Method for generating auxiliary decision of large-area fault of distribution network, and electronic device

Abstract

The application discloses a kind of generation methods of distribution network large-area fault auxiliary decision and electronic equipment. Among them, the method includes: obtaining fault information using multi-source heterogeneous mining technology;Based on fault information, using genetic algorithm to generate power restoration auxiliary decision;Using multi-source heterogeneous mining technology to obtain bus load information;Based on power restoration auxiliary decision and bus load information, bus outage bulk transfer decision is generated using machine learning algorithm;At least one of power restoration auxiliary decision and bus outage bulk transfer decision is used to generate comprehensive auxiliary decision based on it, and comprehensive auxiliary decision is used to show target user to assist target user to make decision.The application solves the technical problem that the reliability and applicability of distribution network large-area fault auxiliary decision is not high.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of auxiliary decision generation, in particular to a method for generating auxiliary decision of large-area fault of distribution network and an electronic device. BACKGROUND

[0002] The analysis of auxiliary decision of large-area fault of distribution network involves multiple technical aspects. In terms of generation of transfer strategy, a method for generating transfer strategy of intelligent distribution network based on prediction is proposed. First, the section data of system operation is obtained from the distribution monitoring system, combined with the one-time model information and the operating state of the equipment, and the topological structure of system operation is calculated through the topological service to provide the basis for load transfer. Then, the system prediction results are obtained from the prediction system, and the topological structure of system operation and the prediction results are input into the load transfer expert system to calculate and generate the transfer strategy according to the weight configuration of transfer. Finally, the transfer strategy is stored in the database or displayed on the interface to provide decision basis for the operating personnel.

[0003] In terms of generation of planned maintenance strategy, an ant colony algorithm-based maintenance strategy method for distribution network is proposed, which uses ant colony algorithm to solve the problem of state maintenance model of distribution equipment. The traditional maintenance model based on minimum cost often leads to excessive remaining time, in order to solve this problem, the optimization model is improved, and the equipment operation reliability is introduced as a constraint condition to limit the cycle number and cycle length of maintenance plan. Through the analysis of the fault data of actual distribution transformer, an optimal maintenance plan model is obtained, which can consider the cycle number and total cost comprehensively, and the model has high reliability.

[0004] For a method for generating transfer strategy of intelligent distribution network based on prediction, the method depends on accurate prediction results to generate transfer strategy, but the prediction results may be affected by various factors such as weather and unexpected events, resulting in inaccurate prediction results and affecting the effectiveness of the transfer strategy; secondly, this method may have deficiencies when dealing with multi-source heterogeneous data, and cannot fully mine the valuable information in the data, resulting in inaccurate fault perception.

[0005] For an ant colony algorithm-based maintenance strategy method for distribution network, although the ant colony algorithm can find a better solution in some cases, it still has problems such as slow convergence speed and easy to fall into local optimum, which may affect the generation efficiency and quality of the maintenance strategy; secondly, this method relies on the analysis of fault data of actual distribution transformer, if the data is not comprehensive or accurate, it may affect the reliability and applicability of the model.

[0006] In view of the above problems, no effective solution has been proposed so far. SUMMARY

[0007] The embodiment of the present application provides a generation method of auxiliary decision of large-area fault of distribution network and an electronic device, so as to at least solve the technical problem that the reliability and applicability of the auxiliary decision of large-area fault of distribution network are not high.

[0008] According to an aspect of the embodiment of the present application, a generation method of auxiliary decision of large-area fault of distribution network is provided, comprising: obtaining fault information by using multi-source heterogeneous mining technology, the fault information comprising power grid abnormal data of a power grid area where a large-area power failure occurs; generating a power restoration auxiliary decision by using a genetic algorithm based on the fault information, the power restoration auxiliary decision comprising a strategy of power transfer in a specific switch combination, switch sequence and line path; obtaining busbar load information by using multi-source heterogeneous mining technology, the busbar load information comprising busbar load and power transfer capacity; generating a busbar power failure batch power transfer decision by using a machine learning algorithm based on the power restoration auxiliary decision and the busbar load information, the busbar power failure batch power transfer decision comprising a power transfer strategy of transferring load from a power failure busbar to other normally operating busbars; generating a comprehensive auxiliary decision based on at least one of the power restoration auxiliary decision and the busbar power failure batch power transfer decision, the comprehensive auxiliary decision being used to show the target user to assist the target user in decision-making.

[0009] Further, after generating the busbar power failure batch power transfer decision by using the machine learning algorithm based on the power restoration auxiliary decision and the busbar load information, the method further comprises: obtaining maintenance information, the maintenance information comprising devices affected by the power failure; generating a preliminary maintenance strategy based on the maintenance information, the preliminary maintenance strategy comprising a range and sequence of device maintenance in the power transfer process; optimizing the preliminary maintenance strategy by using a particle swarm optimization algorithm to obtain a planned maintenance strategy.

[0010] Further, generating the comprehensive auxiliary decision based on at least one of the power restoration auxiliary decision and the busbar power failure batch power transfer decision further comprises: generating the comprehensive auxiliary decision based on the power restoration auxiliary decision, the busbar power failure batch power transfer decision and the planned maintenance strategy.

[0011] Further, after generating the busbar power failure batch power transfer decision by using the machine learning algorithm, the method further comprises: performing feature extraction on strategy information features of the power restoration auxiliary decision and the busbar power failure batch power transfer decision to obtain classification feature results, the strategy information features comprising one of: scheme compilation time, scheme compilation personnel; performing classification management on the power restoration auxiliary decision and the busbar power failure batch power transfer decision based on the classification feature results.

