Line Loss Optimization System and Method Based on Distributed Photovoltaic Topology Analysis

Abstract

The present invention provides a line loss optimization system and method based on distributed photovoltaic topology analysis, which relates to the technical field of distributed photovoltaic, and includes: a topology connection module for performing topology connection to establish a distributed photovoltaic distribution network topology model; a prediction modeling module for performing prediction modeling to obtain a photovoltaic output-grid load spatio-temporal prediction model; an access location optimization module for optimizing the photovoltaic access location and iteratively obtaining a distributed photovoltaic optimized distribution network topology model; a strategy analysis module for performing strategy analysis to determine the line loss control strategy parameters of the distribution network; and a feedback optimization module for performing simulation evaluation and feedback optimization on the line loss control strategy parameters of the distribution network. The present invention solves the technical problem in the prior art that the line loss control strategy of the distribution network is often set based on experience and does not fully combine the dynamic characteristics of photovoltaic power generation and load for real-time adjustment, resulting in poor line loss control effect.

Description

Technical Field

[0001] The present invention relates to the technical field of distributed photovoltaic, and particularly to a line loss optimization system and method based on distributed photovoltaic topology analysis. Background Art

[0002] Distributed photovoltaic power generation is one of the widely used clean energy forms in modern power systems. However, the intermittency, volatility of photovoltaic power generation, and the geographical dispersion of its distribution bring new challenges to the power grid. The problem of power grid line loss has become an important issue that urgently needs to be optimized in power grid operation. Specifically, the selection of the access point of the photovoltaic system has a great impact on the operation of the power grid. An improper access location may lead to long-distance transmission of electricity, thus causing a large amount of transmission losses. Especially in low-voltage distribution networks, the problem of current loss is particularly prominent. In the prior art, the line loss control strategy of the distribution network is often set based on experience and does not fully combine the dynamic characteristics of photovoltaic power generation and load for real-time adjustment, resulting in poor line loss control effect and energy loss in the transmission line. Summary of the Invention

[0003] This application provides a line loss optimization system and method based on distributed photovoltaic topology analysis, aiming to solve the technical problem that the line loss control strategy of the distribution network in the prior art is often set based on experience and does not fully combine the dynamic characteristics of photovoltaic power generation and load for real-time adjustment, resulting in poor line loss control effect.

[0004] In the first aspect disclosed in this application, a line loss optimization system based on distributed photovoltaic topology analysis is provided. The system includes: a topology connection module, which is used to collect and obtain the basic distribution data of the distribution network and the photovoltaic access data, define the graph connection attributes, and perform topology connection on the basic distribution data of the distribution network and the photovoltaic access data based on the graph connection attributes to establish a distributed photovoltaic distribution network topology model; a prediction modeling module, which is used to obtain a photovoltaic output dataset and a power grid load dataset through data mining technology, and use time series analysis to perform prediction modeling on the photovoltaic output dataset and the power grid load dataset to obtain a photovoltaic output-power grid load spatio-temporal prediction model; an access location optimization module, which is used to initialize the particle swarm parameters based on the distributed photovoltaic distribution network topology model, optimize the photovoltaic access location for the particle swarm parameters according to the line loss optimization target, and iteratively obtain a distributed photovoltaic optimized distribution network topology model; a strategy analysis module, which is used to obtain the spatio-temporal distribution characteristic information of the photovoltaic load based on the photovoltaic output-power grid load spatio-temporal prediction model, and perform strategy analysis based on the spatio-temporal distribution characteristic information of the photovoltaic load and the distributed photovoltaic optimized distribution network topology model to determine the line loss control strategy parameters of the distribution network; a feedback optimization module, which is used to perform simulation evaluation on the line loss control strategy parameters of the distribution network, obtain the distribution network loss reduction simulation effect, and perform feedback optimization on the line loss control strategy parameters of the distribution network based on the distribution network loss reduction simulation effect.

[0005] Furthermore, the establishment of the distributed photovoltaic distribution network topology model includes:

[0006] According to the graph connection attributes, determine the entity node attributes and the node connection edge attributes; based on the entity node attributes, perform entity recognition and attribute identification on the basic distribution data of the distribution network and the photovoltaic access data to obtain a distribution network entity set and an entity node attribute set; analyze the connection relationship of the distribution network entity set through the basic distribution data of the distribution network and the photovoltaic access data to construct a node adjacent connection relationship set; perform topology abstraction on the node adjacent connection relationship set based on the node connection edge attributes to obtain an entity node topology adjacency matrix; perform topology identification connection on the distribution network entity set based on the entity node topology adjacency matrix and the entity node attribute set to establish the distributed photovoltaic distribution network topology model.

[0007] Furthermore, the obtaining of the photovoltaic output-power grid load spatio-temporal prediction model includes:

[0008] Use time series analysis to perform time series arrangement and characteristic analysis on the photovoltaic output data set and the power grid load data set, and obtain the photovoltaic output characteristic data set and the power grid load characteristic data set; perform prediction training on the photovoltaic output characteristic data set and the power grid load characteristic data set respectively through the LSTM network to obtain the photovoltaic output prediction model and the power grid load prediction model; perform parallel fusion on the photovoltaic output prediction model and the power grid load prediction model to generate the initial photovoltaic load spatio-temporal prediction model; use the model optimizer to verify and optimize the initial photovoltaic load spatio-temporal prediction model to obtain the photovoltaic output-power grid load spatio-temporal prediction model.

[0009] Furthermore, the iterative acquisition of the distributed photovoltaic optimized distribution network topology model includes:

[0010] Extract the line loss evaluation index for the line loss optimization target to obtain the line loss evaluation index set, and construct the line loss optimization effect fitness function according to the line loss evaluation index set; determine the parameter particle position and parameter particle velocity according to the particle swarm parameters, and use the line loss optimization effect fitness function to evaluate the fitness of the particle swarm parameters to obtain the particle swarm fitness set; perform iterative update on the parameter particle position and parameter particle velocity based on the particle swarm fitness set until the preset termination condition is met, and optimize to determine the optimal parameter particle with the maximum fitness. The optimal parameter particle includes the optimized position of photovoltaic access; optimize and update the distributed photovoltaic distribution network topology model based on the optimized position of photovoltaic access to obtain the distributed photovoltaic optimized distribution network topology model.

[0011] Furthermore, the determination of the distribution network line loss control strategy parameters includes:

[0012] Perform an analysis on the impact of the power grid power flow distribution based on the distributed photovoltaic optimized distribution network topology model to obtain the power grid power flow distribution impact parameters, where the power grid power flow distribution impact parameters include line load impact parameters and power grid line loss impact parameters; construct a line loss control strategy library, and perform matching analysis with the line loss control strategy library based on the spatio-temporal distribution characteristic information of the photovoltaic load and the power grid power flow distribution impact parameters to obtain the distribution network line loss matching control strategy; perform threshold division on the spatio-temporal distribution characteristic information of the photovoltaic load and the power grid power flow distribution impact parameters based on the distribution network line loss matching control strategy to obtain the threshold for selecting the line loss control strategy parameters; use the line loss optimization effect fitness function to perform global optimization within the threshold for selecting the line loss control strategy parameters to determine the distribution network line loss control strategy parameters.

[0013] Furthermore, the determination of the distribution network line loss control strategy parameters includes:

[0014] Randomly select multiple policy parameters within the threshold for selecting line loss control policy parameters, and use the fitness function of the line loss optimization effect to evaluate the multiple policy parameters to obtain multiple parameter fitness values; approximate the search area for the threshold of the line loss control policy parameters based on the multiple parameter fitness values to determine the local search area for the policy parameters; set the parameter search step size according to the local search area for the policy parameters; perform policy parameter search and evaluation within the local search area for the policy parameters according to the parameter search step size, and perform iterative approximation of the search area based on the parameter search and evaluation results until the preset number of iterations, and determine the line loss control policy parameters of the distribution network through fitness comparison.

