Fault recovery methods, fault recovery devices and electronic equipment for power systems

Abstract

This application provides a fault recovery method, fault recovery device, and electronic device for power systems. The method includes: acquiring fault characteristics in the current power system and inputting these characteristics into a fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data, each set including historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal changes in the power system. Based on the current fault type, a corresponding fault recovery model is determined. The fault recovery model includes an objective function and constraints. An adaptive quantum particle swarm optimization algorithm is used to solve the fault recovery model to obtain the optimal fault location. Based on the fault type and the optimal fault location, a fault recovery scheme is determined and executed. This method solves the problem of low accuracy in existing fault detection methods.

Description

Technical Field

[0001] This application relates to the field of power system faults, and more specifically, to a power system fault recovery method, a computer-readable storage medium, a fault recovery device, and an electronic device. Background Technology

[0002] As a crucial component of the power system, the distribution network's primary function is to transmit high-voltage electricity to users at all levels through substations and distribution lines, ensuring their power supply. However, distribution networks frequently encounter various faults during operation. These faults not only cause power outages, disrupting users' normal production and daily lives, but existing automated fault detection methods based on sensor networks and smart meters also suffer from insufficient accuracy in identifying abnormal states in the face of complex power grid environments.

[0003] Therefore, there is an urgent need for a highly accurate method for detecting faults. Summary of the Invention

[0004] The main objective of this application is to provide a fault recovery method for power systems, a computer-readable storage medium, a fault recovery device, and an electronic device, so as to at least solve the problem of low accuracy in fault detection methods in the prior art.

[0005] To achieve the above objectives, according to one aspect of this application, a fault recovery method for a power system is provided, comprising: acquiring fault characteristics in the current power system; inputting the current fault characteristics into a fault model to obtain a current fault type; wherein the fault model is trained using multiple sets of historical data, each set of historical data including historical fault characteristics and corresponding historical fault types, the fault characteristics being abnormal change data of the power system; determining a corresponding fault recovery model based on the current fault type; solving the fault recovery model using an adaptive quantum particle swarm optimization algorithm to obtain an optimal fault location, the optimal fault location being the global optimal position of the particles; the fault recovery model including an objective function and constraints; determining a fault recovery scheme based on the fault type and the optimal fault location; and executing the corresponding fault recovery scheme.

[0006] Optionally, the current operating data of the power system is acquired; the operating data is analyzed to obtain abnormal change data; and the abnormal change data is subjected to time domain analysis and / or frequency domain analysis to obtain the fault characteristics in the current power system.

[0007] Optionally, in the fault recovery model, a quantum particle swarm is randomly generated; the state of each particle in the quantum particle swarm is initialized to obtain the initial position and initial velocity of the particle, wherein the initial position is randomly distributed in the solution space and is represented as X.i (0) = X min +rand()×(X max -X min ), where X min and X max Let represent the lower and upper bounds of the solution space, respectively. `rand()` is a function used to generate a random number between [0,1]. The initial velocity is a random number or zero. Based on the objective function in the fault recovery model, calculate the first fitness value of the particle. Use the first fitness value to update the individual historical optimal positions of all particles. Analyze the individual historical optimal positions of all particles to obtain the individual historical optimal position of the optimal particle. The optimal particle is the particle corresponding to the individual historical optimal position, and the individual historical optimal position of the optimal particle is the global optimal position. Based on the initial velocity, initial position, and quantum behavior of the particle, obtain the current position of the particle. Update the global optimal position of the particle based on its individual historical optimal position and current position. Based on the updated... The global optimal position is determined, and a second fitness value for that position is calculated. The first and second fitness values ​​are compared to determine the trend of the particle's fitness value. Based on this trend, the parameters of the adaptive quantum particle swarm optimization algorithm are determined to meet predetermined conditions. These predetermined conditions include at least the convergence curve of the objective function in the algorithm converging to the solution corresponding to the optimal fault position. The parameters include a convergence factor, an inertia weight parameter, and a learning factor. If the parameters do not meet the predetermined conditions, an adaptive strategy is used to dynamically adjust the parameters until the algorithm meets a termination condition, at which point the optimal fault position is output. The termination condition is either the number of iterations reaching a threshold or the second fitness value being less than or equal to a fitness value threshold.

[0008] Optionally, if the first fitness value of the particle's current position is better than the fitness value of the individual's historical best position, the individual's historical best position is updated to the particle's current position.

[0009] Optionally, if either the fitness value of the particle's current position or the fitness value of the individual's historical best position is better than the fitness value of the global best position, the global best position is updated to the best position of the two, which is the position with the smallest fitness value between the particle's current position and the individual's historical best position.

