Control method, device and equipment of power distribution network and storage medium

Abstract

The embodiment of the invention provides a control method and device of a power distribution network, equipment and a storage medium. The method comprises the following steps: acquiring acquisition data and simulation data of a power distribution network; wherein the acquired data represents operation data of the power distribution network acquired based on acquisition equipment; the simulation data represents data for simulating the running state of the power distribution network through simulation software; determining target features according to the acquisition data and the simulation data; wherein the target characteristic represents the operation state of the power distribution network; predicting operation parameters of the power distribution network according to the target characteristics; determining a target configuration scheme of the reactive power compensation device of the power distribution network according to the operation parameters; and according to the target configuration scheme, controlling a fling-cut switch of the reactive power compensation device so as to control the normal operation of the power distribution network. The method can achieve the effect of timely coping with the dynamic change of the power distribution network.

Description

Technical Field

[0001] The present application relates to the technical field of distribution network technology, and in particular to a control method, device, equipment and storage medium for a distribution network. Background Art

[0002] The distribution network platform can monitor and analyze grid operation data in real time, achieve comprehensive perception of the grid status, and ensure safe and stable operation of the grid.

[0003] Most existing distribution network platforms are equipped with digital twin models that include topology structure, flow calculation and state estimation. Based on this digital twin model, the configuration plan of the distribution network can be adjusted to ensure the normal operation of the distribution network.

[0004] However, these digital twin models often rely on offline distribution network operating data for training and updating, making them unable to monitor and respond quickly to the distribution network's status in real time. This results in low efficiency in responding to dynamic changes in the grid. Therefore, a distribution network control method that can promptly respond to dynamic changes in the grid is urgently needed. Summary of the Invention

[0005] The embodiments of the present application provide a control method, apparatus, device, and storage medium for a power distribution network, so as to achieve the effect of promptly responding to dynamic changes in the power distribution network.

[0006] In a first aspect, an embodiment of the present application provides a method for controlling a power distribution network, comprising:

[0007] Acquire collected data and simulated data of the distribution network; wherein the collected data represents the operating data of the distribution network collected by the collection equipment; and the simulated data represents the data of the operating status of the distribution network simulated by the simulation software;

[0008] Determining target characteristics based on the collected data and the simulation data; wherein the target characteristics represent the operating status of the distribution network;

[0009] predicting operating parameters of the distribution network based on the target characteristics; and determining a target configuration scheme for a reactive power compensation device of the distribution network based on the operating parameters;

[0010] According to the target configuration scheme, the switching of the reactive compensation device is controlled to control the normal operation of the distribution network.

[0011] In one possible implementation, determining a target configuration scheme for a reactive power compensation device of the distribution network according to the operating parameters includes:

[0012] Determine the initial configuration plan based on operating parameters;

[0013] The initial configuration scheme is optimized to obtain the target configuration scheme.

[0014] In a possible implementation, optimizing the initial configuration solution to obtain the target configuration solution includes:

[0015] Generate multiple solutions based on the operating parameters, wherein each solution represents a configuration scheme corresponding to a set of distribution network operating parameters; repeat the following steps until a preset number of iterations is reached, and determine the solution with the highest fitness as the target configuration scheme:

[0016] For each solution, multi-level simulation is performed on the solution to determine the fitness of the solution;

[0017] Based on a preset selection algorithm, the operating parameters of the solution are adjusted to obtain other solutions.

[0018] In a possible implementation, performing multi-level simulation processing on the solution to determine the fitness of the solution includes:

[0019] The solution is simulated at multiple levels to determine network losses, voltage deviations, and load imbalance.

[0020] The adaptability of the solution is determined according to the network loss, voltage deviation and load imbalance.

[0021] In a possible implementation, determining target features based on the collected data and the simulation data includes:

[0022] determining acquisition features based on the acquired data; and determining simulation features based on the simulation data;

[0023] Based on the operating parameters of the distribution network, the collected features and the simulation features are screened to obtain the target features.

[0024] In a possible implementation, predicting the operating parameters of the distribution network according to the target characteristics includes:

[0025] The target characteristics are input into a preset prediction model, and the operating parameters of the distribution network are output.

[0026] In a possible implementation, obtaining simulation data of the distribution network includes:

[0027] Based on the collected data, multi-level simulation processing is performed on the operating status of the distribution network to obtain the simulation data; wherein the multi-level simulation processing includes at least two of the equipment level, feeder level, and network level.