[0015] Furthermore, the feedback optimization of the line loss control policy parameters of the distribution network based on the distribution network loss reduction simulation effect includes:

[0016] Analyze the optimization direction of the line loss control policy parameters of the distribution network based on the distribution network loss reduction simulation effect to obtain the parameter mutation optimization rule; expand the line loss control policy parameters by mutation according to the parameter mutation optimization rule to obtain a cluster of line loss control policy parameters; perform parameter comparison and optimization within the cluster of line loss control policy parameters to obtain the optimized line loss control policy parameters, and perform line loss optimization control of the distribution network through the optimized line loss control policy parameters.

[0017] The second aspect disclosed in this application provides a line loss optimization method based on distributed photovoltaic topology analysis. The method is implemented through the above-mentioned line loss optimization system based on distributed photovoltaic topology analysis. The method includes: collecting and obtaining the basic distribution data and photovoltaic access data of the distribution network, and defining the graph connection attributes, and performing topological connection on the basic distribution data and photovoltaic access data of the distribution network based on the graph connection attributes to establish a distributed photovoltaic distribution network topological model; obtaining the photovoltaic output data set and the power grid load data set through data mining technology, and using time series analysis to perform prediction modeling on the photovoltaic output data set and the power grid load data set to obtain a photovoltaic output-power grid load spatio-temporal prediction model; initializing the particle swarm parameters based on the distributed photovoltaic distribution network topological model, optimizing the photovoltaic access position of the particle swarm parameters according to the line loss optimization target, and iteratively obtaining an optimized distributed photovoltaic distribution network topological model; obtaining the spatio-temporal distribution characteristic information of the photovoltaic load based on the photovoltaic output-power grid load spatio-temporal prediction model, and performing policy analysis based on the spatio-temporal distribution characteristic information of the photovoltaic load and the optimized distributed photovoltaic distribution network topological model to determine the line loss control policy parameters of the distribution network; performing simulation evaluation on the line loss control policy parameters of the distribution network to obtain the distribution network loss reduction simulation effect, and performing feedback optimization on the line loss control policy parameters of the distribution network based on the distribution network loss reduction simulation effect.

[0018] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0019] A distributed photovoltaic distribution network topology model is established. This model effectively integrates the basic distribution data of the distribution network and the photovoltaic access data to form a clear network structure. Using the method of graph theory topological connection, it accurately reflects the connection relationship between each node in the power grid, enabling the visualization analysis of the impact of photovoltaic access on the power grid power flow; data mining and time series analysis technologies are used to construct a photovoltaic output-grid load spatio-temporal prediction model. This model synthesizes the spatio-temporal characteristics of photovoltaic power generation and the dynamic changes of the power grid load demand, and realizes the matching prediction of photovoltaic power generation and power grid load demand; the particle swarm algorithm is used to optimize the photovoltaic access location, iteratively adjust the optimal location of the photovoltaic access point based on the line loss optimization goal, and form an optimized distributed photovoltaic optimized distribution network topology model. This process combines the power grid topology structure and the prediction model, enabling the photovoltaic access point to minimize the line loss in the power grid operation, reduce the loss in the power transmission process, and achieve the rational allocation of power grid resources and the maximization of power efficiency; through the comprehensive analysis of the spatio-temporal distribution characteristics of photovoltaic load, combined with the distributed photovoltaic optimized distribution network topology model, effective distribution network line loss control strategy parameters are formulated, which can respond to the dynamic changes of photovoltaic output and power grid load in real time. By reasonably dispatching photovoltaic power generation and adjusting the power flow path, the line loss is further reduced; simulation evaluation and feedback optimization are carried out. The formulated line loss control strategy is verified through simulation, and parameter optimization feedback is carried out according to the simulation results. This process ensures the effectiveness and pertinence of the line loss control strategy, enables the strategy to be continuously adjusted and improved according to the actual situation, realizes closed-loop optimization, and ensures the minimization of line loss during power grid operation.

[0020] The above description is only an overview of the technical solutions of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the following specific embodiments of this application are specifically given. Brief Description of the Drawings

[0021] Figure 1 It is a schematic structural diagram of a line loss optimization system based on distributed photovoltaic topology analysis provided by an embodiment of this application;

[0022] Figure 2 It is a schematic flow diagram of a line loss optimization method based on distributed photovoltaic topology analysis provided by an embodiment of this application.

[0023] Description of the reference numerals: Topological connection module 10, prediction modeling module 20, access location optimization module 30, strategy analysis module 40, feedback optimization module 50. Detailed Description of the Embodiment

[0024] By providing a line loss optimization system and method based on distributed photovoltaic topology analysis, the embodiment of the present application solves the technical problem in the prior art that the line loss control strategy of the distribution network is often set based on experience and does not fully combine the dynamic characteristics of photovoltaic power generation and load for real-time adjustment, resulting in poor line loss control effect.

[0025] After introducing the basic principle of the present application, the various non-restrictive embodiments of the present application will be specifically introduced below in conjunction with the accompanying drawings of the specification. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0026] Embodiment 1, as Figure 1 shown, the embodiment of the present application provides a line loss optimization system based on distributed photovoltaic topology analysis. The system includes:

[0027] A topology connection module 10 for collecting and obtaining the basic distribution data of the distribution network and the photovoltaic access data, defining the graph connection attributes, and performing topology connection on the basic distribution data of the distribution network and the photovoltaic access data based on the graph connection attributes to establish a distributed photovoltaic distribution network topology model; a prediction modeling module 20 for obtaining a photovoltaic output - grid load spatio-temporal prediction model by using data mining technology to associate and obtain a photovoltaic output data set and a grid load data set and performing prediction modeling on the photovoltaic output data set and the grid load data set using time series analysis; an access location optimization module 30 for initializing the particle swarm parameters based on the distributed photovoltaic distribution network topology model, optimizing the photovoltaic access location for the particle swarm parameters according to the line loss optimization target, and iteratively obtaining a distributed photovoltaic optimized distribution network topology model; a strategy analysis module 40 for obtaining the spatio-temporal distribution characteristic information of the photovoltaic load based on the photovoltaic output - grid load spatio-temporal prediction model, and performing strategy analysis based on the spatio-temporal distribution characteristic information of the photovoltaic load and the distributed photovoltaic optimized distribution network topology model to determine the line loss control strategy parameters of the distribution network; a feedback optimization module 50 for performing simulation evaluation on the line loss control strategy parameters of the distribution network to obtain the distribution network loss reduction simulation effect, and performing feedback optimization on the line loss control strategy parameters of the distribution network based on the distribution network loss reduction simulation effect.

[0028] Furthermore, the establishment of the distributed photovoltaic distribution network topology model includes:

[0029] Determine the entity node attributes and node connection edge attributes according to the described graph connection attributes; perform entity recognition and attribute identification on the distribution network basic distribution data and photovoltaic access data based on the entity node attributes to obtain a distribution network entity set and an entity node attribute set; analyze the connection relationships of the distribution network entity set through the distribution network basic distribution data and photovoltaic access data to construct a node proximity connection relationship set; perform topological abstraction on the node proximity connection relationship set based on the node connection edge attributes to obtain an entity node topological adjacency matrix; perform topological identification connection on the distribution network entity set based on the entity node topological adjacency matrix and the entity node attribute set to establish the distributed photovoltaic distribution network topological model.