[0012] Further, after generating the comprehensive auxiliary decision, the method comprises: sending the comprehensive auxiliary decision to a main grid OMS system through a distribution network OMS system; performing information checking on the distribution network OMS system and the main grid OMS system by using a preset interactive interface, the checked information comprising a name of a remote control switch and a position of the remote control switch in the power grid.

[0013] Further, based on the fault information, the genetic algorithm is used to generate the power restoration auxiliary decision, including: generating a set of initial transfer strategies based on the fault information, the fault information including at least one of the following: current mutation information, voltage fluctuation mode; the initial transfer strategy is used as the initial population of the genetic algorithm; the fitness function of the genetic algorithm is defined; the genetic operation is performed on the initial population, and the genetic operation includes at least one of the following: selection, crossover, mutation; the optimal solution of the genetic algorithm is determined based on the fitness function, and the optimal solution is determined as the power restoration auxiliary decision.

[0014] Further, the fitness function of the genetic algorithm is defined, including: determining the optimization target, the optimization target including at least one of the following: minimizing the power outage range, minimizing the power restoration time; the fitness function is defined based on the optimization target.

[0015] Further, based on the power restoration auxiliary decision and the bus load information, the machine learning algorithm is used to generate the bus outage batch transfer decision, including: the bus load information is used as a training set; the selected machine learning algorithm is trained using the training set to adjust the parameters of the model established by the machine learning algorithm to obtain an evaluation model; and the evaluation model is used to generate the bus outage batch transfer decision.

[0016] According to another aspect of the embodiments of the present application, an electronic device is also provided, including: a memory storing an executable program; and a processor configured to execute the program, wherein the program performs the method in the embodiments of the present application when executed.

[0017] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, including a stored executable program, wherein the computer readable storage medium controls the device where the computer readable storage medium is located to perform the method in the embodiments of the present application when the executable program is executed.

[0018] In the embodiments of the present application, the multi-source heterogeneous mining technology is used to obtain the fault information and the bus load information, the genetic algorithm is used to generate the power restoration auxiliary decision, and the machine learning algorithm is used to generate the bus outage batch transfer decision, so as to achieve the purposes of realizing fast and accurate fault perception and realizing fast response and efficient auxiliary decision through advanced algorithms, thereby realizing the technical effects of being able to quickly respond and provide scientific and reasonable auxiliary decision when a large-area fault outage occurs, ensuring the reliability of transfer and the accuracy of repair, and further solving the technical problems of low reliability and applicability of auxiliary decision for large-area fault of distribution network. BRIEF DESCRIPTION OF DRAWINGS

[0019] The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:

[0020] Figure 1 is a hardware structure block diagram of a computer terminal of a generation method of a power distribution network large-area fault auxiliary decision according to an optional embodiment of the application;

[0021] Figure 2 is a flowchart of a generation method of a power distribution network large-area fault auxiliary decision according to an optional embodiment of the application;

[0022] Figure 3 is a schematic diagram of a generation method of a power supply recovery auxiliary decision according to an optional embodiment of the application;

[0023] Figure 4 is a flowchart of a machine learning algorithm according to an optional embodiment of the application;

[0024] Figure 5 is a framework schematic diagram of a transfer strategy management system according to an optional embodiment of the application;

[0025] Figure 6 is a flowchart of a planned maintenance strategy analysis according to an optional embodiment of the application;

[0026] Figure 7 is a flowchart of a main power distribution network remote control switch control analysis according to an optional embodiment of the application;

[0027] Figure 8 is a schematic diagram of an overall technical architecture according to an optional embodiment of the application. DETAILED DESCRIPTION

[0028] In order to enable persons skilled in the art to better understand the application scheme, the technical solutions in the embodiments of the application will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the application. Obviously, the described embodiments are only a part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by persons skilled in the art without creative work should belong to the protection scope of the application.

[0029] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and the above-described accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] According to an embodiment of the present application, a method embodiment of a method for generating a power distribution large-area fault auxiliary decision is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0031] The method embodiment can be executed in an electronic device containing a memory and a processor in a computer or similar computing device. For example, as shown in the computer's electronic device, Figure 1 may include one or more processors 102 (the processor can include but is not limited to a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP) chip, a microprocessor (MCU), a programmable logic device (FPGA), a neural network processor (NPU), a tensor processor (TPU), an artificial intelligence (AI) type processor, etc. processing device) and memory 104 for storing data. Optionally, the above-mentioned computer's electronic device can also include a transmission device 106 for communication function, an input and output device 108, and a display device 110. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned computer's electronic device. For example, the computer's electronic device can also include more or less components than those described above, or have a different configuration from that described above.

[0032] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as the computer program corresponding to the method for generating auxiliary decision of large-area fault of distribution network in the embodiments of the present application. The processor 102 can execute various functional applications and data processing, i.e., implement the method for generating auxiliary decision of large-area fault of distribution network, by running the computer programs stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, and the remote memory can be connected to the mobile terminal through a network. Examples of the network can include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0033] The transmission device 106 is configured to receive or send data via a network. Examples of the network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC) which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device can be a radio frequency (RF) module which is configured to communicate with the Internet in a wireless manner.

[0034] The display device 110 can be, for example, a liquid crystal display (LCD) and a touch display (also referred to as a "touch screen" or "touch display screen"). The liquid crystal display can enable a user to interact with a user interface of the mobile terminal. In some embodiments, the mobile terminal has a graphical user interface (GUI), and a user can interact with the GUI through finger contacts and / or gestures on the touch-sensitive surface. The interactions between the user and the GUI can optionally include one or more of the following: creating a webpage, drawing, text inputting, composing an electronic mail, playing a game, viewing a video, viewing a digital photo, and / or browsing a network resource. The executable instructions for performing these interactions can be configured and stored in a computer program product or a readable storage medium that can be executed by one or more processors.