[0028] In a second aspect, an embodiment of the present application provides a control device for a power distribution network, comprising:

[0029] An acquisition module is used to acquire collected data and simulation data of the distribution network; wherein the collected data represents the operating data of the distribution network collected by the collection equipment; and the simulation data represents the data of the distribution network operating status simulated by the simulation software;

[0030] A determination module, configured to determine a target feature based on the collected data and the simulation data; wherein the target feature represents an operating state of the distribution network;

[0031] a prediction module, configured to predict operating parameters of the distribution network based on the target characteristics; and determine a target configuration scheme for a reactive power compensation device of the distribution network based on the operating parameters;

[0032] A control module is used to control the switching of the reactive compensation device according to the target configuration scheme to control the normal operation of the distribution network.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor;

[0034] The memory stores computer-executable instructions;

[0035] The processor executes the computer-executable instructions stored in the memory, so that the processor executes the above first aspect and / or various possible implementations of the first aspect.

[0036] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the first aspect above and / or various possible implementation methods of the first aspect.

[0037] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the above first aspect and / or various possible implementation methods of the first aspect.

[0038] The control method, device, equipment and storage medium of the distribution network provided in the embodiments of the present application obtain the collected data and simulation data of the distribution network, and extract target features that are highly correlated with the operating status of the distribution network from the collected data and simulation data, and then predict the operating parameters of the distribution network based on the target features, and determine the target configuration scheme of the reactive compensation device according to the operating parameters, and then control the switching of the reactive compensation device based on the target configuration scheme to control the normal operation of the distribution network. Compared with the prior art that relies on the digital twin model to adjust the configuration scheme of the distribution network, through this method, the distribution network platform can adjust the operating parameters of the distribution network in real time based on the collected data that characterizes the current operating conditions, combined with simulation data that can simulate the behavior of the distribution network from multiple dimensions such as electrical, thermal, and mechanical, with higher real-time performance to adapt to the dynamic changes of the distribution network, and can combine multi-dimensional simulation data to improve the accuracy and reliability of the operating parameters, thereby improving the accuracy of the configuration scheme and ensuring the safe and stable operation of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] Figure 1 A schematic diagram of a control method for a power distribution network provided in this application Figure 1 ;

[0041] Figure 2 A schematic diagram of a control method for a power distribution network provided in this application Figure 2 ;

[0042] Figure 3 A schematic diagram of the structure of a distribution network platform provided for this application;

[0043] Figure 4 A schematic diagram of the structure of the control device for the distribution network provided in this application;

[0044] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application.

[0045] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0046] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0047] First, let’s explain the terms involved in this application:

[0048] Distribution network: It is an electric power network that receives electric energy from the transmission network or regional power plants and distributes it to users step by step according to voltage levels through distribution facilities (such as transformers, lines, etc.).

[0049] Most existing digital twin models rely on offline distribution network operation data for training and updating, and are unable to achieve real-time monitoring and rapid response to the status of the distribution network, resulting in low efficiency when responding to dynamic changes in the power grid. Therefore, an embodiment of the present application provides a control method for a distribution network, which determines the operating parameters of the distribution network in real time based on the real-time data of the power grid and multi-dimensional simulation data, and then obtains a configuration scheme based on the operating parameters, and adjusts the reactive compensation device of the distribution network in real time to cope with the dynamic changes of the distribution network and ensure the safe and stable operation of the distribution network. In this way, when the distribution network changes dynamically, the distribution point network platform can adjust the operating parameters in real time and determine the configuration scheme to cope with the real-time dynamic changes of the distribution network and ensure the safe and stable operation of the distribution network. The executor of the embodiment of the present application may be a distribution network platform.

[0050] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0051] Figure 1 A schematic diagram of a control method for a power distribution network provided in this application Figure 1 ,like Figure 1 As shown, the method includes:

[0052] S101. Acquire collected data and simulation data of the distribution network.

[0053] Exemplarily, the collected data represents the operating data of the distribution network collected by the collection equipment, such as voltage, current, temperature, switch status, etc. It is understandable that each key node of the distribution network can be deployed with collection equipment such as sensors and telemetry devices to continuously and frequently collect data. The collection equipment may, for example, be: a voltage transformer for measuring node voltage, a current transformer for capturing line current, a temperature sensor for monitoring the operating temperature of equipment (such as transformers and cable connectors), and a switch status monitor for recording the open and closed status of switches such as circuit breakers and switches.

