Distributed photovoltaic consumption-oriented energy storage planning method and system for flexible distribution network

Abstract

A distributed photovoltaic consumption-oriented energy storage planning method and system for a flexible distribution network. The method comprises: acquiring grid data, photovoltaic data and load data of a distribution network in a target area, preprocessing the data, screening the preprocessed data, and selecting fault data; on the basis of the selected fault data and a genetic algorithm, establishing a distribution network energy storage system capacity configuration model; and on the basis of the distribution network energy storage system capacity configuration model, performing distributed photovoltaic consumption-oriented flexible distribution network energy storage planning.

Description

Flexible distribution network energy storage planning method and system for distributed photovoltaic consumption Technical Field

[0001] The present invention relates to the technical field of flexible distribution network energy storage planning, and in particular to a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption. Background Art

[0002] With the continuous increase in global energy demand and growing awareness of environmental protection, renewable energy has gradually become a focus of attention. As a major renewable energy technology, photovoltaic power generation systems have significant development potential and broad application prospects. Energy storage systems can store excess electricity when solar energy is sufficient and release it during periods of insufficient sunlight or increased power demand to meet user needs. Therefore, energy storage system capacity assessment has become a key component of the planning and design of distributed photovoltaic distribution networks.

[0003] The flexible interconnection devices currently designed are only used in single application scenarios, such as local back-to-back converters, and cannot achieve coordinated deployment and flow control in multiple areas.

[0004] Summary of the Invention

[0005] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0006] In view of the above existing problems, the present invention is proposed.

[0007] Therefore, the present invention provides a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption, which can solve the problems mentioned in the background technology.

[0008] To solve the above technical problems, the present invention provides the following technical solutions, namely, a flexible distribution network energy storage planning method for distributed photovoltaic consumption, comprising:

[0009] Obtaining grid data, photovoltaic data, and load data of the distribution network in the target area, preprocessing the data, and screening the preprocessed data to filter out fault data;

[0010] Based on the screened fault data and combined with genetic algorithm, a capacity configuration model for the distribution network energy storage system is established;

[0011] According to the distribution network energy storage system capacity configuration model, flexible distribution network energy storage planning for distributed photovoltaic consumption is carried out.

[0012] As a preferred solution of the flexible distribution network energy storage planning method for distributed photovoltaic consumption described in the present invention, wherein: the grid data, photovoltaic data and load data of the distribution network in the target area are obtained, the data are preprocessed, and the preprocessed data are filtered to filter out fault data including:

[0013] The grid data, photovoltaic data and load data include grid structure, transformer capacity, line current carrying capacity, distributed photovoltaic power generation, and energy storage system energy status;

[0014] The fault data includes equipment network fault data, energy storage system energy data, power output, and charging efficiency;

[0015] The screening is performed using an improved robustness index, which is expressed as follows:

[0016] MDRI=1 / (1+e^(γ*(w_true-w_pred)))

[0017] Among them, γ is a hyperparameter that controls the steepness of the decision boundary, w_true is the true category weight, which indicates the actual importance of each category, and w_pred is the predicted category weight, which indicates the predicted importance of each category;

[0018] Robustness indicator thresholds for equipment network fault data, energy storage system energy data, power output, and charging efficiency are designed respectively, and data that meets the threshold conditions are screened out.

[0019] As a preferred solution of the flexible distribution network energy storage planning method for distributed photovoltaic consumption described in the present invention, wherein: the establishment of a distribution network energy storage system capacity configuration model based on the screened fault data in combination with a genetic algorithm includes:

[0020] The modularity indicators are as follows:

[0021] Among them, e i,j is the weight of the correlation parameter in the network, is the sum of all weights of parameters in the network, k i 、k j is the weight of parameter i and parameter j;

[0022] When parameter i and parameter j are in the same cluster, δ(i, j) = 1, otherwise δ(i, j) = 0.

[0023] As a preferred solution of the flexible distribution network energy storage planning method for distributed photovoltaic consumption described in the present invention, wherein: the establishment of a distribution network energy storage system capacity configuration model based on the screened fault data in combination with a genetic algorithm also includes:

[0024] The calculation formula for the comprehensive purity index of the whole system cluster division is as follows:

[0025] Among them, O wi is the comprehensive purity index in a certain scenario, is the number of clusters divided, For scene w i The power generation and consumption characteristic purity index value of cluster c is between -1 and 1.