[0035] With the continuous development and expansion of the power system, distribution networks face increasingly complex operating environments. In actual operation, large-area fault power outages in distribution networks occur from time to time. How to quickly and accurately make auxiliary decision analysis to improve the efficiency of power supply and reduce the scope of planned maintenance has become a problem that needs to be solved. Currently, traditional fault handling methods often rely on human experience and rules, which are not sufficient when faced with complex and variable power grid structures. The interaction and verification of device information between distribution networks and main networks are not efficient enough, affecting the timeliness and accuracy of fault handling, leading to a slow decision-making process and difficulty in achieving global optimization. At the same time, traditional methods lack flexibility and intelligence, and cannot adapt to real-time changes in power grid conditions, resulting in low fault recovery efficiency. In order to overcome these problems, more advanced technical means need to be introduced, such as hybrid optimization algorithms, which combine the advantages of multiple optimization techniques and can generate more scientific and reasonable auxiliary decision-making schemes for large-area fault power outages in distribution networks.

[0036] Principle and application of hybrid optimization algorithm: Hybrid optimization algorithm combines the advantages of multiple algorithms to solve complex optimization problems, especially in nonlinear, multivariate, multi-objective or uncertain scenarios. It usually includes but is not limited to genetic algorithms, particle swarm optimization algorithms, machine learning algorithms, and traditional optimization algorithms, etc. to improve the search efficiency and global optimization ability of the algorithm, and overcome the limitations of single algorithms.

[0037] Multi-source heterogeneous data mining technology: Multi-source heterogeneous data mining technology focuses on processing data from different sources with different formats and structures. The core of the technology is data preprocessing, feature extraction and selection, and then using appropriate mining algorithms (such as classification, clustering, association rule learning, etc.) to analyze data and extract valuable information or knowledge. In the power system, it can identify fault patterns, predict demand changes, etc. from various data sources such as smart meter data, protection relay signals, and distributed energy output information.

[0038] Genetic Algorithm (GA): Genetic Algorithm is a heuristic optimization algorithm inspired by natural selection and genetic mechanisms in biological evolution. In the algorithm, solutions to problems are encoded as chromosomes, which are evolved through selection, crossover, and mutation operations, producing more adapted offspring in each generation. Through iterative optimization, the algorithm can find the approximate optimal solution or optimal solution of the problem. In the distribution network, genetic algorithm can be used for optimization of power supply strategy to find the best path that minimizes the outage range and recovery time.

[0039] Machine Learning Algorithms: Machine learning is a branch of artificial intelligence that focuses on building models that allow computers to automatically learn from data and make predictions or decisions. It encompasses a variety of algorithms such as Support Vector Machines (SVM), Decision Trees, Neural Networks, and more. In power distribution networks, machine learning can be used to train models that predict load changes, the reliability of transfer strategies, and assess potential environmental impacts, resulting in more intelligent and optimized strategies.

[0040] Particle Swarm Optimization (PSO): Particle Swarm Optimization is a global optimization algorithm inspired by the foraging behavior of bird swarms. In the algorithm, each solution is represented as a particle in the search space, and these particles update their positions and velocities through iterations to find the optimal or near-optimal solution. In power systems, PSO can be used to generate maintenance scheduling strategies by considering multiple objectives such as maintenance time, cost, and impact on users.

[0041] Figure 2 According to the method of the embodiment of the present application, as shown in Figure 2 the method comprises the following steps:

[0042] Step S10, obtaining fault information using multi-source heterogeneous mining technology, the fault information including power grid abnormal data of the power grid area where a large-area fault blackout occurs;

[0043] Step S20, generating a power restoration auxiliary decision based on the fault information using a genetic algorithm, the power restoration auxiliary decision including a strategy for transferring power with specific switch combinations, switch sequences, and line paths;

[0044] Step S30, obtaining bus load information using multi-source heterogeneous mining technology, the bus load information including bus load and transfer capacity;

[0045] Step S40, generating a bus outage bulk transfer decision based on the power restoration auxiliary decision and the bus load information using a machine learning algorithm, the bus outage bulk transfer decision including a transfer strategy for transferring load from a blackout bus to other normally operating buses;

[0046] Step S50, generating a comprehensive auxiliary decision based on at least one of the power restoration auxiliary decision and the bus outage bulk transfer decision, the comprehensive auxiliary decision used to show the target user to assist the target user in making decisions.

[0047] In the embodiment of the present application, the method for obtaining fault information and bus load information by using multi-source heterogeneous mining technology is adopted, the restoration power supply auxiliary decision is generated by using genetic algorithm, and the bus outage batch power supply decision is generated by using machine learning algorithm, so that the purposes of realizing fast and accurate fault perception and realizing fast response and efficient auxiliary decision by using advanced algorithm are achieved, thereby realizing the technical effects that when large-area fault outage occurs, fast response and scientific and reasonable auxiliary decision can be provided, the reliability of power supply and the accuracy of maintenance are ensured, and the technical problems of low reliability and applicability of auxiliary decision for large-area fault of distribution network are solved.