[0010] Optionally, if the fault type is a short-circuit fault, the fault recovery plan is determined to be fault isolation, and the fault recovery plan for fault isolation is executed according to the optimal fault location; if the fault type is an open-circuit fault, the fault recovery plan is determined to be power restoration, and the fault recovery plan for power restoration is executed according to the optimal fault location; if the fault type is a ground fault, the fault recovery plan is determined to be load transfer, and the fault recovery plan for load transfer is executed according to the optimal fault location.

[0011] Optionally, the objective function is Where, r ij x represents the line resistance from node i to node j of the power system. ij Let c represent the decision variable. k y represents the unit load cost of node k in the power system. k The indicator represents the operating status of node k in the power system after network reconfiguration; the constraints are voltage stability constraints, power balance constraints, and equipment operation limits. The voltage stability constraint means that the voltage of any node is maintained between the maximum and minimum voltages. The power balance constraint means that the total power input is the same as the total power output. The equipment operation limit means that the actual current between any two nodes is less than the maximum allowable current between the two nodes.

[0012] According to another aspect of this application, a fault recovery device for a power system is provided, comprising:

[0013] The acquisition unit acquires the fault characteristics in the current power system and inputs the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0014] The execution unit determines the corresponding fault recovery model based on the current fault type, solves the fault recovery model using an adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Based on the fault type and the optimal fault location, the execution unit determines a fault recovery scheme and executes the corresponding fault recovery scheme.

[0015] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program performs any of the methods described above.

[0016] According to another aspect of this application, an electronic device is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any of the methods described above.

[0017] The technical solution of this application first obtains the fault characteristics of the current power system and inputs these characteristics into a fault model to obtain the current fault type. Second, based on the current fault type, a corresponding fault recovery model is determined, and an adaptive quantum particle swarm optimization (IPS) algorithm is used to solve the fault recovery model to obtain the optimal fault location. Based on the fault type and the optimal fault location, a fault recovery scheme is determined and executed. Compared with existing automated fault detection methods based on sensor networks and smart meters, which lack accuracy in identifying abnormal states in complex power grid environments, the solution of this application utilizes the adaptive quantum particle swarm optimization algorithm to provide faster global search capabilities by considering the probability distribution of qubits and adaptively adjusts search parameters to adapt to the dynamic changes of complex networks. By searching for the globally optimal position of particles, the optimal fault location is obtained, thereby improving the accuracy of fault detection. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 A hardware structure block diagram of a mobile terminal for performing a power system fault recovery method according to an embodiment of this application is shown.

[0020] Figure 2 A flowchart illustrating a power system fault recovery method according to an embodiment of this application is shown.

[0021] Figure 3 A comparison graph is shown showing the response time of a power system fault recovery method according to an embodiment of this application and different algorithms for different fault types;

[0022] Figure 4 A comparison diagram is shown of the detection accuracy of a power system fault recovery method according to an embodiment of this application and different algorithms for different fault types.

[0023] Figure 5A comparison diagram is shown of the fault recovery method for a power system according to an embodiment of this application and the location errors of different algorithms for different fault types.

[0024] Figure 6 A comparison diagram is shown of the fault recovery method for a power system according to an embodiment of this application and the location time of different algorithms for different fault types.

[0025] Figure 7 A comparison diagram of the combined performance of a power system fault recovery method according to an embodiment of this application and different algorithms is shown.

[0026] Figure 8 A flowchart illustrating an implementation of a power system fault recovery method according to an embodiment of this application is shown.

[0027] Figure 9 A structural block diagram of a power system fault recovery device provided according to an embodiment of this application is shown. Detailed Implementation

[0028] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] As described in the background section, existing intelligent algorithms suffer from low accuracy in fault detection. To address this issue, embodiments of this application provide a fault recovery method for power systems.

[0032] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0033] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a power system fault recovery method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0034] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the device information display method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0035] This embodiment provides a fault recovery method for a power system that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0036] Figure 2 This is a flowchart of a power system fault recovery method according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0037] Step S201: Obtain the fault characteristics in the current power system and input the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0038] Specifically, a fault model refers to a model used to describe the possible faults and causes of a system or device. By establishing a fault model, we can better understand the problems the system may face, thereby taking corresponding preventive and remedial measures to improve the reliability and stability of the system.

[0039] Specifically, abnormal changes in power system data refer to data that show sudden or unexpected changes compared to normal operating conditions. These abnormal changes may include sudden increases or decreases in power load, voltage fluctuations, frequency anomalies, equipment failures, and other situations.

[0040] Step S202: Determine the corresponding fault recovery model based on the current fault type, solve the fault recovery model using the adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Determine the fault recovery scheme based on the fault type and the optimal fault location, and execute the corresponding fault recovery scheme.