[0026] As a preferred solution of the flexible distribution network energy storage planning method for distributed photovoltaic consumption described in the present invention, wherein: the establishment of a distribution network energy storage system capacity configuration model based on the screened fault data in combination with a genetic algorithm also includes:

[0027] The modularity index and the comprehensive purity index are weighted to form a comprehensive evaluation index Φ. The cluster for energy storage planning uses the partition optimization model to maximize Φ as the optimization goal. The formula is as follows:

[0028] Among them, Ф is the comprehensive evaluation index of cluster division, β is the modularity index based on electrical distance; r1 is the weight of the modularity index; r2 is the weight of the purity offset characteristic index; W is the total number of scenarios, P(w i ) is w i The probability of the scenario.

[0029] As a preferred solution of the flexible distribution network energy storage planning method for distributed photovoltaic consumption described in the present invention, wherein: the establishment of a distribution network energy storage system capacity configuration model based on the screened fault data in combination with a genetic algorithm also includes:

[0030] Initialize the genetic algorithm population, combine it with the screened fault data, and evaluate the modularity index of each individual using the modularity index calculation formula;

[0031] The comprehensive index of cluster division is obtained according to the calculation formula of the comprehensive purity index of the whole system cluster division;

[0032] The modularity index and the comprehensive purity index are weighted to form a comprehensive evaluation index;

[0033] Determine whether the maximum number of iterations of the genetic algorithm has been reached. If not, the genetic algorithm generates the next generation population;

[0034] If it is reached, the calculation result is output.

[0035] As a preferred solution of the flexible distribution network energy storage planning method for distributed photovoltaic consumption described in the present invention, it also includes: updating the distribution network energy storage system capacity configuration model parameters and genetic algorithm parameters according to the real-time operating data of the distribution network.

[0036] The flexible distribution network energy storage planning system for distributed photovoltaic consumption is characterized by including: a data acquisition and screening module, a model building module and a planning module.

[0037] A data acquisition and screening module is used to acquire grid data, photovoltaic data, and load data of the distribution network in the target area, pre-process the data, and screen the pre-processed data to filter out fault data;

[0038] A model building module, wherein the model building module is used to establish a capacity configuration model of the distribution network energy storage system based on the screened fault data in combination with a genetic algorithm;

[0039] A planning module is used to perform flexible distribution network energy storage planning for distributed photovoltaic consumption based on the distribution network energy storage system capacity configuration model.

[0040] A computer device includes a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the above method when executing the computer program.

[0041] A computer-readable storage medium stores a computer program thereon, wherein the computer program implements the steps of the method described above when executed by a processor.

[0042] Beneficial effects of the present invention: The present invention proposes a flexible distribution network energy storage planning method and system for distributed photovoltaic absorption, which obtains the grid data, photovoltaic data and load data of the distribution network in the target area, pre-processes the data, and filters the pre-processed data to filter out fault data; based on the filtered fault data, combined with a genetic algorithm, a distribution network energy storage system capacity configuration model is established; based on the distribution network energy storage system capacity configuration model, flexible distribution network energy storage planning for distributed photovoltaic absorption is carried out. This patent coordinates deployment and flow control: The system can realize the coordinated deployment and flow control of multi-region distribution networks, achieve power balance and load balance between different regions, and improve the stability and reliability of the power grid. This patent can also be data-driven optimization: The system uses technologies such as clustering learning and deep reinforcement learning of historical big data to optimize the power transmission, load distribution, etc. of the distribution network, improve energy utilization efficiency and supply and demand balance. This patent can also perform fault diagnosis and intelligent control: The system can timely detect and handle fault conditions in the distribution network through equipment fault diagnosis and intelligent control, thereby improving the reliability and safety of the system. This patent agreement can also flexibly adapt to different scenarios: the system can switch the control mode of the flexible interconnection device according to the needs of different scenarios, flexibly respond to the characteristics of the power system and environmental conditions in different regions, and improve the adaptability and flexibility of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0044] FIG1 is a flowchart of a method and system for planning flexible distribution network energy storage for distributed photovoltaic consumption according to an embodiment of the present invention;