[0054] The simulation data represents the data that simulates the operating status of the distribution network through simulation software. The simulation data may include, for example, device-level simulation data (voltage, current, loss, temperature distribution, stress, deformation of transformers, circuit breakers, and cables), feeder-level simulation data (voltage, current, loss, temperature distribution, structural strength of feeders), and network-level simulation data (whole-network current, thermal impact, mechanical stress distribution, etc.). For example, the distribution network platform can build a simulation model based on the actual topological structure of the distribution network based on the preset distribution network simulation software, wherein the simulation model can accurately replicate the actual power grid architecture, including the electrical parameters (such as impedance, capacity, transformation ratio, etc.) of each component such as substations, feeders, transformers, distributed energy, and the connection relationship between them; and then, based on the simulation model, the operating status of the distribution network under the working conditions represented by the current collected data can be simulated, and simulation data such as device-level voltage and current waveforms, loss changes, feeder-level current distribution, temperature distribution, and network-level system stability indicators (such as voltage stability margin, frequency deviation, etc.) can be collected.

[0055] S102: Determine target features based on collected data and simulation data.

[0056] The target feature characterizes the operating status of the distribution network and is highly correlated with its operating status. For example, it can be a feature related to parameters such as reactive power and grid stability. It is understood that the collected data and simulation data include a large number of parameter types, such as voltage, current, temperature, and switch status. It is necessary to identify parameters or features that are highly correlated with the operating status of the distribution network from these parameters and use them as target features. In other words, this target feature can be used to reflect the operating status of the distribution network.

[0057] In one example, the distribution network platform can extract peak values, mean values, frequency components and other features from the collected data as collection features, for example, calculating the peak value and mean value of the voltage within a certain time period. Various simulation data obtained from the simulation analysis can also be converted into simulation features, such as converting the temperature distribution of the equipment into features such as average temperature, maximum temperature, temperature gradient, etc.; converting the structural strength analysis results of the feeder into strength index features. Furthermore, based on correlation analysis or principal component analysis, features that are highly correlated with the operating status of the distribution network can be determined from the collection features and simulation features as target features. It should be noted that the principle of feature extraction is similar, and the embodiments of this application will not be given examples one by one here.

[0058] For example, the correlation coefficient between each feature and reactive power can be calculated, and the features with correlation coefficients greater than a certain threshold are used as target features.

[0059] S103. Predicting operating parameters of the distribution network based on the target characteristics; and determining a target configuration scheme for reactive power compensation devices of the distribution network based on the operating parameters.

[0060] The operating parameters of the distribution network are used to describe the physical quantities of the operating status, performance, and power quality during the operation of the distribution network. For example, they may include reactive power, voltage of each node, power factor, load rate, etc. The embodiments of this application are not limited here and can be set according to actual needs.

[0061] Reactive power compensation devices are used to improve the power factor of power grids, reduce line losses, and improve power quality. They can provide or absorb reactive power in the power grid to adjust the reactive balance of the grid. Examples include shunt capacitors, synchronous condensers, static var compensators (SVCs), and static synchronous compensators. It is understood that different operating conditions and load variations can cause grid voltage fluctuations and changes in reactive power distribution. Adjusting the configuration of reactive power compensation devices can flexibly adjust the reactive power compensation amount according to actual conditions, better adapt to voltage fluctuations, improve voltage stability, and reduce line losses.

[0062] The target configuration plan can include the number of reactive compensation devices such as capacitor banks or reactor banks to be switched on and off, the switching time, and the transformer tap position. For example, when low voltage is predicted, a certain number of capacitor banks will be deployed to increase the voltage; when the power factor is low, the switching method of the reactive compensation device will be adjusted to improve the power factor.

[0063] In one example, the distribution network platform can input the target features into a preset prediction model and output the operating parameters of the distribution network. The prediction model can be, for example, a linear regression model, a gradient boosting tree, a neural network model, a support vector machine model, etc., which is not limited in the embodiment of the present application. The prediction model is obtained by training historical target features and historical operating parameters as sample data. Optionally, the adjusted distribution network operating parameters can be recorded, and the new data can be fed back into the prediction model, and the prediction model can be retrained regularly to optimize the prediction accuracy.

[0064] In one example, the distribution network platform can determine the target configuration scheme of the reactive compensation device based on the predicted operating parameters and the current state of the reactive compensation device, combined with the goals of reactive compensation (such as maintaining voltage stability, improving power factor, etc.). In one possible implementation method, the distribution network platform can preset an adjustment algorithm and obtain the target configuration scheme of the reactive compensation device based on the predicted operating parameters and the preset adjustment algorithm. In this way, the relationship between the distribution network operating parameters and the reactive compensation device can be learned, and a mathematical model or rule base between reactive compensation and operating parameters can be established, so that the determination of the configuration scheme is more scientific and reasonable, and the adjustment scheme of the reactive compensation device can be accurately formulated according to the actual operating conditions of the distribution network.