[0030] Furthermore, the obtaining of the photovoltaic output-grid load spatio-temporal prediction model includes:

[0031] Use time series analysis to perform time series arrangement and characteristic analysis on the photovoltaic output data set and the grid load data set to obtain a photovoltaic output characteristic data set and a grid load characteristic data set; perform prediction training on the photovoltaic output characteristic data set and the grid load characteristic data set respectively through an LSTM network to obtain a photovoltaic output prediction model and a grid load prediction model; perform parallel fusion on the photovoltaic output prediction model and the grid load prediction model to generate an initial photovoltaic load spatio-temporal prediction model; use a model optimizer to verify and optimize the initial photovoltaic load spatio-temporal prediction model to obtain the photovoltaic output-grid load spatio-temporal prediction model.

[0032] Furthermore, the iterative obtaining of the distributed photovoltaic optimized distribution network topological model includes:

[0033] Extract line loss evaluation indicators for the line loss optimization target to obtain a line loss evaluation indicator set, and construct a line loss optimization effect fitness function according to the line loss evaluation indicator set; determine the parameter particle position and parameter particle velocity according to the particle swarm parameters, and use the line loss optimization effect fitness function to perform fitness evaluation on the particle swarm parameters to obtain a particle swarm fitness set; perform iterative update on the parameter particle position and parameter particle velocity based on the particle swarm fitness set until the preset termination condition is met, and optimize and determine the optimal parameter particle with the maximum fitness. The optimal parameter particle includes the optimized position of photovoltaic access; optimize and update the distributed photovoltaic distribution network topological model based on the optimized position of photovoltaic access to obtain the distributed photovoltaic optimized distribution network topological model.

[0034] Furthermore, the determination of the distribution network line loss control strategy parameters includes:

[0035] Based on the distributed photovoltaic optimized distribution network topology model, an analysis of the impact on the power flow distribution of the power grid is carried out to obtain the parameters affecting the power flow distribution of the power grid. The parameters affecting the power flow distribution of the power grid include the line load impact parameter and the power grid line loss impact parameter; a line loss control strategy library is constructed. Based on the spatio-temporal distribution characteristic information of the photovoltaic load and the parameters affecting the power flow distribution of the power grid, a matching analysis is carried out with the line loss control strategy library to obtain the matching control strategy for the distribution network line loss; based on the matching control strategy for the distribution network line loss, a threshold division is carried out on the spatio-temporal distribution characteristic information of the photovoltaic load and the parameters affecting the power flow distribution of the power grid to obtain the threshold for selecting the line loss control strategy parameters; the line loss optimization effect fitness function is used to perform global optimization within the threshold for selecting the line loss control strategy parameters to determine the line loss control strategy parameters for the distribution network.

[0036] Furthermore, the determination of the line loss control strategy parameters for the distribution network includes:

[0037] Randomly select multiple strategy parameters within the threshold for selecting the line loss control strategy parameters, and use the line loss optimization effect fitness function to evaluate the multiple strategy parameters to obtain multiple parameter fitness values; based on the multiple parameter fitness values, approximate the optimization region of the threshold for selecting the line loss control strategy parameters to determine the local optimization region of the strategy parameters; according to the local optimization region of the strategy parameters, set the parameter search step size; perform a search and evaluation of the strategy parameters within the local optimization region of the strategy parameters according to the parameter search step size, and perform an iterative approximation of the optimization region according to the parameter search evaluation results until the preset number of iterations, and determine the line loss control strategy parameters for the distribution network through fitness comparison.

[0038] Furthermore, the feedback optimization of the line loss control strategy parameters for the distribution network based on the distribution network loss reduction simulation effect includes:

[0039] Based on the distribution network loss reduction simulation effect, an analysis of the optimization direction of the line loss control strategy parameters for the distribution network is carried out to obtain the parameter mutation and optimization rules; based on the parameter mutation and optimization rules, the line loss control strategy parameters for the distribution network are mutated and expanded to obtain a cluster of line loss control strategy parameters; parameter comparison and optimization are carried out within the cluster of line loss control strategy parameters to obtain the optimized line loss control strategy parameters, and the distribution network line loss is optimized and controlled through the optimized line loss control strategy parameters.

[0040] Through the subsequent detailed description of the line loss optimization method based on distributed photovoltaic topology analysis in this specification, those skilled in the art can clearly know the line loss optimization system based on distributed photovoltaic topology analysis in this embodiment. Since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method section.

[0041] Embodiment 2, based on the same inventive concept as the line loss optimization system based on distributed photovoltaic topology analysis in the foregoing embodiment, as Figure 2 shown, an embodiment of the present application provides a line loss optimization method based on distributed photovoltaic topology analysis, and the method includes:

[0042] Collect and obtain the basic distribution data of the distribution network and the photovoltaic access data, and define the graph connection attributes. Based on the graph connection attributes, perform topological connection on the basic distribution data of the distribution network and the photovoltaic access data to establish a distributed photovoltaic distribution network topology model.

[0043] Collect and obtain the basic distribution data of the distribution network and the photovoltaic access data through sensors, data acquisition systems, etc. Among them, the basic distribution data is the basic information related to the distribution network, such as the geographical locations, connection relationships, capacities, load data, etc. of substations, lines, load points, branches, etc. The photovoltaic access data refers to the relevant information of the distributed photovoltaic system accessing the distribution network, including the geographical location of the photovoltaic power generation system, the access point location, the access power, the installed capacity, the power generation curve, etc.

[0044] Define the graph connection attributes. The graph connection attributes refer to the connection relationships between each node (such as substation nodes, photovoltaic nodes, load nodes) defined in topological modeling, including entity node attributes and node connection edge attributes. Among them, the entity node attributes include entities in the distribution network, such as substations, user loads, and photovoltaic sites. The node connection edge attributes represent the connection relationships between nodes and usually represent lines.

[0045] Based on the graph connection attributes, perform topological connection on the basic distribution data of the distribution network and the photovoltaic access data. This means mapping the actual physical devices and connection relationships into a graph structure, connecting each node together according to their geographical locations or electrical connection methods. Specifically, through the basic distribution data of the distribution network and the photovoltaic access data, identify each entity node in the network, such as load nodes, power generation nodes, substation nodes, etc. Based on the line distribution of the distribution network, the photovoltaic access location, etc., construct the adjacency relationship between nodes, generate the corresponding connection edges, abstract the physical structure of the distribution network into a topological graph, where the nodes represent the physical entities in the network and the edges represent the power lines. Based on the topological connection result, establish a distributed photovoltaic distribution network topology model. This model describes the connection methods of each node and edge in the distribution network and serves as the basis for subsequent analysis.

[0046] Associate and obtain the photovoltaic output data set and the power grid load data set through data mining technology, and use time series analysis to perform predictive modeling on the photovoltaic output data set and the power grid load data set to obtain a photovoltaic output-power grid load spatio-temporal prediction model.

[0047] Data mining technology refers to the technology of extracting useful information from a large amount of raw data. Here, the goal of data mining is to extract the photovoltaic output dataset and the power grid load dataset from the monitoring data and historical data of the distribution network. Among them, the photovoltaic output dataset includes time-series data related to photovoltaic power generation, such as the power generation amount, power generation power, light intensity, temperature, etc. of the photovoltaic power generation system. The photovoltaic output data is affected by factors such as meteorological conditions and time (such as seasons and day length). The power grid load dataset includes time-series data of load demand in the power grid, such as power consumption and load change rate. The power grid load data is affected by various factors such as weather, time, and user demand.