[0041] Specifically, in the adaptive quantum particle swarm optimization algorithm, the position and velocity of the particles are dynamically adjusted according to the current search situation and the characteristics of the problem, in order to explore the search space more effectively and find the optimal solution. At the same time, the quantum state of the quantum particles is also dynamically adjusted according to the characteristics of the problem, in order to improve the search efficiency and convergence speed.

[0042] In the above embodiments, firstly, the fault characteristics of the current power system are acquired and input into the fault model to obtain the current fault type. Secondly, a corresponding fault recovery model is determined based on the current fault type, and an adaptive quantum particle swarm optimization (IPS) algorithm is used to solve the fault recovery model to obtain the optimal fault location. Based on the fault type and the optimal fault location, a fault recovery scheme is determined and executed. Compared with existing automated fault detection methods based on sensor networks and smart meters, which lack accuracy in identifying abnormal states in complex power grid environments, the scheme of this application utilizes the adaptive quantum particle swarm optimization algorithm to provide faster global search capabilities by considering the probability distribution of qubits and adaptively adjusting search parameters to adapt to the dynamic changes of complex networks. By searching for the globally optimal position of particles, the optimal fault location is obtained, thereby improving the accuracy of fault detection.

[0043] In one embodiment of this application, fault characteristics in the current power system are obtained, and these fault characteristics are input into a fault model to obtain the current fault type. This includes: obtaining current power system operating data; analyzing the operating data to obtain abnormal change data; and performing time-domain and / or frequency-domain analysis on the abnormal change data to obtain the fault characteristics in the current power system. In this method, various operating data of the current power system are collected, and by analyzing this data and comparing historical and real-time data, abnormal change data is identified. Time-domain and frequency-domain analysis is performed on the abnormal change data. Based on the results of the time-domain and frequency-domain analysis, possible fault characteristics in the current power system can be obtained. The fault types include short-circuit faults, open-circuit faults, and ground faults. The fault characteristics of a short-circuit fault are a sudden increase in current, a sudden drop in voltage, and high temperature. The fault characteristics of an open-circuit fault are current interruption, voltage imbalance, and changes in line reactive power. The fault characteristics of a ground fault are ground current, a sudden drop in voltage, and a change in the fault current path.

[0044] To further improve the accuracy of fault location after fault type detection, in one embodiment of this application, an adaptive quantum particle swarm optimization algorithm is used to solve the above-mentioned fault recovery model to obtain the optimal fault location. This includes: randomly generating a quantum particle swarm in the fault recovery model; initializing the state of each particle in the quantum particle swarm to obtain the initial position and initial velocity of the particles, wherein the initial positions are randomly distributed in the solution space and can be represented as X. i (0) = X min +rand()×(X max -X min ), where X min and X maxLet represent the lower and upper bounds of the solution space, respectively. `rand()` is a function used to generate a random number between [0,1]. The initial velocity is a random number or zero. Based on the objective function in the fault recovery model, calculate the first fitness value of the particle. Use the first fitness value to update the individual historical optimal position of all particles. Analyze the individual historical optimal positions of all particles to obtain the individual historical optimal position of the optimal particle. The optimal particle is the particle corresponding to the individual historical optimal position, and the individual historical optimal position of the optimal particle is the global optimal position. Based on the initial velocity, initial position, and quantum behavior of the particle, obtain the current position of the particle. Update the global optimal position of the particle based on its individual historical optimal position and current position. Based on the updated global optimal position... Calculate the second fitness value of the globally optimal position; compare the first fitness value and the second fitness value to determine the trend of the particle's fitness value; based on the trend of the particle's fitness value, determine whether the parameters of the adaptive quantum particle swarm optimization algorithm meet predetermined conditions. The predetermined conditions are at least that the convergence curve of the objective function in the adaptive quantum particle swarm optimization algorithm converges to the solution corresponding to the optimal fault position. The parameters include a convergence factor, an inertia weight parameter, and a learning factor. If the parameters of the adaptive quantum particle swarm optimization algorithm do not meet the predetermined conditions, use an adaptive strategy to dynamically adjust the parameters until the adaptive quantum particle swarm optimization algorithm meets the termination condition and outputs the optimal fault position. The termination condition is either the number of iterations reaching an iteration number threshold or the second fitness value being less than or equal to a fitness value threshold.

[0045] Specifically, before the algorithm begins, the position and velocity of each particle in the particle swarm are initialized. For each particle, its fitness at its current position is evaluated using a predefined fitness function. This fitness function, designed based on the requirements of fault detection and localization, is used to measure the quality of the solution. Afterward, the individual's historical best position P is updated. best and the global optimal position G best If the current particle's fitness is better than its historical best fitness, update its P. best If the current particle's fitness is better than the global optimal fitness, update G. bestDuring the iteration process, the particle's current position is updated according to quantum behavior and calculated based on the concept of qubit probability clouds. Simultaneously, the algorithm parameters are dynamically adjusted according to the number of iterations or changes in the particle's fitness. Finally, the algorithm checks whether it has reached the maximum number of iterations or the fitness has reached a preset threshold. If the conditions are met, the algorithm stops and outputs the current global position as the fault location. This allows for rapid and accurate fault location, obtaining the optimal fault location and further improving the accuracy and response time of fault detection.