[0065] Another possible implementation involves using optimization algorithms (such as genetic algorithms and particle swarm optimization) to determine the target configuration of reactive power compensation devices. For example, with voltage stability, improved power factor, and reduced line losses as optimization objectives, and taking into account constraints such as the capacity and switching frequency limits of reactive power compensation devices, the algorithm solves the optimal reactive power compensation device switching combination and adjustment amount, achieving optimized reactive power compensation in the distribution network. This approach allows the configuration plan to comprehensively consider multiple factors, achieving multi-objective optimized operation of the distribution network and improving its stability and economic efficiency.

[0066] S104. According to the target configuration plan, control the switching of the reactive power compensation device to control the normal operation of the distribution network.

[0067] For example, the determined target configuration scheme for the reactive power compensation device is converted into specific control instructions and transmitted to the control unit of the reactive power compensation device via a communication network (such as a dedicated power communication network or a wireless communication network). The control instructions may include switch operation information, such as the switch number, operation type (on or off), and operation time. After receiving the control instructions, the control unit of the reactive power compensation device operates the switches according to the instructions. For example, the switching switch of a capacitor may be controlled to switch the capacitor on or off, thereby changing the reactive power compensation capacity.

[0068] Optionally, the distribution network platform can continuously monitor changes in distribution network operating parameters and verify the effectiveness of reactive power compensation device adjustments by collecting data feedback. If the voltage still hasn't returned to normal or the reactive power balance hasn't met expectations, a new target configuration solution is determined according to the above steps, and control commands are issued again, forming a closed-loop control loop until the distribution network stabilizes.

[0069] The control method of the distribution network provided in the embodiment of the present application obtains the collected data and simulation data of the distribution network, and extracts target features that are highly correlated with the operating status of the distribution network from the collected data and simulation data, and then predicts the operating parameters of the distribution network based on the target features, and determines the target configuration scheme of the reactive compensation device according to the operating parameters, and then controls the switching of the reactive compensation device based on the target configuration scheme to control the normal operation of the distribution network. Compared with the prior art that relies on the digital twin model to adjust the configuration scheme of the distribution network, through this method, the distribution network platform can adjust the operating parameters of the distribution network in real time based on the collected data that characterizes the current operating conditions, combined with simulation data that can simulate the behavior of the distribution network from multiple dimensions such as electrical, thermal, and mechanical, with higher real-time performance to adapt to the dynamic changes of the distribution network, and can combine multi-dimensional simulation data to improve the accuracy and reliability of the operating parameters, thereby improving the accuracy of the configuration scheme and ensuring the safe and stable operation of the distribution network.

[0070] Figure 2 A schematic diagram of a control method for a power distribution network provided in this application Figure 2 , Figure 3 A schematic diagram of the structure of a distribution network platform provided in this application, combined with Figure 2 and Figure 3 As shown, this embodiment Figure 1 Based on the embodiment, a control method for a distribution network is described in detail. The method includes:

[0071] S201: Acquire collected data of the distribution network.

[0072] Exemplarily, the data acquisition and integration module can be used to obtain the operating data collected by the acquisition equipment to obtain the collected data of the distribution network.

[0073] S202: Perform multi-level simulation processing on the operating status of the distribution network according to the collected data to obtain simulation data.

[0074] Exemplarily, the multi-level simulation process includes at least two of the device level, feeder level, and network level.

[0075] Among them, device-level simulation is used for:

[0076] (1) Select electrical component models of transformers, circuit breakers, and cables, set actual parameters of rated voltage, impedance, and rated capacity for the models, run simulations under specific operating conditions, and analyze the electrical performance of the equipment in terms of voltage, current, and loss;

[0077] (2) Establish a heat conduction model based on the thermal characteristics of the equipment, set the ambient temperature and heat dissipation conditions, simulate the temperature distribution of the equipment, and evaluate hot spots and thermal stability;

[0078] (3) Considering the mechanical structure of the equipment, a mechanical model is established, and mechanical loads such as wind and gravity are applied under actual working conditions to simulate the stress, deformation, and vibration of the equipment.

[0079] Feeder-level simulation is used to:

[0080] (1) Build a network model based on the actual connection of the feeder, integrate the parameters of the feeder and its connected equipment, perform power flow calculations, and analyze the voltage, current, and loss of the feeder;

[0081] (2) Establish a thermal model for the feeder, taking into account factors such as the conductor cross-sectional area and material, as well as the effects of ambient temperature and wind speed on feeder heat dissipation, simulate the temperature distribution of the feeder, and assess the overheating risk;

[0082] (3) Considering the tension and vibration of the feeder, simulate the strength and stability of the feeder.