[0048] Time series analysis is a technology used to analyze time series data. It uses the time characteristics of the data for modeling and prediction. Time series analysis is performed on the photovoltaic output dataset and the power grid load dataset respectively to capture their spatio-temporal variation laws. Specifically, the photovoltaic output dataset and the power grid load dataset are arranged in chronological order to construct a time series. For example, the power generation amount or electricity load at different times within a day. The characteristics of these time series data are analyzed to identify influencing factors, such as seasonal trends, daily fluctuations, peak and valley electricity consumption periods, etc. Photovoltaic power generation and power grid load may exhibit periodic and seasonal fluctuations. According to the characteristics of the data, a time series prediction model is established to obtain the photovoltaic output prediction model and the power grid load prediction model. The models are combined in parallel and verified and optimized to generate the spatio-temporal prediction model of photovoltaic output - power grid load.

[0049] Initialize the particle swarm parameters based on the distributed photovoltaic distribution network topology model, and optimize the photovoltaic access location according to the line loss optimization goal, and iteratively obtain the distributed photovoltaic optimized distribution network topology model.

[0050] Use the particle swarm optimization algorithm to optimize the photovoltaic access location. The particle swarm optimization algorithm is an optimization algorithm based on swarm intelligence, which simulates the cooperative behavior of bird flocks or fish schools in the process of finding food. Each particle represents a potential solution to the problem. Through the information exchange and update between particles, it gradually approaches the optimal solution.

[0051] First, initialize the particle swarm parameters based on the distributed photovoltaic distribution network topology model, that is, randomly generate a group of particles. Each particle represents a candidate solution for the photovoltaic access location. All particles together form a particle swarm. The particles within the group will continuously move in the solution space to gradually optimize the access location. Define the line loss optimization goal, that is, to find the photovoltaic power generation access location so that the line loss of the distribution network is minimized after the photovoltaic system is connected.

[0052] Optimize the photovoltaic access location according to the line loss optimization goal. Specifically, calculate the line loss of the distribution network based on the photovoltaic access location of each particle. The calculated fitness value represents the quality of the current solution of each particle. The goal is to minimize the line loss. Update the velocity of the particle according to the current velocity and the current best position (personal best position and global best position) of the particle. Update the position of the particle according to the new velocity, calculate the new fitness of the updated particle, that is, the line loss of the new access location, and update the personal best position and global best position of each particle.

[0053] Through multiple iterations, the particle swarm algorithm continuously adjusts the access position of the particles and gradually approaches the optimal solution. After each iteration, update the distribution network topology model according to the current best photovoltaic access position. When the particle swarm algorithm converges or reaches the preset number of iterations, determine the optimal particle with the maximum fitness, that is, the optimal solution of the photovoltaic access position. At this time, the access position of the distributed photovoltaic has been determined through optimization, and an optimized distributed photovoltaic distribution network topology model can be obtained. This model has better line loss performance than the initial model and can significantly reduce the loss in power transmission.

[0054] Obtain the spatio-temporal distribution characteristic information of photovoltaic load according to the photovoltaic output-grid load spatio-temporal prediction model. Based on the spatio-temporal distribution characteristic information of photovoltaic load and the optimized distributed photovoltaic distribution network topology model, conduct strategy analysis to determine the line loss control strategy parameters of the distribution network.

[0055] According to the photovoltaic output-grid load spatio-temporal prediction model, predict the photovoltaic output and grid load at different future time and space nodes, and generate the spatio-temporal distribution characteristic information of photovoltaic load, including the output capacity of photovoltaic power generation at different times (temporality), the distribution of grid load in different regions (spatiality), and the matching degree between the photovoltaic power generation and the grid load.

[0056] Conduct strategy analysis. Specifically, analyze the change in power flow in the power grid, that is, the power flow distribution in the power grid. After the access of photovoltaic power generation, it will change the power distribution in the power grid. It is necessary to analyze how power is transmitted and exchanged in the power grid at different times and in different regions, especially the impact of the access of photovoltaic power generation on the power flow, including the line load and line loss distribution. According to the analysis results, conduct matching analysis in the line loss control strategy library to obtain the line loss matching control strategy of the distribution network. Based on the line loss matching control strategy of the distribution network, conduct global optimization within the parameter selection threshold to determine the line loss control strategy parameters of the distribution network.

[0057] Conduct simulation evaluation on the line loss control strategy parameters of the distribution network to obtain the simulation effect of distribution network loss reduction, and conduct feedback optimization on the line loss control strategy parameters of the distribution network based on the simulation effect of distribution network loss reduction.

[0058] Using a distributed photovoltaic distribution network topology model, a simulation environment is constructed. The determined parameters of the distribution network line loss control strategy are imported into the simulation environment. Different load scenarios and photovoltaic power generation scenarios are run in the simulation environment to simulate the actual operation of the distribution network. The scenarios can include typical peak and valley electricity consumption, and changes in photovoltaic power generation under different weather conditions. During the simulation process, data such as the power flow distribution, voltage conditions, and photovoltaic power generation access volume of the distribution network are recorded in real time, and the line loss under the simulation is calculated. As the simulation result, the effectiveness of the line loss control strategy is evaluated based on the simulation result. The evaluation indicators mainly include line loss change, that is, by simulating and calculating the distribution network line loss under different scenarios, comparing the line loss before and after applying the line loss control strategy, and observing whether the line loss is significantly reduced. It also includes voltage stability, load matching degree, power flow distribution, etc.

[0059] If the simulation result shows that the line loss does not reach the expected reduction effect, or there are problems with voltage stability, then the relevant control strategy parameters are optimized. For example, the priority of photovoltaic access points is adjusted to ensure that more photovoltaic power generation can be consumed locally and long-distance power transmission is reduced until the simulation result meets the expected requirements. By feedback-optimizing the strategy parameters, the accuracy and effectiveness of the control strategy can be further improved, thus ultimately achieving the effect of minimizing the line loss.

[0060] Furthermore, the establishment of the distributed photovoltaic distribution network topology model includes:

[0061] According to the graph connection attributes, the entity node attributes and node connection edge attributes are determined; based on the entity node attributes, entity recognition and attribute identification are performed on the distribution network basic distribution data and photovoltaic access data to obtain the distribution network entity set and the entity node attribute set; through the distribution network basic distribution data and photovoltaic access data, connection relationship analysis is performed on the distribution network entity set to construct a node adjacent connection relationship set; based on the node connection edge attributes, topological abstraction is performed on the node adjacent connection relationship set to obtain an entity node topological adjacency matrix; based on the entity node topological adjacency matrix and the entity node attribute set, topological identification connection is performed on the distribution network entity set to establish the distributed photovoltaic distribution network topology model.

[0062] The graph connection attributes are characteristic attributes used to describe the connection relationship between each node and its mutual relationship in the distribution network. All relevant node basic data are obtained from the distribution network, such as the geographical locations and equipment characteristics of substations, photovoltaic access points, load points, switches, etc. Specific attributes are defined for each node, such as what type of node the node is, the voltage level and capacity of the node, etc., as the entity node attributes; for each pair of connected nodes, the attributes of the line between them, such as length, impedance, maximum load current, etc., are defined as the node connection edge attributes.

[0063] By analyzing the basic distribution data of the distribution network and the photovoltaic access data, all entity node types in the distribution network are identified, which generally include: substation nodes, serving as the power source or voltage conversion point of the power grid; photovoltaic nodes, representing the access points of distributed photovoltaic power generation systems; load nodes, representing the points of power consumption; and other nodes, such as switches, sectionalizing points, etc., depending on specific requirements. For each identified entity node, attribute identification is carried out according to its physical characteristics and power functions, such as voltage level, power, geographical location, etc. All the identified and labeled entity nodes are integrated to form a set of distribution network entities, that is, the set of all nodes in the distribution network, and a set of entity node attributes, including the detailed attributes of each node.

