorithm converts the multi-objective optimization problem into N single-objective problems that are optimized at the same time, which can reduce the difficulty of target optimization. In addition, the algorithm uses the co-evolution mechanism between sub-problems, so it can greatly reduce the responsibility of the calculation process and has the characteristics of fast iteration speed and low computational complexity. The genetic algorithm used in the second stage is mainly the second-generation fast non-dominated sorting genetic algorithm. Based on prior experience, the calculation results of the previous stage are used for further iterative calculation. The algorithm introduces crowding and crowding comparison operators, which is conducive to maintaining the diversity of the population, and introduces an elite strategy, which is conducive to keeping the excellent individuals of the parent generation into the next generation. The hierarchical storage strategy is used for all individuals in the population, which helps to quickly improve the population level. Although the computational complexity is increased, the optimization effect is also greatly improved. Therefore, in the optimization calculation stage, the combination of the two algorithms can not only improve the optimization speed, but also ensure the robustness of the optimization results.
[0090] Finally, after step S40 is completed, the allocation result is obtained, and the data format of the allocation result needs to be converted, and the converted allocation scheme is output, such as Figure 5 This part includes reverse clustering the allocation results, and then aligning the data format in combination with manual correction to obtain the final allocation solution.
[0091] The method for allocating power material demand provided in the embodiment of the present invention can reduce the amount of data and the complexity of calculation by clustering and decomposing material demand; realizes data dimension reduction by constructing an abstract expression of the allocation plan; and adopts different algorithms at different stages in the algorithm optimization process, thereby improving the optimization speed and ensuring the stability of the optimization results.
[0092] In order to help understand the solution provided by the present invention, the following is a detailed description of an embodiment in which specific data is substituted, wherein the process of the entire allocation method is as follows: Figure 6 Specifically, the contents of each step are as follows:
[0093] (1) Regularly obtain the demand submissions from all cities and prefectures in each cycle, including but not limited to: material code, city code, demand quantity, demand detail identification code, submission time, and required arrival time. And sort them according to material code and city code.
[0094] (2) At the beginning of the matching algorithm, the database is connected to obtain the latest material contract information, including but not limited to: contract code, supplier code, material code, total contract quantity, matched quantity, and signing time.
[0095] (3) Preprocess the demand data and contract data. Use the urgent demand identification module to identify whether each demand detail is urgent. Use the batch marking module to divide the contracts into batches according to the signing time. Use the fast delivery marking module to judge the supplier information and identify the contracts with faster supply speed (first-tier contracts).
[0096] (4) Based on the demand and contract information processed above, determine whether the total remaining quantity of each type of material under the contract can meet the current total demand. If the demand for the material type cannot be fully met, output information to prompt the administrator to sign a new contract and manually allocate it.
[0097] (5) After the total quantity is satisfied, the emergency demand is satisfied. The total emergency demand of each type of material and the total remaining quantity of the first-tier contract are compared. If the emergency demand cannot be satisfied, the emergency demand downgrade module is used to sort the emergency demands from early to late according to the submission time, giving priority to satisfying the emergency demands submitted earlier, and the remaining unsatisfied parts are downgraded to ordinary demands.
[0098] (6) Cluster the demand data after the above processing, aggregate them according to the material type and city dimension, and judge the aggregated amount after aggregation. If the aggregated amount exceeds 15 units, use the clustering decomposition module to re-aggregate the larger aggregated amount into several smaller aggregated amounts.
[0099] (7) Sort the demand and contract data and arrange them in ascending order according to the material code. For demands with the same material code, sort them in the order of non-urgent demands first and then urgent demands. For contracts with the same material code, sort them in the order of ordinary contracts first and then first-tier contracts.
[0100] (8) According to the above arrangement, construct the lower limit of all requirements And the upper limit of value
[0101] (9) Construct the decision variables of the evolutionary algorithm X = {x1, x2, ..., x n}, and its construction method is as follows Figure 3 shown.