[0048] The present application focuses on solving many key technical problems in the scene of large-area fault outage of distribution network. In the actual operation of the power system, when large-area outage of distribution network is caused by natural disasters, equipment failure and the like, the traditional coping method has very low decision efficiency in the face of such conditions, and it is difficult to output optimized large-area outage auxiliary decision, bus outage batch power supply strategy and planned maintenance strategy. At the same time, there are obvious deficiencies in the value mining of multi-source heterogeneous data, and fast and accurate fault perception cannot be realized. Furthermore, the current power supply strategy management is not convenient and efficient, which is not conducive to the query and selection of operators. In addition, there is a lack of effective means for information interaction and verification between the distribution network and the main network, and it is difficult to maximize the power supply efficiency and minimize the planned maintenance range. The present application integrates multi-source heterogeneous data mining technology, genetic algorithm, machine learning algorithm and particle swarm optimization algorithm and the like by means of hybrid optimization algorithm, generates corresponding strategies and performs information interaction and verification. It is widely used in various complex distribution network environments, can quickly respond and provide scientific and reasonable auxiliary decision when large-area fault outage occurs, ensures the reliability of power supply and the accuracy of maintenance, provides convenience for operators to query and select power supply strategies, strengthens the collaborative operation of distribution network and main network, and effectively improves the stability and reliability of the power system.

[0049] The present application focuses on solving many key technical problems in the scene of large-area fault outage of distribution network. In the actual operation of the power system, when large-area outage of distribution network is caused by natural disasters, equipment failure and the like, the traditional coping method has very low decision efficiency in the face of such conditions, and it is difficult to output optimized large-area outage auxiliary decision, bus outage batch power supply strategy and planned maintenance strategy. At the same time, there are obvious deficiencies in the value mining of multi-source heterogeneous data, and fast and accurate fault perception cannot be realized. Furthermore, the current power supply strategy management is not convenient and efficient, which is not conducive to the query and selection of operators. In addition, there is a lack of effective means for information interaction and verification between the distribution network and the main network, and it is difficult to maximize the power supply efficiency and minimize the planned maintenance range. The present application integrates multi-source heterogeneous data mining technology, genetic algorithm, machine learning algorithm and particle swarm optimization algorithm and the like by means of hybrid optimization algorithm, generates corresponding strategies and performs information interaction and verification. It is widely used in various complex distribution network environments, can quickly respond and provide scientific and reasonable auxiliary decision when large-area fault outage occurs, ensures the reliability of power supply and the accuracy of maintenance, provides convenience for operators to query and select power supply strategies, strengthens the collaborative operation of distribution network and main network, and effectively improves the stability and reliability of the power system.

[0050] In summary, the application realizes fast fault perception, generates reliable transfer strategy and accurate planned maintenance strategy, facilitates operator query and selection, strengthens the collaborative operation of distribution network and main network, improves the stability and reliability of the power system, and ensures that the power supply can be quickly and effectively restored when the distribution network fails in a large area.

[0051] The application provides a distribution network large-area fault power failure auxiliary decision analysis method based on a hybrid optimization algorithm.

[0052] The technical scheme is designed as follows: firstly, multi-source heterogeneous data mining technology is used for fast fault perception and genetic algorithm is used for auxiliary decision generation. The preliminary auxiliary decision of large-area fault power failure is generated; secondly, based on the preliminary auxiliary decision, a machine learning algorithm is used to generate a bus power failure batch transfer strategy. The strategy needs to consider load information and transfer capacity to ensure the reliability of the transfer. The transfer strategy obtained after analysis also needs to be managed to facilitate operator query and selection; then, the equipment that needs to be maintained after this fault is counted, and a particle swarm optimization algorithm is used to form a planned maintenance strategy. Finally, these strategies are interacted to the distribution network OMS system through the Webservice interface. The distribution network OMS system and the distribution network OCS system interact information, and the distribution network OCS system generates a comprehensive strategy. The comprehensive strategy generated by the distribution network OCS system is transmitted to the main network OCS system through the Webservice interface, and the information is interactively checked to select the optimized multiple transfer strategies for the operation and maintenance personnel to select, so as to maximize the transfer efficiency and minimize the planned maintenance range.

[0053] The main goal of the large-area fault power failure auxiliary decision (i.e., the power restoration auxiliary decision) is to generate an effective decision to realize fast power restoration when a large-scale power failure event occurs. The application uses multi-source heterogeneous data mining technology to quickly and effectively confirm fault-related information, including specific location, cause, etc. Then, a genetic algorithm is used to find the best power restoration auxiliary decision. Figure 3 The specific implementation steps are as follows:

[0054] (1) Fault awareness. Fault awareness is achieved by timely detection and response to faults, avoiding the expansion of faults and preventing potential safety risks, thereby improving the reliability of the entire power system. In the case of large-area power failure in distribution networks, multi-source heterogeneous data mining technology plays a crucial role. By deeply mining data from different data sources and different structures, the occurrence of faults can be quickly and accurately perceived. This provides a key information foundation for subsequent auxiliary decision-making, enabling the capture of fault signals at the first time and gaining valuable time for timely response measures.

[0055] (2) Auxiliary decision-making. After obtaining specific information about the fault, a restoration power supply auxiliary decision is generated using a genetic algorithm. Genetic algorithms are powerful optimization tools that simulate natural selection and genetic mechanisms to solve complex optimization problems. In this application, the genetic algorithm is used to find the optimal transfer strategy to minimize the impact of power failure and quickly restore power supply. Based on the results of fault awareness, the genetic algorithm initially generates a set of feasible transfer strategies as the initial population of the genetic algorithm; then evaluates the pros and cons of these transfer strategies, including considering the reliability of transfer and the stability of the system, to search for a better transfer strategy; according to the characteristics of the genetic algorithm, repeat the genetic operation and fitness evaluation until the optimal transfer strategy that meets the requirements is found.