[0064] Using the basic distribution data of the distribution network and the photovoltaic access data, the topological structure of the distribution network is analyzed to identify the neighboring nodes of each node. Neighboring nodes refer to the nodes directly connected by lines. For example, a photovoltaic node may be adjacent to the nearest substation or load node. Based on the identified neighboring nodes, connection direction and distance analysis are carried out. Specifically, the power flow direction is determined. For example, in a typical distribution network, power usually flows from the substation node to the load node. The line length between two nodes is calculated through the basic distribution data of the distribution network, which can be obtained through the geographical coordinates of the nodes or the pre-recorded line length information. The connection relationship between each node and its neighboring nodes is recorded to form a set of node neighboring connection relationships, which describes the physical and electrical connection relationships between each node and its neighboring nodes in the network.

[0065] After constructing the set of node neighboring connection relationships, topological abstraction is performed on the connection edges between nodes, that is, the nodes and connections in the physical power grid are represented through a graph theory model to more intuitively represent the network structure. Specifically, connection edge identification is carried out on the connection direction and distance between each node, such as directed edges and connection edge lengths. For the convenience of identification, an entity node topological adjacency matrix of each node is constructed. The adjacency matrix is a matrix that describes the connection relationships between nodes in a graph, and each element in it indicates the connection relationship between a node and the rest of the nodes.

[0066] Exemplarily, for a network with n nodes, the adjacency matrix A is an n×n matrix, and each element A[i][j] represents the connection situation between node i and node j, specifically including: if there is a connection between node i and node j, then A[i][j]≠0, and the value can represent the attribute of the connection edge, such as the length of the connection; if there is no connection between node i and node j, then A[i][j]=0; if the connection is directional, the values of A[i][j] and A[j][i] can be different, representing the power flow direction.

[0067] Topological identification connection refers to identifying and abstracting the nodes and their connection relationships in the distribution network, mapping the actual physical connection relationships into the topological model so that it can be used for mathematical analysis and simulation calculations. Specifically, by combining the entity node topological adjacency matrix and the entity node attribute set, each node in the distribution network is identified, and a complete network topology is constructed according to the connection relationships between the nodes. Combining node attributes, adjacency matrices, and connection edge attributes, a distributed photovoltaic distribution network topological model is finally constructed. This model reflects how electricity flows in the network and can be used for analysis and optimization.

[0068] Furthermore, the obtaining of the photovoltaic output-grid load spatio-temporal prediction model includes:

[0069] Using time series analysis to perform time series arrangement and characteristic analysis on the photovoltaic output data set and the grid load data set to obtain a photovoltaic output characteristic data set and a grid load characteristic data set; respectively performing prediction training on the photovoltaic output characteristic data set and the grid load characteristic data set through an LSTM network to obtain a photovoltaic output prediction model and a grid load prediction model; parallelly fusing the photovoltaic output prediction model and the grid load prediction model to generate an initial photovoltaic load spatio-temporal prediction model; using a model optimizer to verify and optimize the initial photovoltaic load spatio-temporal prediction model to obtain the photovoltaic output-grid load spatio-temporal prediction model.

[0070] Both photovoltaic output data and grid load data have obvious time correlations. Time series arrangement is to organize the data in chronological order for subsequent time series analysis. Characteristic analysis refers to identifying and extracting the key factors that affect photovoltaic output and grid load and integrating them into the characteristic data set. Photovoltaic output characteristic analysis includes analyzing solar radiation intensity, temperature, time period, etc. For example, solar radiation intensity directly affects the power generation of photovoltaic systems, and high temperatures usually reduce the efficiency of photovoltaic modules; grid load characteristic analysis includes analyzing time factors, weather factors, and social factors. For example, load demand is closely related to time, such as the load increases during morning and evening peak hours, while it is relatively low at night or in the middle of weekdays. According to the analysis results, a photovoltaic output characteristic data set and a grid load characteristic data set are obtained.

[0071] The LSTM (Long Short-Term Memory) network is a special type of recurrent neural network suitable for processing and predicting time series data. The structure of the LSTM can capture long-term dependencies in the data, making it particularly suitable for analyzing time-dependent sequence data such as photovoltaic power output and grid load. Specifically, the LSTM network is used to train the photovoltaic power output characteristic dataset with the aim of predicting future photovoltaic power generation through historical data and its influencing factors (such as sunshine, temperature, etc.), and obtaining a photovoltaic power output prediction model. Similarly, the LSTM network is used to train the grid load characteristic dataset to predict future grid load based on historical electricity consumption data and its related features (such as time, weather, etc.), and obtain a grid load prediction model.

[0072] Parallel fusion is to integrate the output results of the two prediction models so that the predictions of photovoltaic power output and grid load can be processed simultaneously. Specifically, the photovoltaic power output prediction and the grid load prediction are fused according to the time step. Assuming that the power generation and load demand within the next 24 hours are predicted, the prediction result of the photovoltaic power output for each hour will correspond to the prediction result of the grid load for the same hour. Through parallel fusion, an initial spatio-temporal prediction model of photovoltaic load is obtained. This model is a comprehensive model that can predict photovoltaic power generation and grid load demand simultaneously in both the time and space dimensions.

[0073] The model optimizer is an algorithm used to adjust model parameters, such as the Adam optimizer, RMSprop, etc. The optimizer can automatically adjust the weight and bias parameters during the training process, enabling the model to converge to a better solution. The selected optimizer automatically adjusts the weight parameters of the model through the gradient descent method to minimize the loss function. After each round of iteration, the model parameters are adjusted through the feedback error until the validation error reaches the optimal value. After verification and optimization, the finally obtained spatio-temporal prediction model of photovoltaic power output-grid load can more accurately predict the photovoltaic power generation and grid load demand at different time periods and different spatial nodes in the future.

[0074] Furthermore, the iterative acquisition of the distributed photovoltaic optimized distribution network topology model includes:

[0075] Extract line loss evaluation indicators for the line loss optimization target to obtain a set of line loss evaluation indicators, and construct a fitness function for the line loss optimization effect according to the set of line loss evaluation indicators; determine the parameter particle position and parameter particle velocity according to the particle swarm parameters, and use the fitness function of the line loss optimization effect to evaluate the fitness of the particle swarm parameters to obtain a set of particle swarm fitness; iteratively update the parameter particle position and parameter particle velocity based on the set of particle swarm fitness until a preset termination condition is met, and optimize to determine the optimal parameter particle with the maximum fitness. The optimal parameter particle includes the optimized position of photovoltaic access; optimize and update the distributed photovoltaic distribution network topology model based on the optimized position of photovoltaic access to obtain the optimized distributed photovoltaic distribution network topology model.

[0076] The line loss optimization target is to reduce the power loss in the distribution network by adjusting the photovoltaic access point, load distribution, power flow control, etc. The line loss in the distribution network is mainly determined by factors such as current loss during transmission and power transmission distance. Line loss evaluation indicators are key parameters used to evaluate the line loss of the power system, including indicators such as line current, line impedance, power transmission distance, load demand, and photovoltaic access position, which form a set of line loss evaluation indicators.

[0077] Construct a fitness function for the line loss optimization effect according to the set of line loss evaluation indicators. The fitness function is a function used to evaluate the quality of each particle in the particle swarm optimization. Here, the fitness function is used to evaluate the effect of the given photovoltaic access position on line loss optimization, and the goal is to minimize the total line loss in the distribution network.