[0045] FIG2 is an energy storage configuration diagram of a photovoltaic distribution network of a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption provided by one embodiment of the present invention;

[0046] FIG3 is a diagram showing the model accuracy of a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption according to an embodiment of the present invention;

[0047] FIG4 is a model loss rate diagram of a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption provided by one embodiment of the present invention;

[0048] FIG5 is an internal structural diagram of a computer device of a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0049] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0050] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0051] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0052] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0053] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0054] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0055] Example 1

[0056] 1-5 , which illustrate a first embodiment of the present invention, provide a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption, including:

[0057] Obtain grid data, photovoltaic data, and load data of the distribution network in the target area, preprocess the data, and filter the preprocessed data to filter out fault data;

[0058] Among them, grid data, photovoltaic data and load data include grid structure, transformer capacity, line current carrying capacity, distributed photovoltaic power generation, and energy storage system energy status;

[0059] Specifically, fault data includes equipment network fault data, energy storage system energy data, power output, and charging efficiency;

[0060] It should be noted that the screening is performed using an improved robustness index, which is expressed as follows:

[0061] MDRI=1 / (1+e^(γ*(w_true-w_pred)))

[0062] Among them, γ is a hyperparameter that controls the steepness of the decision boundary, w_true is the true category weight, which indicates the actual importance of each category, and w_pred is the predicted category weight, which indicates the predicted importance of each category;

[0063] Furthermore, robustness indicator thresholds for equipment network fault data, energy storage system energy data, power output, and charging efficiency are designed respectively to filter out data that meets the threshold conditions.

[0064] It should be noted that the use of improved robustness indicators can improve the accuracy of data screening: by introducing improved robustness indicators, faulty data can be better screened out, thereby improving the accuracy of data screening. It can also enhance the robustness of the system: the improved robustness indicator can better handle incomplete, noisy, or highly variable data, allowing the system to maintain high performance and robustness when faced with abnormal data. It can also optimize the decision boundary: by adjusting the hyperparameter γ, the decision boundary can be optimized, thereby improving the accuracy and precision of classification. It can also adaptively adjust the threshold: according to the characteristics and distribution of different data, the threshold of each indicator can be adaptively adjusted to better adapt to different scenarios and needs.

[0065] In summary, the application of the improved robustness index enables the flexible distribution network energy storage planning method and system for distributed photovoltaic consumption to be more accurate and robust when processing complex and changeable distribution network data, and to adaptively adjust the threshold, thereby better meeting the needs of practical applications.

[0066] Furthermore, based on the screened fault data and combined with genetic algorithms, a capacity configuration model for the energy storage system in the distribution network is established;

[0067] Among them, based on the screened fault data and combined with the genetic algorithm, the distribution network energy storage system capacity configuration model is established, including:

[0068] The modularity indicators are as follows:

[0069] Among them, e i,j is the weight of the correlation parameter in the network, is the sum of all weights of parameters in the network, k i 、k j is the weight of parameter i and parameter j;

[0070] It should be noted that when parameter i and parameter j are in the same cluster, δ(i, j) = 1, otherwise δ(i, j) = 0.

[0071] Furthermore, based on the filtered fault data and combined with the genetic algorithm, the capacity configuration model of the distribution network energy storage system is established, which also includes:

[0072] The calculation formula for the comprehensive purity index of the whole system cluster division is as follows:

[0073] Among them, O wi is the comprehensive purity index in a certain scenario, is the number of clusters divided, For scene w i The power generation and consumption characteristic purity index value of cluster c is between -1 and 1.

[0074] Furthermore, based on the filtered fault data and combined with the genetic algorithm, the capacity configuration model of the distribution network energy storage system is established, which also includes:

[0075] The modularity index and the comprehensive purity index are weighted to form a comprehensive evaluation index Φ. The cluster for energy storage planning uses the partition optimization model to maximize Φ as the optimization goal. The formula is as follows:

[0076] Among them, Ф is the comprehensive evaluation index of cluster division, β is the modularity index based on electrical distance; r1 is the weight of the modularity index; r2 is the weight of the purity offset characteristic index; W is the total number of scenarios, P(w i ) is w i The probability of the scenario.