[0083] Network-level simulation is used to:

[0084] (1) Build a full-network model of all feeders, substations, and distributed energy resources, perform full-network power flow calculations, analyze system stability, simulate short-circuit and disconnection faults, and analyze system responses;

[0085] (2) Integrate the thermal model of all network devices to analyze the thermal impact of the entire network under different working conditions;

[0086] (3) Considering the mechanical interaction of all network devices, simulate the mechanical stress distribution of the entire network under extreme conditions.

[0087] In one example, a simulation analysis module is used in physics-based simulation software to simulate the behavior of the distribution network under the current operating conditions represented by the collected data to obtain simulation data.

[0088] Optionally, after the data acquisition and integration module obtains the collected data and simulation data, the data processing and cleaning module can perform data cleaning processing on the collected data and simulation data respectively, for example, it may include removing duplicate values, outliers, filling missing values, data verification, etc., which is not limited in the embodiments of the present application. For example, the distribution network platform can preset a data preprocessing algorithm to automatically scan the collected data and identify and remove outliers. For example, if a node voltage suddenly has spike data that far exceeds the normal range, it will be judged as abnormal and eliminated. At the same time, the data quality analysis tool verifies the integrity and accuracy of the collected data, checks whether there is any data missing, and marks it if some temperature data in a certain period is not collected; and verifies the accuracy of the data, such as comparing the current values of the same line collected by different sensors, and verifies and corrects it when the deviation is too large, to ensure that the data entering the subsequent analysis process is reliable.

[0089] S203: Determine acquisition features based on the acquired data; and determine simulation features based on the simulation data.

[0090] For example, the dynamic modeling module is used to extract peak values, mean values, frequency components, and other features from collected data as acquisition features. For example, it can calculate the peak and mean values of voltage within a specific time period. It can also convert various simulation data obtained through simulation analysis into simulation features. For example, it can convert the temperature distribution of equipment into features such as average temperature, maximum temperature, and temperature gradient; and it can convert the results of feeder structural strength analysis into strength index features.

[0091] S204: Based on the operating parameters of the distribution network, the collected features and the simulated features are screened to obtain target features.

[0092] For example, taking the operating parameters of the distribution network including reactive power as an example, the dynamic modeling module is used to summarize the correlation coefficient between each feature and reactive power by calculating the acquisition features and simulation features, and to screen each feature based on the correlation coefficient to obtain the target feature.

[0093] S205: Input the target features into a preset prediction model and output the operating parameters of the distribution network.

[0094] Exemplarily, the dynamic modeling module is used to input target features into a preset gradient boosting tree model and output operating parameters of the distribution network.

[0095] S206: Determine an initial configuration solution based on the operating parameters.

[0096] Exemplarily, an initial configuration scheme can be generated as an initial solution based on the predicted operating parameters. For example, based on the predicted operating parameters, it is determined that three groups of reactive compensation capacitors need to be invested. Any three groups of reactive compensation capacitors can be selected as the initial configuration scheme.

[0097] S207: Optimize the initial configuration plan to obtain a target configuration plan for the reactive power compensation device of the distribution network.

[0098] Exemplarily, the decision support module is used to optimize the initial configuration scheme based on a preset genetic algorithm to obtain a target configuration scheme for the reactive compensation device of the distribution network.

[0099] In some possible implementations, multiple solutions are generated based on the operating parameters; each solution represents a configuration scheme corresponding to a set of distribution network operating parameters. Exemplarily, fine-tuning can be performed based on the initial solution. For example, based on the initial solution of investing in any three groups of reactive compensation capacitors, different solutions including investing in two groups, three groups, and four groups may be obtained. At the same time, multiple solutions can be obtained by combining different transformer tap positions and line switch status combinations.

[0100] Repeat the following steps S301 and S302 until the preset number of iterations is reached, and determine the solution with the highest fitness as the target configuration solution:

[0101] S301: For each solution, perform multi-level simulation processing on the solution to determine the fitness of the solution;

[0102] It is understandable that when performing simulation processing, multiple indicators can be obtained, and then the fitness can be determined based on these indicators.

[0103] Specifically, a multi-level simulation process is performed on the solution to determine the network loss, voltage deviation and load imbalance; and the adaptability of the solution is determined based on the network loss, voltage deviation and load imbalance.