[0102] (10) Enter other parameters, including:
[0103] Aggregated demand in each city:
[0104] The city codes corresponding to the decision variables are:
[0105] Contract serial number: C = {c1,c2,...,c m};
[0106] Contract Remaining Amount:
[0107] Contract execution ratio (matched / total contract amount):
[0108] Total contract volume:
[0109] Contract batch:
[0110] Supplier of the contract:
[0111] (11) Based on the principle of empirical allocation, four sets of objective functions and constraint variables are constructed. The constraint variables constrain the upper limit of the contract allocation, stipulating that the total amount of each contract allocation shall not exceed its remaining amount. Constraints are also set for each demand, that is, each demand can only match one contract.
[0112] (12) A two-stage evolutionary algorithm was constructed. In the first stage, a decomposition-based multi-objective evolutionary algorithm was selected, and in the second stage, a second-generation fast non-dominated sorting genetic algorithm was selected. The population size of both algorithms was set to 80, the maximum number of iterations was set to 1000, and the encoding method used was binary Gray coding.
[0113] (13) For the population described in the random initialization algorithm, the algorithm will use the penalty function method (for example, calculate the demand corresponding to all decision variables with a value of 1 (establishing a supply relationship with Contract 1), calculate the sum of the corresponding demand, and subtract the remaining amount of Contract 1. If the result is less than or equal to 0, it means that the quantity allocated to Contract 1 this time does not exceed its remaining amount, satisfying the constraint. If the value is greater than 0, the constraint is violated) to mark all individuals in all populations that violate the constraint and modify their values in the next iteration.
[0114] (14) After the two-stage algorithm processing, the allocation results are output. Combined with the allocation results and the data before clustering, the results are reversely aggregated to determine the contract code corresponding to each demand detail, establish a matching relationship between the demand and the contract, align the data format according to the database table structure, write it into the database and display it in the system.
[0115] See also Figure 7 A certain embodiment of the present invention further provides a power material demand allocation device, comprising:
[0116] The preprocessing unit 01 is used to preprocess the power material data information; the power material data information includes the reported quantity of power material demand, current inventory materials and contract remaining materials;
[0117] The pre-allocation unit 02 is used to construct an abstract expression of the allocation scheme according to the pre-processing result;
[0118] Function construction unit 03, used to construct the objective function and constraint conditions using the abstract expression of the allocation scheme;
[0119] The algorithm optimization unit 04 is used to perform algorithm optimization based on the objective function and constraint conditions to generate a power material demand allocation result.
[0120] In one embodiment, the preprocessing unit 01 includes the following modules: Figure 8 shown.
[0121] The demand urgency identification module 011 is used to identify the demand urgency of the power material demand;
[0122] Emergency demand downgrade module 012, used to downgrade the current power material demand when the contract materials cannot supply the power material demand;
[0123] Demand clustering module 013, used to cluster demand according to the type of power material demand and the reporting area;
[0124] A cluster decomposition module 014, used to decompose the aggregate quantity exceeding a preset value into multiple aggregate quantities;
[0125] Batch marking module 015 is used to mark the current inventory materials and contract materials according to the time period priority;
[0126] The fast delivery marking module 016 is used to divide the manufacturer contracts according to the delivery speed priority and match the division results with different urgency requirements.
[0127] In one embodiment, the pre-allocation unit 02 is further used for:
[0128] Divide the aggregated power material demand into different decision variables;
[0129] Different value ranges are set for the decision variables, and the decision variables are matched with the contracts according to the value ranges to generate a supply relationship.
[0130] In one embodiment, the algorithm optimization unit 04 is further used for:
[0131] The optimization process is divided into a first stage and a second stage; wherein, in the first stage, a multi-objective evolutionary algorithm is used for calculation, and in the second stage, a second-generation fast non-dominated sorting genetic algorithm is used for calculation.
[0132] The power material demand allocation device provided in an embodiment of the present invention is used to execute the power material demand allocation method as described in any of the above embodiments. This embodiment can reduce the amount of data and reduce the calculation complexity by clustering and decomposing the material demand; realize data dimensionality reduction by constructing an abstract expression of the allocation plan; and adopt different algorithms at different stages in the algorithm optimization process, thereby improving the optimization speed and ensuring the stability of the optimization results.