[0056] In the event of a large-area power failure in a distribution network, the preliminary auxiliary decision refers to a set of emergency response strategies quickly generated using optimization algorithms (such as genetic algorithms) based on the preliminary understanding of the fault and the current state of the power grid after the fault awareness stage. The purpose of this strategy is to restore power supply as quickly as possible and reduce the impact of power failure on users and the power grid. The generation of preliminary auxiliary decisions usually includes the following steps:

[0057] 1. Fault awareness and identification: Through multi-source heterogeneous data mining technology, the location, type, and impact range of the fault are identified from the data collected from various sensors, smart meters, monitoring systems, etc.

[0058] 2. State assessment: Assess the current state of the power grid, including key parameters such as load, voltage, available resources (such as backup power and transfer lines), etc., to determine which parts can be safely used for transfer.

[0059] 3. Strategy generation: Use optimization techniques such as genetic algorithms to generate one or more transfer strategies. Genetic algorithms simulate natural selection processes such as crossover, mutation, and selection to continuously evolve the solution set, seeking the best strategy that can minimize the range and time of power failure.

[0060] 4. Preliminary decision: Based on the above steps, a preliminary auxiliary decision is formed, including transfer path, switch operation sequence, and possible transfer capacity, etc., providing a basis for subsequent fine control and adjustment.

[0061] The generation of preliminary auxiliary decision is the first step in the fault recovery process, which needs to give a rough solution within a limited time for subsequent detailed analysis and execution.

[0062] The planned maintenance strategy refers to the pre-planned maintenance and repair activities in the distribution network, which is used to preventively check and repair equipment to improve the reliability and efficiency of the power grid and reduce the occurrence of sudden failures. In this invention, the generation of planned maintenance strategy is based on the evaluation of faulty equipment and the in-depth analysis of the operation state of the power grid, and the main steps include:

[0063] 1. Equipment impact analysis: Determine which equipment or lines are affected by the fault, and evaluate their damage degree and impact on the operation of the power grid.

[0064] 2. Maintenance resource planning: Considering the available human, material resources, and the maintenance priority of equipment, plan a reasonable maintenance sequence and time window.

[0065] 3. Strategy optimization: Use particle swarm optimization algorithm and other optimization techniques to adjust the maintenance plan to find the maintenance strategy that meets the maintenance needs while minimizing the impact on the operation of the power grid and the cost.

[0066] 4. Strategy implementation and adjustment: Implement the optimized planned maintenance strategy in the power grid, and dynamically adjust it according to the real-time operation state of the power grid and external environmental changes (such as weather, load demand) to ensure the smooth progress of the maintenance activities and the stable operation of the power grid.

[0067] The purpose of the planned maintenance strategy is to ensure the safe and stable operation of the power grid, and to improve the availability of equipment and the overall performance of the system through scientific planning and optimization. The combination of these two concepts, preliminary auxiliary decision and planned maintenance strategy, constitutes a comprehensive solution for the invention to deal with large-area power failure in distribution network, which not only focuses on emergency recovery after failure, but also focuses on preventive maintenance and repair to comprehensively improve the operation efficiency and power supply quality of the power system.

[0068] Further, based on the restoration power supply auxiliary decision and bus load information, the method further comprises: obtaining maintenance information, the maintenance information including equipment affected by the power failure; generating a preliminary maintenance strategy based on the maintenance information, the preliminary maintenance strategy including the range and sequence of equipment maintenance during power transfer; and using a particle swarm optimization algorithm to optimize the preliminary maintenance strategy to obtain a planned maintenance strategy.

[0069] After the preliminary generated strategy is analyzed by the busbar outage bulk transfer strategy, the equipment, line and other devices that need to be repaired in the fault need to be considered to reduce the scope of repair, save human resources and improve the efficiency of power restoration. The first step of planned repair is to analyze the impact of the fault. Determine which devices are affected by the fault and the extent of the impact. This helps to determine the focus and priority of the repair, arrange the repair resources reasonably and improve the efficiency of the repair; then, combined with the analysis of the transfer strategy, consider how to transfer during the repair process to ensure that the power supply to the users is not greatly affected. Analyze the feasibility and risk of transfer, develop a reasonable transfer plan and ensure the stable operation of the power system during the repair period; finally, the planned repair strategy is optimized by the particle swarm optimization algorithm. This algorithm can find the optimal solution among numerous repair schemes, taking into account various factors such as repair time, cost, impact on users, etc., and ultimately provide a scientific and reasonable auxiliary decision to provide strong support for the operation and maintenance personnel. The implementation method of the planned repair strategy analysis is as shown in Figure 6

[0070] Further, generating an integrated auxiliary decision based on at least one of the power restoration auxiliary decision and the busbar outage bulk transfer decision further includes generating the integrated auxiliary decision based on the power restoration auxiliary decision, the busbar outage bulk transfer decision, and a planned repair strategy.