[0104] For example, network loss includes transformer loss and resistance loss. For line resistance loss data, the line resistance parameters (usually predetermined based on line material, length, cross-sectional area, etc. and stored in the system database) and the current value flowing through each line (calculated in real time during the simulation process) can be used to calculate the line resistance loss according to the formula P line =I 2 R, calculate the line loss power P line , I is the line current, R is the line resistance, and then the resistance loss of each line can be calculated, and then the total resistance loss of the entire network line P can be obtained by accumulating linetotal .

[0105] For transformer loss, obtain the transformer's no-load loss P0 (given by the transformer equipment parameters), load loss coefficient K (determined according to the transformer specifications), and load current I load , through the formula P T =P0+I load 2K, calculate the power loss P of each transformer T , and the total transformer loss of the entire network P is obtained by summing up Ttotal Furthermore, the sum of the total transformer loss of the entire network and the total line resistance loss of the entire network is taken as the network loss.

[0106] During the simulation process, the voltage amplitude of each key node of the power grid (such as the end of the feeder, important load access point, etc.) and its change over time are monitored, and the voltage deviation index is calculated, for example, the root mean square error of all key nodes, which is not limited in this embodiment of the present application.

[0107] During the simulation process, the load power of multiple areas can be calculated, and then the standard deviation of the load distribution can be calculated to measure the degree of load imbalance.

[0108] Furthermore, the weight coefficients of the above indicators such as network loss, voltage deviation and load imbalance can be set according to the real-time operation status of the power grid and the optimization target priority to calculate the fitness. For example, the formula Calculate the fitness F, where ω1~ω3 represent weight coefficients, P loss Indicates network loss, V dec represents the voltage deviation, σ load Indicates the degree of load imbalance.

[0109] S302: Based on a preset selection algorithm, adjust the operating parameters of the solution to obtain other solutions.

[0110] It should be noted that the decision support module can set optimization objectives, such as minimizing network losses, improving voltage stability, and achieving load balancing, and use transformer tap positions, reactive compensation device settings, etc. as decision variables.

[0111] For example, based on the calculated fitness, a probability of selection is assigned to each solution based on a preset selection algorithm. For example, the preset selection algorithm is a roulette wheel method, where the sum of the fitness of all solutions serves as the total scale of the "roulette wheel," and the proportion of each solution's fitness to the total scale represents its probability of selection. A solution with a higher fitness value, meaning it performs better in achieving the optimization objectives (minimizing grid losses, improving voltage stability, and achieving load balancing), occupies a relatively larger area on the "roulette wheel," and has a higher probability of being selected for the next generation. Simultaneously, an elite retention strategy is introduced, retaining a certain percentage (e.g., 10%) of the individuals with the highest fitness in each generation. This ensures that solutions demonstrating superior genetic combinations (such as reasonable reactive compensation device parameter configuration, precise transformer tap positions, and effective line switch states) are fully passed on to the next generation. This prevents the loss of optimal genetic fragments due to random factors during the genetic operation, accelerating the optimization process's convergence to the global optimum.

[0112] Among the individuals that survive the selection operation, pairs are randomly paired. For each pair, the intervals of decision variables that need to be exchanged are determined. For example, for reactive power compensation devices, different group exchange intervals are divided based on their layout and functional relevance in the power grid. This ensures that the exchange operation can introduce new configuration ideas without disrupting the overall coordination of reactive power compensation. Then, according to the defined exchange intervals, some decision variables between the paired individuals are exchanged. Taking the configuration of the number of reactive power compensation device switching groups as an example, suppose a pair of individuals A and B has three groups of reactive power compensation capacitors configured in a certain area, and B has four groups. Through the exchange operation, A obtains B's four-group configuration and B obtains A's three-group configuration. Combined with the corresponding transformer tap position and line switch state adjustments, two new solutions are generated, exploring the space of more optimal parameter combinations and discovering potential optimization paths.

[0113] The mutation probability is dynamically set based on the number of iterations and the current population diversity. In the initial optimization phase, when the population diversity is high, a relatively high mutation probability (e.g., 0.1) is set to more broadly explore the solution space. Decision variables such as the number of reactive compensation device switching groups, output capacity, and transformer tap position are boldly and randomly adjusted. As the number of iterations increases and the population converges, when most individuals converge on certain key decision variables, the mutation probability is reduced (e.g., to 0.03), focusing on fine-tuning around high-quality solutions to prevent excessive mutation from destroying existing superior gene combinations. Mutation is then performed on selected individuals (randomly selected based on the mutation probability). For reactive compensation device parameters, minor adjustments may be made to the number of switching groups (e.g., adding or subtracting one group) or to the output capacity (e.g., increasing or decreasing by 5%). Transformer tap positions are randomly shifted by ±1 steps. Line switch states are randomly switched on and off. These mutation operations introduce new genes, break the constraints of local optimal solutions, and maintain the population's evolutionary vitality.