[0077] Furthermore, based on the filtered fault data and combined with the genetic algorithm, the capacity configuration model of the distribution network energy storage system is established, which also includes:

[0078] Initialize the genetic algorithm population, combine it with the screened fault data, and evaluate the modularity index of each individual using the modularity index calculation formula;

[0079] The comprehensive index of cluster division is obtained according to the calculation formula of the comprehensive purity index of the whole system cluster division;

[0080] The modularity index and the comprehensive purity index are weighted to form a comprehensive evaluation index;

[0081] Determine whether the maximum number of iterations of the genetic algorithm has been reached. If not, the genetic algorithm generates the next generation population;

[0082] If it is reached, the calculation result is output.

[0083] It should be noted that combining a genetic algorithm with a distribution network energy storage system capacity configuration model can optimize the decision boundary. By introducing an improved robustness index and a comprehensive evaluation index Φ, the decision boundary can be further optimized, improving classification accuracy and precision. System robustness can also be enhanced. The improved robustness index can better handle incomplete, noisy, or highly variable data, allowing the system to maintain high performance and robustness even in the face of abnormal data. Thresholds can also be automatically adjusted. Based on the characteristics and distribution of different data, the thresholds of various indicators can be adaptively adjusted to better adapt to different scenarios and needs. Computational complexity can also be reduced. Using a genetic algorithm to initialize the population and generate the next generation of populations avoids local optimal solutions, reduces computational complexity, and improves efficiency. Clustering effectiveness can also be enhanced. By weighting the modularity index and the comprehensive purity index to form the comprehensive evaluation index Φ, the effectiveness of different clustering divisions can be better measured, resulting in better clustering results.

[0084] In summary, the beneficial effects of combining genetic algorithms enable the flexible distribution network energy storage planning method and system for distributed photovoltaic consumption to be more accurate and robust when processing complex and changeable distribution network data, and to adaptively adjust the threshold, thereby better meeting the needs of practical applications.

[0085] Furthermore, based on the capacity configuration model of the distribution network energy storage system, flexible distribution network energy storage planning for distributed photovoltaic consumption is carried out.

[0086] It should be noted that the capacity configuration model parameters and genetic algorithm parameters of the distribution network energy storage system are updated according to the real-time operating data of the distribution network.

[0087] In summary, the present invention proposes a flexible distribution network energy storage planning method for distributed photovoltaic consumption. The method obtains the grid data, photovoltaic data, and load data of the distribution network in the target area, preprocesses the data, and filters the preprocessed data to filter out fault data. Based on the filtered fault data, a distribution network energy storage system capacity configuration model is established in combination with a genetic algorithm. Based on the distribution network energy storage system capacity configuration model, flexible distribution network energy storage planning for distributed photovoltaic consumption is carried out. This patent provides collaborative scheduling and flow control: The system can achieve collaborative scheduling and flow control of multi-region distribution networks, achieve power balance and load balancing between different regions, and improve the stability and reliability of the power grid. This patent can also enable data-driven optimization: The system uses technologies such as clustering learning and deep reinforcement learning of historical big data to optimize the power transmission and load distribution of the distribution network, improving energy utilization efficiency and supply and demand balance. This patent can also perform fault diagnosis and intelligent control: Through equipment fault diagnosis and intelligent control, the system can promptly detect and handle fault conditions in the distribution network, improving the reliability and safety of the system. This patent agreement can also flexibly adapt to different scenarios: the system can switch the control mode of the flexible interconnection device according to the needs of different scenarios, flexibly respond to the characteristics of the power system and environmental conditions in different regions, and improve the adaptability and flexibility of the system.

[0088] In a preferred embodiment, a flexible distribution network energy storage planning system for distributed photovoltaic consumption includes: a data acquisition and screening module, a model building module, and a planning module.