[0071] ​The bus power outage batch transfer strategy is a strategy for transferring loads from a power outage bus to other normally operating buses in order to ensure the continuity of user power supply and the stability of power grid operation when a certain bus (a group of connection points in a substation for collecting and distributing power) needs to be powered off due to failure, maintenance or other reasons. This strategy usually involves several steps: 1. Load statistics and analysis: First, all load points on the power-off bus, including various users and electrical equipment, need to be counted and analyzed for their load properties and importance levels. For example, industrial loads, residential loads or critical infrastructure (such as hospitals, emergency services) loads. 2. Transfer path identification: Next, based on the topology and operating state of the power grid, identify the paths that can be used for transfer. This includes finding the connection lines between adjacent buses or substations, and evaluating the carrying capacity of the lines and the stability of the power grid. 3. Strategy planning: After identifying possible transfer paths, specific transfer strategies need to be planned. This may include deciding the amount of load to be transferred, the time window for transfer, the priority of transfer, etc. Strategy planning needs to consider physical constraints of the power grid, such as maximum current limit of the line, and power supply and demand balance, to avoid overload or voltage abnormalities during the transfer process. 4. Batch transfer: Batch transfer means that the load is transferred from the power-off bus to the transferable bus in one or more batches, rather than individually. This can reduce the number of operations, improve transfer efficiency, and reduce the instantaneous impact on the power grid. 5. Strategy optimization and evaluation: The transfer strategy needs to be optimized through optimization algorithms to find the optimal solution under all constraint conditions (such as line capacity limit, voltage stability, load importance, etc.). At the same time, the strategy needs to be evaluated to ensure its feasibility and minimal impact on power grid operation.

[0072] Further, after generating the bus power outage batch transfer decision using the machine learning algorithm, the method further includes: performing feature extraction on the strategy information features of the power restoration auxiliary decision and the bus power outage batch transfer decision to obtain classification feature results, the strategy information features including one of: scheme preparation time, scheme preparation personnel; and classifying and managing both the power restoration auxiliary decision and the bus power outage batch transfer decision based on the classification feature results.

[0073] The obtained transfer strategy is effectively managed, facilitating operator query and selection. By establishing a perfect transfer strategy management system, various transfer schemes can be classified, stored and displayed, and operators can quickly select the most suitable transfer strategy according to actual conditions according to strategy information features such as scheme preparation time and preparation personnel. This not only improves the convenience of operation, but also ensures the efficient execution of the transfer strategy. The designed transfer strategy management system framework is shown in Figure 5

[0074] ​Further, after generating the comprehensive auxiliary decision, the method comprises: sending the comprehensive auxiliary decision to the main grid OMS system through the distribution grid OMS system; and performing information checking on the distribution grid OMS system and the main grid OMS system by using a preset interaction interface, wherein the checked information comprises the name and position of the remote control switch in the power grid.

[0075] The main-distribution grid remote control switch control analysis implementation method is as shown in Figure 7 After sequentially analyzing and deciding the preliminary auxiliary decision, information interaction and checking between the distribution grid system and the main grid system are involved, including the large-area power failure auxiliary decision, the busbar power failure batch transfer strategy and the planned maintenance strategy generated in each link are summarized, the application uses the Webservice interface to summarize the information of these strategies and analysis to the distribution grid OMS system, and the distribution grid OMS system is transmitted to the distribution grid OCS system for summarization to generate a comprehensive strategy, and then the Webservice interface is used to realize information interaction and checking between the distribution grid OCS system and the main grid OCS system, including checking the name and position of the remote control switch in the information. After the operator selects the comprehensive strategy to be executed, the main grid OCS system performs sequence control through the checked switch opening strategy to realize fault power restoration.

[0076] Further, based on the fault information, a genetic algorithm is used to generate a power restoration auxiliary decision, which comprises: generating a group of initial transfer strategies based on the fault information, wherein the fault information comprises at least one of the following: current mutation information and voltage fluctuation mode; taking the initial transfer strategy as the initial population of the genetic algorithm; defining the fitness function of the genetic algorithm; performing genetic operations on the initial population, wherein the genetic operations comprise at least one of the following: selection, crossover and mutation; determining the optimal solution of the genetic algorithm based on the fitness function, and determining the optimal solution as the power restoration auxiliary decision.

[0077] Further, the fitness function of the genetic algorithm is defined, which comprises: determining an optimization target, wherein the optimization target comprises at least one of the following: minimizing the power failure range and shortening the power restoration time; and defining the fitness function based on the optimization target.

[0078] The initially generated auxiliary decision does not take into account the load information and transfer capacity of the busbar, so it is necessary to use a machine learning algorithm to further consider these two factors to obtain a comprehensive transfer strategy. At the same time, the generated strategy needs to be managed, which helps the operator to query according to the characteristic information. The specific implementation steps are as follows:

[0079] (1) Load information statistics and transfer capacity analysis. Understanding the load situation on the bus can help predict the possible load impact during the restoration process, so that measures can be taken to avoid excessive pressure on the power grid; the transfer capacity refers to the additional power supply capacity that can be provided by other power sources or paths within a certain area, ensuring that there is enough transfer capacity to quickly switch to the backup path when the main power supply path fails, ensuring uninterrupted power supply. Using the above multi-source heterogeneous data mining technology, the load information and transfer capacity information are statistically analyzed and imported into the machine learning algorithm for model training, considering multiple objectives for optimization, such as: minimizing power outages, reducing environmental impact, etc. to ensure that the generated strategy meets various physical and technical constraints of the power grid operation, and then dynamically adjust the strategy according to real-time feedback and new information to adapt to changing conditions. The machine learning algorithm process is shown in Figure 3.

[0080] Further, based on the power restoration auxiliary decision and bus load information, a bus outage batch transfer decision is generated using a machine learning algorithm, including: using bus load information as a training set; using the training set to train the selected machine learning algorithm to adjust the parameters of the model established by the machine learning algorithm to obtain an evaluation model; using the evaluation model to generate a bus outage batch transfer decision.