[0114] Repeat the above steps to form an iterative loop. Each iteration is based on the results of the previous iteration, continuously updating the individuals in the population, gradually improving the overall fitness of the population, and taking the solution with the highest fitness as the target configuration solution.

[0115] S208. According to the target configuration plan, control the switching of the reactive power compensation device to control the normal operation of the distribution network.

[0116] Exemplarily, the closed-loop control module is used to convert the determined target configuration scheme of the reactive compensation device into specific control instructions, and send them to the control unit of the reactive compensation device via a communication network (such as a power-specific communication network, a wireless communication network, etc.).

[0117] Optionally, the cyber-physical fusion module is used to continuously calibrate the prediction model through real-time data feedback to ensure the consistency between the virtual grid and the actual grid.

[0118] The control method of the distribution network provided in the embodiment of the present application performs multi-level simulation processing on the collected data of the distribution network acquired in real time to obtain multi-scale and multi-dimensional simulation data, extracts target features from the collected data and the simulation data, predicts the operating parameters of the distribution network in real time based on the target features, determines the corresponding initial configuration scheme based on the operating parameters, optimizes the initial configuration scheme using a genetic algorithm to obtain a target configuration scheme, and, during the optimization process, performs multi-level simulation processing on each configuration scheme, determines the fitness of each configuration scheme as an evaluation index based on the simulation results, and then obtains the optimal target configuration scheme. Finally, based on the target configuration scheme, controls the switching of the reactive compensation device to control the normal operation of the distribution network.

[0119] This approach enables, on the one hand, a highly synchronized virtual and actual distribution networks, providing a solid foundation for intelligent management of the distribution network. This improves management accuracy and efficiency, allows for real-time adjustment and control of the distribution network's status, ensures optimal operation, reduces the probability of failures, and enhances its stability and reliability. Furthermore, multi-scale, comprehensive simulation and analysis tools support distribution network operation optimization, reduce energy loss, and improve efficiency. Simulation and analysis tools also provide detailed data support for distribution network planning and design, enhancing the scientific and rational nature of planning. Real-time monitoring and optimized control reduce the risk of distribution network accidents. Furthermore, closed-loop control enables the distribution network to rapidly respond to emergencies, effectively handle failures, and shorten recovery times.

[0120] Figure 4 The schematic diagram of the control device for the power distribution network provided in this application is as follows: Figure 4 As shown, the control device 400 of the power distribution network provided in this embodiment includes:

[0121] The acquisition module 401 is used to acquire the collected data and simulation data of the distribution network; wherein the collected data represents the operating data of the distribution network collected by the collection equipment; and the simulation data represents the data of the distribution network operating status simulated by the simulation software;

[0122] A determination module 402 is configured to determine a target feature based on the collected data and the simulation data; wherein the target feature represents the operating state of the distribution network;

[0123] A prediction module 403 is configured to predict operating parameters of the distribution network based on the target characteristics; and determine a target configuration scheme for reactive power compensation devices of the distribution network based on the operating parameters;

[0124] The control module 404 is configured to control the switching of the reactive power compensation device according to the target configuration scheme to control the normal operation of the distribution network.

[0125] In a possible implementation, the prediction module 403 is specifically configured to:

[0126] Determine the initial configuration plan based on operating parameters;

[0127] The initial configuration scheme is optimized to obtain the target configuration scheme.

[0128] In a possible implementation, the prediction module 403 is specifically configured to:

[0129] Generate multiple solutions based on the operating parameters, wherein each solution represents a configuration scheme corresponding to a set of distribution network operating parameters; repeat the following steps until a preset number of iterations is reached, and determine the solution with the highest fitness as the target configuration scheme:

[0130] For each solution, multi-level simulation is performed on the solution to determine the fitness of the solution;

[0131] Based on a preset selection algorithm, the operating parameters of the solution are adjusted to obtain other solutions.

[0132] In a possible implementation, the prediction module 403 is specifically configured to:

[0133] The solution is simulated at multiple levels to determine network losses, voltage deviations, and load imbalance.

[0134] The adaptability of the solution is determined according to the network loss, voltage deviation and load imbalance.

[0135] In a possible implementation, the determination module 402 is specifically configured to:

[0136] determining acquisition features based on the acquired data; and determining simulation features based on the simulation data;

[0137] Based on the operating parameters of the distribution network, the collected features and the simulation features are screened to obtain the target features.

