Power data processing method and device based on hybrid expert model, and electronic equipment

By combining particle swarm algorithm, chaos mapping model and clustering algorithm, initial population is generated and clustering center is optimized, the scheduling pressure of factors affecting new energy grid connection in the power system is solved, and the robustness and adaptability of scheduling are improved, so as to avoid The problem of precocious maturity has been solved and more efficient power system scheduling has been achieved.

CN119066449APending Publication Date: 2024-12-03国网浙江省电力有限公司建德市供电公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411096973.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

The existing technology is difficult to effectively consider the influencing factors of grid connection of new energy such as photovoltaic power and wind power in dynamic economic scheduling of power systems, resulting in comprehensive scheduling pressure, and the uneven distribution of the initial population position of the particle swarm algorithm in high-dimensional space affects performance. .

Method used

Combining particle swarm algorithm, chaos mapping model and clustering algorithm, the initial population is generated through the chaos mapping model, reverse normalize the installed capacity, calculate particle fitness value and clustering center, screen clusters to form new clustering centers, and optimize particle swarm algorithm to improve search space and convergence.

Benefits of technology

Effectively avoid premature maturity problems in particle swarm algorithm, improve the diversity of initial populations, improve the robustness and adaptability of power system scheduling, and can traverse all states more effectively in high-dimensional space, solving new energy scenarios scheduling pressure under the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066449A_ABST
    Figure CN119066449A_ABST
Patent Text Reader

Abstract

The invention discloses a power data processing method and device based on a hybrid expert model and electronic equipment, and the method comprises the steps: obtaining the installed capacity of a wind power generator and a photovoltaic power generator in the power equipment; generating an initial population by using a chaotic mapping model, and inversely normalizing the installed capacity to a search space to obtain an initial position of a particle; calculating the fitness value of each particle, and updating the historical optimal values of each particle and the population; establishing each particle and the historical optimal value as a clustering data set, taking the historical optimal value as an initial clustering center, and calculating the distance between each particle and the clustering center; screening the particles of which the distance is smaller than a preset threshold value, and forming clusters by the particles; calculating a mean value of the clusters, and recording the mean value as a new clustering center; and if the new clustering center is the same as the old clustering center, the algorithm converges, and the process is ended. The optimization algorithm can greatly improve the efficiency of power dispatching.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of electric power economic dispatching, and in particular relates to an electric power data processing method, device and electronic equipment based on a hybrid expert model. Background Art

[0002] In the dynamic economic dispatch of power systems, in order to avoid falling into local search, existing particle swarm algorithms generally use methods to adjust the particle positions, such as combining genetic algorithms to perform operations such as crossover and mutation on particles. However, these methods are prone to tens of millions of particles exceeding the limit, and are not very targeted at the search area in the later stages of iteration, which can easily waste tens of millions of iterations.

[0003] For example, the Chinese patent document CN106570579B discloses a method for economic dispatch of hydropower and thermal power based on an improved quantum particle swarm algorithm, which performs power dispatch by establishing a highly mathematical model of hydropower and thermal power economics and a quantum particle swarm algorithm. However, since this prior art solution only considers traditional energy sources such as hydropower and thermal power, and does not consider the grid-connected impact factors of new energy sources such as photovoltaic power and wind power with uncertain output, it cannot solve the pressure of power system dispatch in energy scenarios such as comprehensive photovoltaic and wind power.

[0004] In the particle swarm algorithm, the search space and convergence of the particle swarm in the later stage are affected by the initial population position, which is usually generated by a random number generator. However, in high-dimensional space, the initial population position generated by a random number generator will be unevenly distributed, thus affecting the performance of the particle swarm algorithm. In the particle swarm algorithm, the search space and convergence of the particle swarm in the later stage are affected by the initial population position, which is usually generated by a random number generator. However, in high-dimensional space, the initial population position generated by a random number generator will be unevenly distributed, thus affecting the performance of the particle swarm algorithm. The chaotic mapping model has the characteristics of traversal, randomness and regularity. It can traverse all states without repetition within a certain range. Compared with the random number generator, the chaotic mapping model can improve the diversity of the initial population and effectively avoid the premature problem in the particle swarm algorithm. Summary of the invention

[0005] In view of the above-mentioned prior art, the purpose of the present invention is to combine the particle swarm algorithm, the chaos mapping model and the clustering algorithm to solve the influencing factors of the grid connection of new energy sources such as photovoltaic power and wind power with uncertain output, and to solve the problem of power system scheduling pressure in comprehensive photovoltaic, wind and other energy scenarios.

[0006] In order to solve the above technical problems, the present application provides a power data processing method based on a hybrid expert model, comprising:

[0007] The method is used for electric power equipment, which includes a wind turbine generator and a photovoltaic generator.