[0133] See also Fig. 9 , a certain embodiment of the present invention provides a terminal device, including:
[0134] one or more processors;
[0135] A memory, coupled to the processor, for storing one or more programs;
[0136] When the one or more programs are executed by the one or more processors, the one or more processors implement the power material demand allocation method as described above.
[0137] The processor is used to control the overall operation of the terminal device to complete all or part of the steps of the above-mentioned power material demand allocation method. The memory is used to store various types of data to support the operation of the terminal device, and these data may include, for example, instructions for any application or method used to operate on the terminal device, and data related to the application. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk.
[0138] In an exemplary embodiment, the terminal device can be implemented by one or more application specific integrated circuits (Application Specific 1n Integrated Circuit, referred to as ASC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the power material demand allocation method described in any of the above embodiments, and achieve the same technical effect as the above method.
[0139] In another exemplary embodiment, a computer-readable storage medium including a computer program is also provided, and when the computer program is executed by a processor, the steps of the method for allocating power material demand as described in any of the above embodiments are implemented. For example, the computer-readable storage medium can be the above-mentioned memory including the computer program, and the above-mentioned computer program can be executed by the processor of the terminal device to complete the method for allocating power material demand as described in any of the above embodiments, and achieve the technical effect consistent with the above method.
[0140] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.
Claims
1. A method for allocating power material demand, characterized in that: include: Pre-process the data information of power materials; The power material data information includes power material demand data and contract data; According to the preprocessing results, construct an abstract expression of the allocation scheme; constructing an objective function and constraints using an abstract expression of the allocation scheme; Based on the objective function and constraint conditions, an algorithm optimization is performed to generate a power material demand allocation result; The step of constructing an abstract expression of the allocation scheme according to the preprocessing result includes: Divide the aggregated power material demand into different decision variables; Setting different value ranges for the decision variables, and matching the decision variables with the contracts according to the value ranges to generate a supply relationship; The algorithm optimization based on the objective function and the constraint conditions includes: The optimization process is divided into a first stage and a second stage; wherein, in the first stage, a multi-objective evolutionary algorithm is used for calculation, and in the second stage, a genetic algorithm is used for calculation.
2. The method for allocating power material demand according to claim 1, characterized in that: The preprocessing of the electric power material data information includes: The demand for electric power materials is processed by marking the urgency of demand, downgrading the urgency, clustering, decomposing clusters, batch marking or rapid supply marking.
3. A power material demand distribution device, characterized in that: include: A preprocessing unit, used for preprocessing the power material data information; The power material data information includes the reported quantity of power material demand, current inventory materials and contract remaining materials; A pre-allocation unit, used to construct an abstract expression of the allocation scheme according to the pre-processing result; A function construction unit, used to construct an objective function and constraint conditions using an abstract expression of the allocation scheme; An algorithm optimization unit, used to perform algorithm optimization based on the objective function and constraint conditions to generate a power material demand allocation result; The pre-allocation unit is further used for: Divide the aggregated power material demand into different decision variables; Setting different value ranges for the decision variables, and matching the decision variables with the contracts according to the value ranges to generate a supply relationship; The algorithm optimization unit is further used for: The optimization process is divided into a first stage and a second stage; wherein, in the first stage, a multi-objective evolutionary algorithm is used for calculation, and in the second stage, a genetic algorithm is used for calculation.
4. The power material demand allocation device according to claim 3, characterized in that: The pre-processing unit comprises: The demand urgency identification module is used to identify the demand urgency of power material demand; The emergency demand downgrade module is used to downgrade the current power material demand when the contract materials cannot supply the power material demand; The demand clustering module is used to cluster the demand according to the type of power material demand and the region where it is reported; A cluster decomposition module, used to decompose the aggregate quantity exceeding a preset value into multiple aggregate quantities; Batch marking module, used to mark current inventory materials and contract materials according to time period priority; The fast delivery marking module is used to divide manufacturer contracts according to the priority of delivery speed and match the division results with different urgency requirements.
5. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the power material demand allocation method as described in claim 1 or 2.
6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for allocating power material demand as claimed in claim 1 or 2 is implemented.