[0078] In the particle swarm optimization algorithm, each solution is called a particle. The particle swarm moves in the search space and gradually approaches the optimal solution through interaction with other particles. Here, each particle represents a candidate solution for the photovoltaic access position. The optimization goal is to minimize the line loss of the power grid. Each particle has two main parameters, namely the parameter particle position and the parameter particle velocity. The parameter particle position corresponds to the position of the photovoltaic access point, and the parameter particle velocity represents its moving direction and step size in the solution space, which determines how the particle updates its position in each iteration. Initially, the particle positions can be randomly distributed at different nodes of the distribution network. Each particle corresponds to a photovoltaic access scheme, and the initial velocity of the particle can be randomly set, which determines the initial moving step size of the particle in the solution space. For each particle, calculate its corresponding line loss value using the constructed fitness function of the line loss optimization effect. The larger the fitness value, the better the solution is in reducing the line loss. Obtain a set of particle swarm fitness according to the output of the fitness function.

[0079] The core of the particle swarm optimization algorithm is to gradually optimize the solution by continuously updating the positions and velocities of particles. The velocity and position of each particle are updated according to its own historical best position and the global optimal position in each iteration. The velocity update formula is as follows: , where is the velocity of particle i at time , is the inertia weight, which determines the influence of the particle's previous velocity; , are acceleration factors, representing the weights of individual cognition and swarm cognition respectively; , are random numbers; is the historical best position found by particle i itself; is the global optimal position; is the velocity of particle i at time , is the position of particle i at time . The position update formula is as follows: , where is the position of particle i at time , that is, the position of the particle is updated according to its velocity in each iteration.

[0080] Based on the above velocity update formula and position update formula, in each iteration, after updating the new position of each particle, the line loss optimization effect of the new position is evaluated through the fitness function to obtain a new fitness value. Each particle updates its individual optimal solution. If the position in the current iteration is better than the particle's historical position, it is replaced with the new position. At the same time, the particle with the best fitness among all particles is updated as the global optimal solution, which is the current best solution in the entire particle swarm. The particle swarm optimization algorithm repeatedly updates the positions and velocities of particles and searches for the optimal solution according to the fitness function. The optimal solution is updated according to the position in the new solution space in each iteration, and continuous iteration is carried out until a certain preset termination condition is met. For example, when the number of iterations reaches the upper limit or the change in fitness is not obvious, the global optimal particle in the particle swarm is the final optimization result, representing the optimal position for photovoltaic access.

[0081] In the distributed photovoltaic distribution network topology model, the photovoltaic power generation system is connected to the node at the optimal position for photovoltaic access to obtain a distributed photovoltaic optimized distribution network topology model. This model not only reduces the line loss but also improves the overall performance of the power grid.

[0082] Furthermore, the determination of the distribution network line loss control strategy parameters includes:

[0083] Based on the distributed photovoltaic optimized distribution network topology model, an analysis of the impact on the power flow distribution of the power grid is carried out to obtain the parameters affecting the power flow distribution of the power grid. The parameters affecting the power flow distribution of the power grid include the line load impact parameter and the power grid line loss impact parameter; a line loss control strategy library is constructed. Based on the spatio-temporal distribution characteristic information of the photovoltaic load and the parameters affecting the power flow distribution of the power grid, a matching analysis is carried out with the line loss control strategy library to obtain the matching control strategy for the distribution network line loss; based on the matching control strategy for the distribution network line loss, a threshold division is performed on the spatio-temporal distribution characteristic information of the photovoltaic load and the parameters affecting the power flow distribution of the power grid to obtain the threshold for selecting the line loss control strategy parameters; the line loss optimization effect fitness function is used to perform global optimization within the threshold for selecting the line loss control strategy parameters to determine the line loss control strategy parameters for the distribution network.

[0084] The analysis of the impact on the power flow distribution of the power grid is to evaluate the operating state of the power grid by calculating the flow of electric power between various nodes in the distribution network. The results of the power flow analysis are mainly used to evaluate the operating states of different lines and nodes in the power grid. The key impact parameters include the line load impact parameter and the power grid line loss impact parameter.

[0085] Specifically, the line load impact parameter includes the line load rate and the line flow distribution. Among them, the line load rate refers to the ratio of the actual load of the power line to its rated load. The higher the load rate, the greater the load pressure on the line, which may lead to overload or increased losses. By reasonably connecting photovoltaic power generation, the load on some high-load lines can be effectively reduced; the line flow distribution represents the flow of electric power carried on each line, including the direction and magnitude of the power flow. Reasonable photovoltaic access can guide the power to flow to the load through a shorter path, reducing unnecessary long-distance transmission.

[0086] The power grid line loss impact parameter mainly includes the total line loss. The line loss in the power grid is mainly determined by the line impedance and the magnitude of the current. After optimizing the power flow distribution, it is necessary to calculate the total line loss of the power grid after connecting photovoltaic power generation to measure the change in line loss brought about by the power flow adjustment, which is mainly determined by the current, line impedance, and line length of each line.

[0087] A line loss control strategy library is formulated based on different power flow distributions, photovoltaic power generation outputs, and load demand situations, including photovoltaic power generation scheduling strategies, load transfer strategies, and voltage regulation strategies. For example, during peak load periods, photovoltaic power generation preferentially supplies power to high-load areas, reducing the need for long-distance power transmission, thereby reducing line losses; through load transfer (such as demand response), part of the load on high-load lines is transferred to low-load lines to relieve the line pressure and reduce line losses.

[0088] According to the influencing parameters of the power grid power flow distribution and the spatio-temporal distribution characteristics information of the photovoltaic load, match in the online loss control strategy library to find the most suitable strategy. Specifically, compare the power flow distribution influencing parameters with the strategy parameters in the online loss control strategy library to find the control strategy that conforms to the current power flow state. For example, if the load rate of some lines is too high, select the load transfer strategy; if the voltage deviation of some nodes is too large, select the voltage regulation strategy. According to the spatio-temporal distribution characteristics of photovoltaic power generation and load, judge which strategy can most effectively reduce the line loss. For example, during a high-load period, preferentially select the power generation scheduling strategy to supply photovoltaic power to local loads and reduce long-distance transmission; during a low-load period, adopt the voltage regulation or power flow optimization strategy to avoid too high grid voltage.

[0089] If there are multiple strategies that can match the current power flow distribution and photovoltaic load characteristics, sort the strategies according to the line loss reduction effect, and preferentially select the strategy with the best effect. Finally, obtain the distribution network line loss matching control strategy suitable for the current power grid state.

[0090] By analyzing the spatio-temporal changes of photovoltaic power generation and load demand, determine the range of strategy parameters suitable for each time period or load point. For example, the photovoltaic power generation is usually higher during the day, so the parameter range of power generation scheduling can be set as high as 70%-90% during the day; by analyzing the power grid power flow and line load conditions, determine the parameter range of the load rate and voltage fluctuation of each line. If the load rate of a certain line is high, the threshold of the load transfer strategy is set within a lower load rate range. According to key factors such as photovoltaic power generation, load demand, and power flow distribution, divide the parameter value interval of each control strategy. The result of the division is the upper and lower limits of each parameter, and obtain the threshold for selecting the line loss control strategy parameters, that is, the parameter range allowed for each control strategy.

[0091] Perform global optimization within the threshold for selecting the line loss control strategy parameters. The purpose is to find the optimal solution within the allowed range of these parameters. Evaluate the effects of different strategy parameter combinations through the fitness function. Each group of parameter combinations calculates its impact on the power grid line loss through the fitness function. The goal is to minimize the line loss. Through global optimization, find a group of parameter combinations to maximize the fitness value as the distribution network line loss control strategy parameters.