[0008] Obtaining the installed capacity of the wind turbine and photovoltaic generator inside the power equipment;

[0009] The initial population is generated using the chaotic mapping model, and the installed capacity is denormalized to the search space to obtain the initial position of the particles;

[0010] Calculate the fitness value of each particle and update the historical optimal value of each particle and population;

[0011] Establish each particle and the historical optimal value as a clustering data set, use the historical optimal value as the initial cluster center, and calculate the distance between each particle and the cluster center;

[0012] Filter particles whose distance is less than a preset threshold and form clusters of these particles;

[0013] Calculate the mean of the cluster and record the mean as the new cluster center;

[0014] If the new cluster center is the same as the old cluster center, or the preset number of iterations is reached, or the members of the cluster no longer change, the algorithm converges and the process ends.

[0015] As a preferred method, establish the total cost of generator operation F(P G )’s objective function:

[0016]

[0017] Where f, N MG , T are the total operating cost of generators, the number of generators, and the number of operating hours, respectively;

[0018] are the electricity purchase cost, fuel cost, equipment maintenance cost and environmental cost of the ith generator in the tth period respectively; f EM The cost of carbon emissions.

[0019] Establishing particle swarm optimization and chaos mapping formula

[0020]

[0021] Where: are the velocity and position of the i-th particle in the k+1-th iteration respectively;

[0022] are the speed and position of the ith particle in the kth iteration respectively; ω is the inertia coefficient; c1 and c2 are learning factors; r1 and r2 are random numbers uniformly distributed in the range of [0,1]; p g is the historical optimal position of the particle swarm; p i is the historical optimal position of particle i.

[0023]

[0024] In the formula, where are the values ​​of the d-dimensional component of the chaotic variable at the k+1th and kth iterations respectively;

[0025] The value is the initial value of the chaotic variable d-dimensional component

[0026] Preferably, the method further comprises: if the new cluster center is different from the old cluster center, or the preset number of iterations is not reached, or the members of the cluster continue to change, the algorithm does not converge, and continues to return to calculating the fitness value of each particle, and updating the historical optimal value of each particle and population, and repeats the steps.

[0027] In order to solve the above technical problems, the present application also provides a power data processing system based on a hybrid expert model, comprising:

[0028] Acquisition module: acquiring the installed capacity of the wind turbine generator and the photovoltaic generator inside the power equipment;

[0029] Model generation module: Generate the initial population using the chaos mapping model, and denormalize the installed capacity to the search space to obtain the initial position of the particles;

[0030] The first calculation module: calculates the fitness value of each particle and updates the historical optimal value of each particle and population;

[0031] Clustering module: establish each particle and the historical optimal value as a clustering data set, use the historical optimal value as the initial clustering center, and calculate the distance between each particle and the clustering center;

[0032] Screening module: Screen particles whose distance is less than a preset threshold and form clusters of these particles;

[0033] The second calculation module calculates the mean of the cluster and records the mean as a new cluster center;

[0034] Convergence judgment module: If the new cluster center is the same as the old cluster center, or the preset number of iterations is reached, or the members of the cluster no longer change, the algorithm converges and the process ends.

[0035] In order to solve the above technical problems, the present application also provides a power data processing device based on a hybrid expert model, comprising:

[0036] Memory for storing computer programs;

[0037] A processor is used to point a computer program to implement the steps of a power data processing method based on a hybrid expert model.

[0038] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, all the steps of the above-mentioned power data processing method based on a hybrid expert model are implemented.

[0039] The beneficial effects of this application are as follows:

[0040] In the process of studying the optimal dispatch model of the power system, due to the randomness and uncertainty of the daily load and distributed power output, many results may be optimized, but the economic dispatch model attempts to achieve a universal strategy, and the same strategy can be applied to different loads and distributed power characteristics. In order to achieve this, random optimization, robust optimization and other methods appear. The load is clustered and analyzed, and the common load characteristics obtained by induction are combined with the optimization dispatch analysis. The persuasiveness of the model will be greatly enhanced. The chaos mapping model has the characteristics of traversal, randomness and regularity. It can traverse all states without repetition within a certain range. Compared with the random number generator, the chaos mapping model can improve the diversity of the initial population and effectively avoid the premature problem in the particle swarm algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 Flowchart provided for this application;

[0043] Figure 2 System structure diagram provided for this application;

[0044] Figure 3 Illustration of the equipment provided for this application. DETAILED DESCRIPTION

[0045] As required, detailed embodiments of the present invention are disclosed herein, but it should be understood that the disclosed embodiments are merely exemplary of the present invention, and the present invention may be implemented in different and alternative forms. The accompanying drawings may not be drawn to scale, and certain features may be exaggerated or reduced to show the details of specific components. Therefore, the specific structural and functional details disclosed herein should not be understood as having a limiting meaning, but only as a representative basis to teach those skilled in the art to adopt the present invention differently. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.