[0138] In a possible implementation, the prediction module 403 is specifically configured to:

[0139] The target characteristics are input into a preset prediction model, and the operating parameters of the distribution network are output.

[0140] In a possible implementation, the acquisition module 401 is specifically configured to:

[0141] Based on the collected data, multi-level simulation processing is performed on the operating status of the distribution network to obtain the simulation data; wherein the multi-level simulation processing includes at least two of the equipment level, feeder level, and network level.

[0142] The control device for the distribution network provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0143] Figure 5 This is a schematic diagram of the structure of the electronic device provided in this application. Figure 5 As shown, the electronic device 500 provided in this embodiment includes: at least one processor 501 and a memory 502. Optionally, the electronic device 500 also includes a communication component 503. The processor 501, the memory 502, and the communication component 503 are connected via a bus. The electronic device can be deployed with a power distribution network platform.

[0144] In a specific implementation process, at least one processor 501 executes the computer-executable instructions stored in the memory 502, so that the at least one processor 501 performs the above method.

[0145] The specific implementation process of the processor 501 can be found in the above method embodiment. Its implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0146] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0147] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0148] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0149] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0150] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0151] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0152] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0153] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0154] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0156] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0157] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented using hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0158] Finally, it should be noted that those skilled in the art will readily identify other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A control method for a distribution network, characterized in that: include: Acquire collected data and simulated data of the distribution network; wherein the collected data represents the operating data of the distribution network collected by the collection equipment; and the simulated data represents the data of the operating status of the distribution network simulated by the simulation software; Determining target characteristics based on the collected data and the simulation data; wherein the target characteristics represent the operating status of the distribution network; predicting operating parameters of the distribution network based on the target characteristics; and determining a target configuration scheme for a reactive power compensation device of the distribution network based on the operating parameters; According to the target configuration scheme, the switching of the reactive compensation device is controlled to control the normal operation of the distribution network.

2. The method according to claim 1, characterized in that Determining a target configuration scheme of the reactive power compensation device of the distribution network according to the operating parameters includes: Determine the initial configuration plan based on operating parameters; The initial configuration scheme is optimized to obtain the target configuration scheme.

3. The method according to claim 2, characterized in that The optimizing the initial configuration scheme to obtain the target configuration scheme includes: Generate multiple solutions based on the operating parameters, wherein each solution represents a configuration scheme corresponding to a set of distribution network operating parameters; repeat the following steps until a preset number of iterations is reached, and determine the solution with the highest fitness as the target configuration scheme: For each solution, multi-level simulation is performed on the solution to determine the fitness of the solution; Based on a preset selection algorithm, the operating parameters of the solution are adjusted to obtain other solutions.

4. The method according to claim 3, characterized in that The performing multi-level simulation processing on the solution to determine the fitness of the solution includes: The solution is simulated at multiple levels to determine network losses, voltage deviations, and load imbalance. The adaptability of the solution is determined according to the network loss, voltage deviation and load imbalance.

5. The method according to claim 1, wherein Determining target features based on the collected data and the simulation data includes: determining acquisition features based on the acquired data; and determining simulation features based on the simulation data; Based on the operating parameters of the distribution network, the collected features and the simulation features are screened to obtain the target features.

6. The method according to claim 1, characterized in that The predicting, based on the target characteristics, operating parameters of the distribution network includes: The target characteristics are input into a preset prediction model, and the operating parameters of the distribution network are output.

7. The method according to any one of claims 1 to 6, characterized in that The obtaining of simulation data of the distribution network includes: Based on the collected data, multi-level simulation processing is performed on the operating status of the distribution network to obtain the simulation data; wherein the multi-level simulation processing includes at least two of the equipment level, feeder level, and network level.

8. A control device for a distribution network, characterized in that: include: An acquisition module is used to acquire collected data and simulation data of the distribution network; wherein the collected data represents the operating data of the distribution network collected by the collection equipment; and the simulation data represents the data of the distribution network operating status simulated by the simulation software; A determination module, configured to determine a target feature based on the collected data and the simulation data; wherein the target feature represents an operating state of the distribution network; a prediction module, configured to predict operating parameters of the distribution network based on the target characteristics; and determine a target configuration scheme for a reactive power compensation device of the distribution network based on the operating parameters; A control module is used to control the switching of the reactive compensation device according to the target configuration scheme to control the normal operation of the distribution network.

9. An electronic device, characterized in that: include: Memory, processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images