[0081] The core of the present application is to use a hybrid optimization algorithm, combining advanced technologies such as genetic algorithm, machine learning algorithm and particle swarm optimization algorithm, to deeply mine and analyze a large amount of data in the distribution network system. First, through multi-source heterogeneous data mining technology, real-time operation data is obtained from the distribution monitoring system, including device status, load information, topology structure, etc., providing comprehensive data support for subsequent decision-making. Then, a preliminary auxiliary decision is generated using a genetic algorithm, and an optimal bus outage batch transfer strategy is calculated and generated using a machine learning algorithm that considers load information and transfer capacity constraints. At the same time, an optimal planned maintenance strategy is developed using a particle swarm optimization algorithm to minimize the maintenance scope and shorten the outage time. In order to realize efficient collaborative operation between the distribution network and the main network, the present application realizes information exchange between the distribution network OMS system and the OCS system through the Webservice interface, as well as data verification between the distribution network OCS system and the main network OCS system. This information exchange and verification mechanism ensures the effective implementation and real-time updating of the strategy, enabling the distribution network system to better adapt to real-time changes in power grid conditions. The final multiple optimization comprehensive strategies are displayed through the interface or stored in the database, and the operation and maintenance personnel can quickly select the most suitable strategy according to the actual situation to achieve the goal of maximizing transfer efficiency and minimizing planned maintenance scope. The overall technical architecture is shown in Figure 4. Figure 8

[0082] In an optional embodiment, according to the above technical solution, an example is as follows: ​

[0083] Suppose a large-scale power failure occurs in a certain area of a city.

[0084] (1) After detecting the fault signal, analyze the data from different sensors and monitoring devices through multi-source heterogeneous data mining technology. For example, obtain current data from smart meters and find that the current in a certain area suddenly drops from the normal 100A to close to 0A; find that the voltage in this area has dropped significantly from 220V. It is determined that a fault has occurred in this area, and it is preliminarily judged that the fault location may be in a certain substation or line segment.

[0085] (2) According to the fault information, use genetic algorithm to generate power restoration auxiliary decision. First, generate a set of feasible transfer strategies as the initial population of genetic algorithm. For example, consider transferring power from another nearby substation, the maximum carrying current of the transfer line is 150A, and the voltage is 220V. Then evaluate the pros and cons of this set of transfer strategies, including considering the reliability of transfer and the stability of the system. After multiple genetic operations and fitness evaluations, the optimal transfer strategy that meets the requirements is finally found, such as determining to transfer power with a specific switch combination and line path, ensuring that the current is stable at around 120A and the voltage is maintained at 220V during the transfer process.

[0086] (3) Use multi-source heterogeneous data mining technology to statistically analyze the load information on the bus of the area, and find that the current bus load is 80kW, while the transfer capacity is 100kW. Import these information into the machine learning algorithm for model training, considering the minimization of power outage, reduction of environmental impact and other goals for optimization. The generated transfer strategy may be to gradually increase the transfer current in a certain time period, from the initial 50A to 80A, to avoid load impact. At the same time, manage the transfer strategy, and operators can query and select according to the characteristics of the scheme preparation time, etc.

[0087] (4) Analyze the scope of the fault impact and determine the devices and lines affected by the fault. For example, it is found that the insulation damage of a certain line segment caused the fault, affecting the power supply of multiple users in the surrounding area. Combined with the analysis of the transfer strategy, consider how to transfer during the repair process. Through the particle swarm optimization algorithm, develop a reasonable plan for repair strategy. For example, determine to repair in the next 2 hours, during which the power supply to users is guaranteed through a specific transfer path, and the repair cost is controlled within a certain range, while minimizing the impact on users.

[0088] (5) The strategy and analysis information generated by each link are summarized to the distribution network OMS system, and then transmitted to the distribution network OCS system to generate a comprehensive strategy. The information interaction and verification between the distribution network OCS system and the main network OCS system are realized by using the Webservice interface, so as to ensure that the name and position of the remote control switch are accurate. After the operator selects to execute the comprehensive strategy, the main network OCS system performs sequence control on the switch through the verified switch opening strategy, so as to realize fault power recovery. For example, a specific main network switch is controlled to switch from the closed state to the open state, the current is disconnected from the line connected with the switch, and then the current is redistributed through the transfer line, so as to realize the power recovery of the fault area.

[0089] In summary, the application significantly improves the auxiliary decision-making ability and efficiency in the case of large-area fault power failure of the distribution network by using advanced hybrid optimization algorithms and information technology means. It not only solves the deficiencies in the prior art, but also enhances the flexibility and intelligent level of the system and improves the automation degree of the distribution network fault processing. Through the application of the application, the decision can be made quickly and effectively and the power supply can be restored in the case of large-area fault power failure of the distribution network, so as to ensure the stable operation of the power system and the power supply reliability of the user.

[0090] The application has the following innovative points:

[0091] 1. The advanced data mining technology is used to process heterogeneous data from different sources, so as to realize rapid and accurate fault perception.

[0092] 2. The advantages of the hybrid optimization algorithm are used to optimize the transfer and repair strategy.

[0093] 3. A mechanism is established to ensure the accurate exchange and verification of information between the distribution network and the main network.

[0094] The application provides the following methods:

[0095] 1. A distribution network large-area fault power failure auxiliary decision-making analysis method based on a hybrid optimization algorithm.

[0096] 2. A method for realizing rapid and accurate fault perception by using multi-source heterogeneous data mining technology.

[0097] 3. A method for generating a transfer strategy by combining a genetic algorithm, a machine learning algorithm and a particle swarm optimization algorithm.

[0098] 4. A method for realizing effective information interaction and verification between the distribution network and the main network by using a Webservice interface.