[0046] Figure 1 A flowchart of a power dispatching method based on a particle swarm algorithm provided in an embodiment of the present application, the method is used for power equipment, the power equipment includes a wind turbine and a photovoltaic generator, including:

[0047] S1. Obtaining the installed capacity of the wind turbine and photovoltaic generator inside the power equipment;

[0048] S2, using the chaos mapping model to generate the initial population, and denormalizing the installed capacity to the search space to obtain the initial position of the particles;

[0049] S3, calculate the fitness value of each particle and update the historical optimal value of each particle and population;

[0050] S4, establishing each particle and the historical optimal value as a clustering data set, taking the historical optimal value as the initial clustering center, and calculating the distance between each particle and the clustering center;

[0051] S5, screening particles whose distance is less than a preset threshold, and clustering these particles;

[0052] S6, calculating the mean of the cluster, and recording the mean as a new cluster center;

[0053] S7, if the new cluster center is the same as the old cluster center, or the preset number of iterations is reached, or the members of the cluster no longer change, the algorithm converges and the process ends;

[0054] S8: If the new cluster center is different from the old cluster center, or the preset number of iterations is not reached, or the members of the cluster continue to change, return to S3 and continue iterating until the algorithm converges.

[0055] The objective function of the power dispatching method based on particle swarm algorithm is the total operating cost, including electricity purchase cost, MT fuel cost, equipment maintenance cost, environmental maintenance cost and carbon emission cost. The particle swarm algorithm uses chaotic mapping to initialize the population and clustering algorithm.

[0056] Establish the total cost of generator operation F(P G )’s objective function:

[0057]

[0058] Where f, N MG , T are the total operating cost of generators, the number of generators, and the number of operating hours, respectively;

[0059] are the electricity purchase cost, fuel cost, equipment maintenance cost and environmental cost of the ith generator in the tth period respectively; fEM The cost of carbon emissions.

[0060] Establishing particle swarm optimization and chaos mapping formula

[0061]

[0062] Where: are the velocity and position of the i-th particle in the k+1-th iteration respectively; are the speed and position of the ith particle in the kth iteration respectively; ω is the inertia coefficient; c1 and c2 are learning factors; r1 and r2 are random numbers uniformly distributed in the range of [0,1]; p g is the historical optimal position of the particle swarm; p i is the historical optimal position of particle i.

[0063]

[0064] In the formula, where are the values ​​of the d-dimensional component of the chaotic variable at the k+1th and kth iterations respectively; The value is the initial value of the d-dimensional component of the chaotic variable.

[0065] In the particle swarm algorithm, the search space and convergence of the particle swarm in the later stage are affected by the initial population position, which is usually generated by a random number generator. However, in high-dimensional space, the initial population position generated by a random number generator will be unevenly distributed, thus affecting the performance of the particle swarm algorithm. The chaotic mapping model has the characteristics of ergodicity, randomness and regularity. It can traverse all states without repetition within a certain range. Compared with the random number generator, the chaotic mapping model can improve the diversity of the initial population and effectively avoid the premature problem in the particle swarm algorithm.

[0066] like Figure 2 As shown, a power data processing system based on a hybrid expert model includes:

[0067] Acquisition module 20: Acquisition of installed capacity of wind turbines and photovoltaic generators inside the power equipment;

[0068] Model generation module 21: Generate an initial population using a chaotic mapping model, and denormalize the installed capacity to the search space to obtain the initial position of the particle;

[0069] The first calculation module 22: calculates the fitness value of each particle and updates the historical optimal value of each particle and population;

[0070] Clustering module 23: establishing each particle and the historical optimal value as a clustering data set, taking the historical optimal value as the initial clustering center, and calculating the distance between each particle and the clustering center;

[0071] Screening module 24: Screening particles whose distance is less than a preset threshold and clustering these particles;

[0072] The second calculation module 25: calculates the mean of the cluster and records the mean as a new cluster center;

[0073] Convergence judgment module 26: If the new cluster center is the same as the old cluster center, or the preset number of iterations is reached, or the members of the cluster no longer change, the algorithm converges and the process ends.

[0074] like Figure 3 As shown, a power data processing device based on a hybrid expert model includes:

[0075] A memory 30, for storing computer programs;

[0076] The processor 31 is used to implement the steps of the power data processing method based on the hybrid expert model mentioned in the above embodiment when executing the computer program.

[0077] The power data processing device based on the hybrid expert model provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer or a desktop computer.