[0089] The data acquisition and screening module is used to obtain grid data, photovoltaic data, and load data of the distribution network in the target area, pre-process the data, and screen the pre-processed data to filter out fault data;

[0090] The model building module is used to establish a capacity configuration model of the distribution network energy storage system based on the screened fault data and combined with the genetic algorithm;

[0091] The planning module is used to carry out flexible distribution network energy storage planning for distributed photovoltaic consumption based on the distribution network energy storage system capacity configuration model.

[0092] The above-mentioned unit modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above-mentioned modules.

[0093] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG5 . The computer device includes a processor, memory, a communication interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal via wired or wireless communication. The wireless communication may be achieved via Wi-Fi, a carrier network, NFC (near-field communication), or other technologies. When executed by the processor, the computer program implements a flexible distribution network energy storage planning method for distributed photovoltaic consumption. The display screen of the computer device may be a liquid crystal display or an electronic ink display. The input device of the computer device may be a touch layer covering the display screen, or may be buttons, a trackball, or a touchpad provided on the computer device housing, or may be an external keyboard, touchpad, or mouse.

[0094] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0095] Obtain grid data, photovoltaic data, and load data of the distribution network in the target area, preprocess the data, and filter the preprocessed data to filter out fault data;

[0096] Based on the screened fault data and combined with genetic algorithm, a capacity configuration model for the distribution network energy storage system is established;

[0097] Based on the capacity configuration model of the distribution network energy storage system, flexible distribution network energy storage planning for distributed photovoltaic accommodation is carried out.

[0098] Example 2

[0099] 3-4 , which is an embodiment of the present invention, provides a flexible distribution network energy storage planning method and system for distributed photovoltaic consumption. In order to verify the beneficial effects of the present invention, a scientific demonstration is conducted through comparative experiments.

[0100] Figure 3 shows the accuracy of the proposed model. As can be seen, the model's accuracy gradually improves with increasing training data. When the training data is small, the accuracy is low, but it gradually improves as more data is added. This demonstrates that the proposed model has good generalization capabilities and can effectively learn useful information from large amounts of training data.

[0101] Figure 4 shows a graph of the loss rate for the model of the present invention. As can be seen from the graph, the model's loss rate gradually decreases as training progresses. This indicates that the model gradually acquires better feature representation and classification capabilities during training. Furthermore, it can be seen that the rate of loss rate decreases somewhat slower in the middle and late stages of training. This may be because the model is nearing convergence, and factors such as noise and overfitting in the training data begin to affect model performance.

[0102] In this paper, stochastic gradient descent (SGD) was used as the optimization algorithm, and the learning rate was set to 0.01. At the same time, L2 regularization was used to prevent model overfitting, and the regularization parameter was set to 0.001. These parameters can be adjusted according to different datasets and tasks.

[0103] In addition to the parameters mentioned above, data augmentation techniques are used to increase the diversity of the training data. Data augmentation is a technique that generates new data by randomly transforming the data, which can increase the generalization ability of the model. In this paper, data augmentation techniques such as random cropping and random horizontal flipping are used to improve the performance of the model.

[0104] In summary, by using appropriate data augmentation techniques and parameter adjustments, better performing models can be trained to better solve classification problems.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

[0106] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. The scheme in the embodiment of the present application can be implemented in various computer languages, for example, object-oriented programming language Java and literal translation scripting language JavaScript, etc.

[0107] The present application is described with reference to the flow chart and / or block diagram of the method, device (system), and computer program product according to the embodiment of the present application. It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processing machine or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for realizing the function specified in one flow chart flow or multiple flows and / or one box or multiple boxes of the block diagram.

[0108] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0109] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0110] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0111] Obviously, those skilled in the art may make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is intended to include these modifications and variations.

Claims

1. A flexible distribution network energy storage planning method for distributed photovoltaic consumption, characterized in that: include: Acquire grid data, photovoltaic data, and load data of the distribution network in the target area, preprocess the data, and filter the preprocessed data to filter out fault data; Based on the screened fault data and combined with genetic algorithm, a capacity configuration model for the energy storage system of the distribution network is established; According to the distribution network energy storage system capacity configuration model, flexible distribution network energy storage planning for distributed photovoltaic consumption is carried out.