[0092] Furthermore, determining the distribution network line loss control strategy parameters includes:

[0093] Randomly select multiple policy parameters within the threshold for selecting line loss control policy parameters, and use the fitness function of the line loss optimization effect to evaluate the multiple policy parameters to obtain multiple parameter fitness values; based on the multiple parameter fitness values, approximate the search area of the threshold for selecting line loss control policy parameters to determine the local search area of the policy parameters; according to the local search area of the policy parameters, set the parameter search step size; search and evaluate the policy parameters within the local search area of the policy parameters according to the parameter search step size, and perform iterative approximation of the search area according to the parameter search and evaluation results until the preset number of iterations, and determine the line loss control policy parameters of the distribution network through fitness comparison.

[0094] Within the threshold for selecting line loss control policy parameters, generate multiple policy parameters by random sampling. For each randomly selected policy parameter, use the fitness function of the line loss optimization effect to evaluate it to measure the optimization effect of each set of policy parameters on the line loss of the distribution network. The calculation result is the fitness value of each policy parameter. The larger the fitness value, the better the line loss optimization effect of the combination.

[0095] Sort the multiple parameter fitness values of all policy parameters according to their quality, find the policy parameters with larger fitness values, that is, better optimization effects. By analyzing the distribution of fitness values, narrow the value range of the policy parameters and gradually approach the local area where the optimal solution is located to determine the local search area of the policy parameters. In this way, more refined searches can be concentrated in the better area.

[0096] The search step size refers to the amplitude of adjusting the parameters during each search in the optimization process. The step size determines the search accuracy in the optimization process. The smaller the step size, the more refined the search, but the computational complexity will also increase; the larger the step size, the coarser the search, but it may approach the solution faster. According to the local search area of the policy parameters, set the parameter search step size. That is, when the local search area is small, a smaller step size needs to be set to accurately search for the optimal solution; when the area is large, a slightly larger step size can be used for preliminary search and the step size can be gradually reduced.

[0097] Within the local search area of the policy parameters, generate multiple policy parameters again according to the search step size, use the line loss optimization fitness function to evaluate each policy parameter, calculate its line loss optimization effect, obtain the corresponding fitness value, compare the fitness values of all parameters, find the parameter with a larger fitness value, and obtain the interval where the parameter is located. Take this interval as the new local search area, and further reduce the search step size. Perform the second round of search in the new smaller interval. In each iteration, gradually reduce the search step size and gradually approach the optimal solution. Repeat this process until the preset number of iterations is reached, and finally determine the optimal line loss control policy parameters of the distribution network.

[0098] Furthermore, the feedback optimization of the power distribution network line loss control strategy parameters based on the power distribution network loss reduction simulation effect includes:

[0099] Analyze the optimization direction of the power distribution network line loss control strategy parameters based on the power distribution network loss reduction simulation effect to obtain the parameter mutation optimization rule; Mutate and expand the power distribution network line loss control strategy parameters according to the parameter mutation optimization rule to obtain the line loss control strategy parameter cluster; Compare and optimize the parameters within the line loss control strategy parameter cluster to obtain the line loss control optimization strategy parameters, and perform power distribution network line loss optimization control through the line loss control optimization strategy parameters.

[0100] The power distribution network loss reduction simulation simulates the operation state of the power distribution network under different line loss control strategy parameters through simulation software to evaluate the optimization effect of the strategy on line loss, including line loss changes, line load rates, voltage deviations, etc. under different loads and power generation conditions. By analyzing the simulation results, it can be determined whether the current line loss control strategy has achieved the expected loss reduction effect and identify areas where there is still room for optimization.

[0101] Based on the simulation results, determine the specific impact of each control strategy parameter on line loss optimization, and analyze how to adjust the parameters to further reduce line loss. For example, if the simulation results show that during certain load peaks, the load transfer strategy fails to effectively relieve the load pressure on the line, it can be inferred that the load transfer parameters need to be further adjusted; If the scheduling strategy for photovoltaic power generation fails to effectively reduce the demand for long-distance power transmission, it can be analyzed whether it is necessary to adjust the priority power supply area or scheduling time of photovoltaic power generation. According to the results of the optimization direction analysis, formulate the parameter mutation optimization rule, which defines how the parameters change during the optimization process to further reduce line loss.

[0102] Mutation expansion refers to making a certain range of changes to the current control strategy parameters based on the optimization rule to generate a new set of parameter combinations. Specifically, use the obtained parameter mutation optimization rule to mutate each control strategy parameter. For example, if the mutation rule for the photovoltaic power generation scheduling parameter is ±5%, then several different scheduling parameters are generated on the original basis, such as +5% and -5%. The mutated parameters form a new parameter cluster, that is, the line loss control strategy parameter cluster, covering multiple possible configuration schemes.

[0103] Comparison and optimization refers to finding the optimal strategy parameters for line loss by evaluating the performance of multiple parameters in a parameter cluster. Specifically, the impact of each set of parameters on line loss under different working conditions is obtained through simulation, the optimization effect of each set of parameters is measured by a fitness function to obtain the fitness value of each set of parameters, and the fitness values of all parameters are compared to find the combination with the largest fitness value, which is the optimized strategy parameters for line loss control. The obtained optimized strategy parameters for line loss control are used in actual distribution network control operations to achieve the optimal line loss control effect.

[0104] In summary, the line loss optimization method based on distributed photovoltaic topology analysis provided by the embodiments of the present application has the following technical effects:

[0105] A distributed photovoltaic distribution network topology model is established. This model effectively integrates the basic distribution data of the distribution network and the photovoltaic access data to form a clear network structure. Using the method of graph theory topology connection, it accurately reflects the connection relationship between each node in the power grid, enabling visual analysis of the impact of photovoltaic access on the power grid flow; data mining and time series analysis techniques are used to construct a photovoltaic output-grid load spatio-temporal prediction model. This model synthesizes the spatio-temporal characteristics of photovoltaic power generation and the dynamic changes in power grid load demand, realizing the matching prediction of photovoltaic power generation and power grid load demand; the particle swarm algorithm is used to optimize the photovoltaic access location, iteratively adjusting the optimal location of the photovoltaic access point based on the line loss optimization goal, and forming an optimized distributed photovoltaic optimized distribution network topology model. This process combines the power grid topology structure and the prediction model, enabling the photovoltaic access point to minimize the line loss in the power grid operation, reduce the loss in the power transmission process, and realize the rational allocation of power grid resources and the maximization of power efficiency; through the comprehensive analysis of the spatio-temporal distribution characteristics of photovoltaic load, combined with the distributed photovoltaic optimized distribution network topology model, effective distribution network line loss control strategy parameters are formulated, which can respond to the dynamic changes of photovoltaic output and power grid load in real time. By reasonably dispatching photovoltaic power generation and adjusting the power flow path, the line loss can be further reduced; simulation evaluation and feedback optimization are carried out. The formulated line loss control strategy is verified through simulation, and parameter optimization feedback is carried out according to the simulation results. This process ensures the effectiveness and pertinence of the line loss control strategy, enabling the strategy to be continuously adjusted and improved according to the actual situation, realizing closed-loop optimization, and ensuring the minimum line loss during power grid operation.