[0078] Among them, the processor 31 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 31 can be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), and programmable logic array (PLA). The processor 31 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 31 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 31 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.

[0079] The memory 30 may include one or more computer-readable storage media, which may be non-transitory. The memory 30 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 30 is at least used to store the following computer program, wherein, after the computer program is loaded and executed by the processor 31, it can implement the relevant steps of the power data processing method based on the hybrid expert model disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 30 may also include an operating system and data, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system may include Windows, Unix, Linux, etc. The data may include but is not limited to the power data processing method based on the hybrid expert model, etc.

[0080] In some embodiments, the power data processing device based on the hybrid expert model may further include a display screen, an input and output interface, a communication interface, a power supply, and a communication bus.

[0081] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation to the power data processing device based on the hybrid expert model, and may include more or less components than those shown in the figure.

[0082] The power data processing device based on the hybrid expert model provided in the embodiment of the present application includes a memory 30 and a processor 31. When the processor 31 executes the program stored in the memory 30, it can implement the power data processing method based on the hybrid expert model.

[0083] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.

[0084] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory), ROM, random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0085] The above is a detailed introduction to the power data processing method, device, equipment and medium based on a hybrid expert model provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can refer to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.

[0086] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

Claims

1. A power data processing method based on a hybrid expert model, characterized in that: The method is used for electric power equipment, which includes a wind turbine generator and a photovoltaic generator. Obtaining the installed capacity of the wind turbine and photovoltaic generator inside the power equipment; The initial population is generated using the chaotic mapping model, and the installed capacity is denormalized to the search space to obtain the initial position of the particles; Calculate the fitness value of each particle and update the historical optimal value of each particle and population; Establish each particle and the historical optimal value as a clustering data set, use the historical optimal value as the initial cluster center, and calculate the distance between each particle and the cluster center; Filter particles whose distance is less than a preset threshold and form clusters of these particles; Calculate the mean of the cluster and record the mean as the new cluster center; If the new cluster center is the same as the old cluster center, or the preset number of iterations is reached, or the members of the cluster no longer change, the algorithm converges and the process ends.

2. The power data processing method based on the hybrid expert model according to claim 1 is characterized in that: Establish the total cost of generator operation F(P G )’s objective function: Where f, N MG , T are the total operating cost of generators, the number of generators, and the number of operating hours, respectively; , , , are the electricity purchase cost, fuel cost, equipment maintenance cost and environmental cost of the ith generator in the tth period respectively; f EM The cost of carbon emissions.

3. The power data processing method based on the hybrid expert model according to claim 2 is characterized in that: The particle swarm algorithm and chaos mapping expressions of the objective function are established: Where: , are the velocity and position of the i-th particle in the k+1-th iteration respectively; , are the speed and position of the ith particle in the kth iteration respectively; ω is the inertia coefficient; c1 and c2 are learning factors; r1 and r2 are random numbers uniformly distributed in the range of [0,1]; p g is the historical optimal position of the particle swarm; p i is the historical optimal position of particle i; In the formula, , where are the values ​​of the d-dimensional component of the chaotic variable at the k+1th and kth iterations respectively; The value is the initial value of the d-dimensional component of the chaotic variable.

4. The power data processing method based on hybrid expert model according to claim 1 is characterized in that: The method then includes: if the new cluster center is different from the old cluster center, or the preset number of iterations is not reached, or the members of the cluster continue to change, the algorithm does not converge, and continues to return to calculating the fitness value of each particle and updating the historical optimal value of each particle and population, and the steps are repeated.

5. A power data processing system based on a hybrid expert model, comprising: Acquisition module: acquiring the installed capacity of the wind turbine generator and the photovoltaic generator inside the power equipment; Model generation module: Generate the initial population using the chaos mapping model, and denormalize the installed capacity to the search space to obtain the initial position of the particles; The first calculation module: calculates the fitness value of each particle and updates the historical optimal value of each particle and population; Clustering module: establish each particle and the historical optimal value as a clustering data set, use the historical optimal value as the initial clustering center, and calculate the distance between each particle and the clustering center; Screening module: Screen particles whose distance is less than a preset threshold and form clusters of these particles; The second calculation module calculates the mean of the cluster and records the mean as a new cluster center; Convergence judgment module: If the new cluster center is the same as the old cluster center, or the preset number of iterations is reached, or the members of the cluster no longer change, the algorithm converges and the process ends.

6. A power data processing device based on a hybrid expert model, characterized in that: include: Memory for storing computer programs; A processor is used to implement the steps of the power data processing method based on the hybrid expert model as described in any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the power data processing method based on the hybrid expert model as described in any one of claims 1 to 4 are implemented.