2. The flexible distribution network energy storage planning method for distributed photovoltaic consumption according to claim 1 is characterized in that: The obtaining of grid data, photovoltaic data and load data of the distribution network in the target area, preprocessing the data, and screening the preprocessed data to screen out fault data includes: The grid data, photovoltaic data and load data include grid structure, transformer capacity, line current carrying capacity, distributed photovoltaic power generation, and energy status of energy storage system; The fault data includes equipment network fault data, energy storage system energy data, power output, and charging efficiency; The screening is performed using an improved robustness index, and the improved robustness index expression is as follows: MDRI=1 / (1+e^(γ*(w_true-w_pred))) Among them, γ is a hyperparameter that controls the steepness of the decision boundary, w_true is the true category weight, indicating the actual importance of each category, and w_pred is the predicted category weight, indicating the predicted importance of each category; The robustness indicator thresholds of equipment network fault data, energy storage system energy data, power output, and charging efficiency are designed respectively, and the data that meets the threshold conditions are screened out.

3. The flexible distribution network energy storage planning method for distributed photovoltaic consumption according to claim 2 is characterized in that: The establishment of a distribution network energy storage system capacity configuration model based on the screened fault data and in combination with a genetic algorithm includes: The modularity indicators are as follows: Among them, e i,j is the weight of the correlation parameter in the network, Ownership of parameters in the network The sum of the weights, k i , k j is the weight of parameter i and parameter j; When parameter i and parameter j are in the same cluster, δ(i, j) = 1, otherwise δ(i, j) = 0.

4. The flexible distribution network energy storage planning method for distributed photovoltaic consumption according to claim 3 is characterized in that: The method of establishing a capacity configuration model for the distribution network energy storage system based on the screened fault data and in combination with a genetic algorithm also includes: The calculation formula for the comprehensive purity index of the whole system cluster division is as follows: Among them, O wi is the comprehensive purity index in a certain scenario. is the number of clusters divided, For scene w i The power generation and consumption characteristics purity index value of cluster c is between -1 and 1.

5. The flexible distribution network energy storage planning method for distributed photovoltaic consumption as claimed in claim 4 is characterized in that: The method of establishing a capacity configuration model for the distribution network energy storage system based on the screened fault data and in combination with a genetic algorithm also includes: The modularity index and the comprehensive purity index are weighted to form a comprehensive evaluation index Ф. The cluster for energy storage planning uses the maximum Ф as the optimization target according to the partition optimization model. The formula is as follows: Among them, Ф is the comprehensive evaluation index of cluster division, β is the modularity index based on electrical distance; r1 is the weight of the modularity index; r2 is the weight of the purity offset characteristic index; W is the total number of scenes, P(w i ) is w i The probability of the scenario.

6. The flexible distribution network energy storage planning method for distributed photovoltaic consumption according to claim 5 is characterized in that: The method of establishing a capacity configuration model for the distribution network energy storage system based on the screened fault data and in combination with a genetic algorithm also includes: Initialize the genetic algorithm population, combine the screened fault data, and evaluate the modularity index of each individual through the modularity index calculation formula; The comprehensive index of cluster division is obtained according to the calculation formula of the comprehensive purity index of the whole system cluster division; The modularity index and the comprehensive purity index are weighted to form a comprehensive evaluation index; Determine whether the maximum number of iterations of the genetic algorithm has been reached. If not, the genetic algorithm generates the next generation population; If it is reached, the calculation result is output.

7. The flexible distribution network energy storage planning method for distributed photovoltaic consumption according to claim 6 is characterized in that: Also includes: The capacity configuration model parameters and genetic algorithm parameters of the distribution network energy storage system are updated according to the real-time operating data of the distribution network.

8. Flexible distribution network energy storage planning system for distributed photovoltaic consumption, characterized by: include: Data acquisition and screening module, model building module and planning module, A data acquisition and screening module, which is used to acquire grid data, photovoltaic data and load data of the distribution network in the target area, pre-process the data, and screen the pre-processed data to screen out fault data; A model building module, wherein the model building module is used to build a capacity configuration model of a distribution network energy storage system based on the screened fault data in combination with a genetic algorithm; A planning module is used to carry out flexible distribution network energy storage planning for distributed photovoltaic consumption according to the distribution network energy storage system capacity configuration model.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images