[0099] The present invention provides a comprehensive and efficient method through its unique technical features and the comprehensive application of multiple advanced algorithms. In terms of data mining, the prediction-based method may only rely on the cross-sectional data and primary model information of the system operation. Although the method based on the ant colony algorithm introduces the equipment operation reliability as a constraint, it may have limitations in processing multi-source heterogeneous data. The present invention, by integrating multi-source heterogeneous data mining technology, can more comprehensively analyze fault information and achieve fast and accurate fault perception; in the application of hybrid optimization algorithms, the prediction-based method mainly relies on the weight configuration of the expert system, which may not be flexible enough in the complex and changeable actual operating environment. Although the method based on the ant colony algorithm optimizes the maintenance cycle, the ant colony algorithm itself may have the problem of slow convergence speed and easy to fall into local optimality. The present invention adopts hybrid optimization methods such as genetic algorithm, machine learning algorithm and particle swarm optimization algorithm. The combination of these algorithms can better balance the search efficiency and the quality of the solution, and avoid falling into the local optimal solution; in terms of information interaction and verification mechanism, the existing methods have not formed a specific mechanism, while the present invention emphasizes the information interaction verification between the distribution network and the main network, and adopts effective means to ensure the coordinated operation between the two, which helps to maximize the transfer efficiency and minimize the scope of planned maintenance.

[0100] An embodiment of the present application further provides an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the program executes the methods of various embodiments of the present invention when running.

[0101] An embodiment of the present application further provides a computer-readable storage medium, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the methods in various embodiments of the present invention.

[0102] An embodiment of the present application further provides a computer program product, including a computer program, which implements the methods in various embodiments of the present invention when executed by a processor.

[0103] An embodiment of the present application further provides a computer program product, including a non-volatile computer-readable storage medium, wherein the non-volatile computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method in each embodiment of the present invention is implemented.

[0104] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0105] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented by other means. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and actual implementation can have another division mode, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between units or modules, which can be electrical or other forms.

[0106] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0107] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0108] The integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0109] The above is only the preferred embodiment of the present application, and it should be pointed out that for ordinary skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, and these improvements and refinements should be considered as the protection scope of the present application.

Claims

1. A method for generating a large-area fault auxiliary decision of network distribution, characterized in that, The method comprises: obtaining fault information by using a multi-source heterogeneous mining technology, the fault information comprising power grid abnormal data of a power grid area where a large-area power failure occurs; generating a power restoration auxiliary decision based on the fault information by using a genetic algorithm, the power restoration auxiliary decision comprising a strategy of power transfer in a specific switch combination, switch sequence and line path; obtaining busbar load information by using a multi-source heterogeneous mining technology, the busbar load information comprising busbar load and power transfer capacity; generating a busbar power failure batch power transfer decision based on the power restoration auxiliary decision and the busbar load information by using a machine learning algorithm, the busbar power failure batch power transfer decision comprising a power transfer strategy of transferring load from a power failure busbar to other normally-operating busbars; obtaining maintenance information, the maintenance information comprising equipment affected by power failure; generating a preliminary maintenance strategy based on the maintenance information, the preliminary maintenance strategy comprising a range and sequence of equipment maintenance during power transfer; optimizing the preliminary maintenance strategy by using a particle swarm optimization algorithm to obtain a planned maintenance strategy; generating a comprehensive auxiliary decision based on the power restoration auxiliary decision, the busbar power failure batch power transfer decision and the planned maintenance strategy, the comprehensive auxiliary decision being used to show the target user to assist the target user in making decisions.

2. The generation method of claim 1, wherein, After generating the busbar power failure batch power transfer decision by using the machine learning algorithm, the method further comprises: extracting features of strategy information of the power restoration auxiliary decision and the busbar power failure batch power transfer decision to obtain classification feature results, the strategy information comprising one of the following: scheme compilation time, scheme compilation personnel; classifying and managing the power restoration auxiliary decision and the busbar power failure batch power transfer decision based on the classification feature results.

3. The generation method of claim 1, wherein, After generating the comprehensive auxiliary decision, the method comprises: sending the comprehensive auxiliary decision to a main grid OMS system through a distribution network OMS system; verifying information of the distribution network OMS system and the main grid OMS system by using a preset interactive interface, the verified information comprising names and positions of remote control switches in the power grid.

4. The generation method of claim 1, wherein, Generating the power restoration auxiliary decision based on the fault information by using the genetic algorithm comprises: generating a group of initial power transfer strategies based on the fault information, the fault information comprising at least one of the following: current mutation information, voltage fluctuation mode; taking the initial power transfer strategies as initial populations of the genetic algorithm; defining a fitness function of the genetic algorithm; performing genetic operations on the initial populations, the genetic operations comprising at least one of the following: selection, crossover and mutation; determining an optimal solution of the genetic algorithm based on the fitness function, and determining the optimal solution as the power restoration auxiliary decision.

5. The generation method of claim 4, wherein, Defining the fitness function of the genetic algorithm comprises: determining an optimization target, the optimization target comprising at least one of the following: minimizing a power failure range, and shortening a power restoration time; defining the fitness function based on the optimization target.

6. The generation method of claim 1, wherein, Generating the busbar power failure batch power transfer decision based on the power restoration auxiliary decision and the busbar load information by using the machine learning algorithm comprises: The bus load information is taken as a training set; A selected machine learning algorithm is trained by using the training set to perform parameter adjustment on a model established by the machine learning algorithm, to obtain an evaluation model; The evaluation model is used to generate the bus power failure batch transfer decision.

7. An electronic device, comprising: Comprise: A memory storing an executable program; A processor configured to execute the program, wherein the program, when executed, performs the method of any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium comprises a stored executable program, wherein the executable program, when executed, controls the device where the storage medium is located to perform the method of any one of claims 1 to 6.

Images