[0106] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A line loss optimization system based on distributed photovoltaic topology analysis, characterized in that: The system comprises: A topological connection module, which is used to collect and obtain basic distribution data of the distribution network and photovoltaic access data, and define graph connection attributes, and topologically connect the basic distribution data of the distribution network and the photovoltaic access data based on the graph connection attributes to establish a distributed photovoltaic distribution network topology model; A prediction modeling module, wherein the prediction modeling module is used to obtain a photovoltaic output data set and a power grid load data set by associating them through data mining technology, and to perform prediction modeling on the photovoltaic output data set and the power grid load data set using time series analysis to obtain a photovoltaic output-power grid load spatiotemporal prediction model; An access location optimization module, the access location optimization module is used to initialize particle swarm parameters based on the distributed photovoltaic distribution network topology model, optimize the photovoltaic access location of the particle swarm parameters according to the line loss optimization target, and iteratively obtain the distributed photovoltaic optimized distribution network topology model; A strategy analysis module, the strategy analysis module is used to obtain the spatiotemporal distribution characteristic information of photovoltaic load according to the spatiotemporal prediction model of photovoltaic output-grid load, perform strategy analysis based on the spatiotemporal distribution characteristic information of photovoltaic load and the distributed photovoltaic optimization distribution network topology model, and determine the distribution network line loss control strategy parameters; A feedback optimization module, the feedback optimization module is used to simulate and evaluate the distribution network line loss control strategy parameters, obtain the distribution network loss reduction simulation effect, and feedback optimize the distribution network line loss control strategy parameters based on the distribution network loss reduction simulation effect.

2. The line loss optimization system based on distributed photovoltaic topology analysis according to claim 1, characterized in that: The establishment of a distributed photovoltaic distribution network topology model includes: Determine entity node attributes and node connection edge attributes according to the graph connection attributes; Based on the entity node attributes, entity recognition and attribute identification are performed on the basic distribution data of the distribution network and the photovoltaic access data to obtain a distribution network entity set and an entity node attribute set; Performing connection relationship analysis on the distribution network entity set through the distribution network basic distribution data and photovoltaic access data to construct a node proximity connection relationship set; Performing topological abstraction on the node neighbor connection relationship set based on the node connection edge attributes to obtain a physical node topological adjacency matrix; The distribution network entity set is connected by topological identification based on the entity node topological adjacency matrix and the entity node attribute set to establish the distributed photovoltaic distribution network topology model.

3. The line loss optimization system based on distributed photovoltaic topology analysis according to claim 1, characterized in that: The step of obtaining a photovoltaic output-grid load spatiotemporal prediction model includes: Using time series analysis to perform time series arrangement and characteristic analysis on the photovoltaic output data set and the power grid load data set to obtain a photovoltaic output characteristic data set and a power grid load characteristic data set; The photovoltaic output characteristic data set and the power grid load characteristic data set are respectively trained for prediction by using an LSTM network to obtain a photovoltaic output prediction model and a power grid load prediction model; The photovoltaic output prediction model and the power grid load prediction model are connected in parallel to generate an initial photovoltaic load spatiotemporal prediction model; The initial photovoltaic load spatiotemporal prediction model is verified and optimized using a model optimizer to obtain the photovoltaic output-grid load spatiotemporal prediction model.

4. The line loss optimization system based on distributed photovoltaic topology analysis according to claim 1, characterized in that: The iterative method for obtaining a distributed photovoltaic optimized distribution network topology model includes: Extracting line loss evaluation indicators for the line loss optimization target to obtain a line loss evaluation indicator set, and constructing a line loss optimization effect fitness function based on the line loss evaluation indicator set; According to the particle swarm parameters, the parameter particle position and the parameter particle speed are determined, and the fitness of the particle swarm parameters is evaluated using the line loss optimization effect fitness function to obtain a particle swarm fitness set; Iteratively updating the parameter particle position and parameter particle speed based on the particle swarm fitness set until a preset termination condition is met, and optimizing and determining the optimal parameter particle with the maximum fitness, wherein the optimal parameter particle includes the photovoltaic access optimization position; The distributed photovoltaic distribution network topology model is optimized and updated based on the photovoltaic access optimization position to obtain the distributed photovoltaic optimization distribution network topology model.

5. The line loss optimization system based on distributed photovoltaic topology analysis according to claim 4, characterized in that: Determining the distribution network line loss control strategy parameters includes: Based on the distributed photovoltaic optimized distribution network topology model, a power grid power flow distribution impact analysis is performed to obtain power grid power flow distribution impact parameters, wherein the power grid power flow distribution impact parameters include line load impact parameters and power grid line loss impact parameters; Constructing a line loss control strategy library, and performing matching analysis with the line loss control strategy library based on the spatiotemporal distribution characteristic information of the photovoltaic load and the influencing parameters of the power grid flow distribution, to obtain a distribution network line loss matching control strategy; Based on the distribution network line loss matching control strategy, the photovoltaic load spatiotemporal distribution characteristic information and the power grid power flow distribution influencing parameters are divided into thresholds to obtain a line loss control strategy parameter selection threshold; The line loss optimization effect fitness function is used to perform global optimization within the line loss control strategy parameter selection threshold to determine the distribution network line loss control strategy parameters.

6. The line loss optimization system based on distributed photovoltaic topology analysis according to claim 5, characterized in that: The determining of the distribution network line loss control strategy parameters comprises: Randomly selecting multiple strategy parameters within the line loss control strategy parameter selection threshold, and evaluating the multiple strategy parameters using the line loss optimization effect fitness function to obtain multiple parameter fitness; Based on the multiple parameter fitnesses, the thresholds for selecting the line loss control strategy parameters are approximated in an optimization region to determine a local optimization region for the strategy parameters; According to the local optimization area of ​​the strategy parameters, setting the parameter search step size; A strategy parameter search and evaluation is performed in the local optimization area of ​​the strategy parameters according to the parameter search step, and an optimization area iterative approximation is performed according to the parameter search and evaluation result until a preset number of iterations is reached, and the distribution network line loss control strategy parameters are determined by fitness comparison.

7. The line loss optimization system based on distributed photovoltaic topology analysis according to claim 1, characterized in that: The performing feedback optimization on the distribution network line loss control strategy parameters based on the distribution network loss reduction simulation effect includes: Based on the distribution network loss reduction simulation effect, the distribution network line loss control strategy parameters are optimized and analyzed to obtain parameter variation optimization rules; According to the parameter variation optimization rule, the distribution network line loss control strategy parameters are mutated and expanded to obtain a line loss control strategy parameter cluster; Parameter comparison and optimization are performed within the line loss control strategy parameter cluster to obtain line loss control optimization strategy parameters, and distribution network line loss optimization control is performed using the line loss control optimization strategy parameters.

8. A line loss optimization method based on distributed photovoltaic topology analysis, characterized in that: Based on the implementation of the line loss optimization system based on distributed photovoltaic topology analysis according to any one of claims 1 to 7, the method comprises: Collect and obtain basic distribution data of the distribution network and photovoltaic access data, and define graph connection attributes, and topologically connect the basic distribution data of the distribution network and photovoltaic access data based on the graph connection attributes to establish a distributed photovoltaic distribution network topology model; The photovoltaic output data set and the grid load data set are obtained by associating them through data mining technology, and the photovoltaic output data set and the grid load data set are predicted and modeled using time series analysis to obtain a photovoltaic output-grid load spatiotemporal prediction model; Initialize particle swarm parameters based on the distributed photovoltaic distribution network topology model, optimize photovoltaic access positions for the particle swarm parameters according to the line loss optimization target, and iteratively obtain the distributed photovoltaic optimized distribution network topology model; According to the photovoltaic output-grid load spatiotemporal prediction model, the spatiotemporal distribution characteristic information of photovoltaic load is obtained, and based on the spatiotemporal distribution characteristic information of photovoltaic load and the distributed photovoltaic optimization distribution network topology model, a strategy analysis is performed to determine the distribution network line loss control strategy parameters; The distribution network line loss control strategy parameters are simulated and evaluated to obtain a distribution network loss reduction simulation effect, and the distribution network line loss control strategy parameters are feedback optimized based on the distribution network loss reduction simulation effect.

Images