[0046] like Figure 3 and Figure 4 As shown, by setting the parameters of the Adaptive Quantum Particle Swarm Optimization (A-QPSO) algorithm to the following values: particle swarm size of 50, maximum number of iterations of 200, quantum behavior parameters of [0.5, 1.0], initial convergence factor of 1.0, and final convergence factor of 0.1, the A-QPSO algorithm is compared with other algorithms. The comparison results of the response time and detection accuracy of A-QPSO, Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) under different fault types show that A-QPSO exhibits significant advantages in both response time and detection accuracy. Specifically, in scenarios involving short-circuit faults, open-circuit faults, and ground faults, the response times of A-QPSO are 0.8 seconds, 0.9 seconds, and 0.85 seconds, respectively, significantly better than PSO's 1.2 seconds, 1.3 seconds, and 1.25 seconds, and GA's 1.5 seconds, 1.6 seconds, and 1.55 seconds. In terms of detection accuracy, A-QPSO achieves 98%, 97%, and 96%, respectively, far exceeding PSO's 90%, 89%, and 88%, and GA's 85%, 84%, and 83%. These results demonstrate that A-QPSO exhibits superior performance in fault detection, enabling faster and more accurate detection of fault location and type. This advantage is primarily attributed to A-QPSO's adaptive parameter adjustment mechanism and the application of the quantum particle swarm optimization algorithm, which allows it to maintain optimal performance at different search stages, improving the algorithm's global search capability and convergence speed, and maintaining efficient global search capability and adaptability in diverse power grid environments. In summary, A-QPSO's superior performance in fault detection makes it an efficient and reliable fault detection algorithm, significantly improving the fault management capabilities and power supply reliability of the distribution network.

[0047] In another embodiment, the individual historical best position of all the particles is updated using the first fitness value, including: if the first fitness value of the current position of the particle is better than the fitness of the individual historical best position, the individual historical best position is updated to the current position of the particle. In this method, the particles continuously update their individual historical best positions based on their previous positions and fitness values, so that they can find the optimal solution more quickly in subsequent searches. By continuously updating the individual historical best positions, the adaptive quantum particle swarm optimization algorithm can search the solution space more effectively and find better solutions, thus better locating the individual historical best positions of the particles.

[0048] To better locate the optimal fault position and further optimize the accuracy and time of fault location in fault detection, in one embodiment of this application, the global optimal position of the particle is updated based on the individual historical optimal position and the current position of the particle. This includes updating the global optimal position to the optimal position between the current position and the individual historical optimal position if either the fitness value of the particle's current position or the fitness value of the individual historical optimal position is better than the fitness value of the global optimal position. The optimal position is the position with the smallest fitness value between the current position and the individual historical optimal position. This method prevents the particle swarm from getting trapped in local optima during the search process. By updating the particle's position, the particle searches along the direction of the global optimal position, thereby further improving the accuracy of fault location detection.

[0049] like Figure 5 and Figure 6 As shown, by setting the parameters of the Adaptive Quantum Particle Swarm Optimization (A-QPSO) algorithm to the following values: particle swarm size of 50, maximum number of iterations of 200, quantum behavior parameters of [0.5, 1.0], initial convergence factor of 1.0, and final convergence factor of 0.1, the positioning accuracy and positioning time of A-QPSO, PSO, and GA under different fault types were compared. The results show that A-QPSO also has significant advantages in both positioning accuracy and positioning time. In the scenarios of short-circuit fault, open-circuit fault, and ground fault, the positioning errors of A-QPSO are 0.5 m, 0.6 m, and 0.55 m, respectively, significantly lower than the corresponding positioning errors of PSO and GA; in terms of positioning time, the positioning times of A-QPSO are 1.0 s, 1.2 s, and 1.1 s, respectively, also significantly better than PSO's 1.8 s, 2.0 s, and 1.9 s, and GA's 2.5 s, 2.6 s, and 2.55 s. Therefore, Figure 5 and Figure 6 This also demonstrates that A-QPSO performs superiorly in fault location, enabling it to locate fault points more quickly and accurately.

[0050] Specifically, dynamically adjusting the algorithm parameters includes: adjusting the convergence factor to obtain the particle position change rate parameter, wherein the adjustment of the convergence factor varies according to the preset search behavior and the complexity of the fault problem; and adjusting the inertia weight parameter to obtain the particle position, wherein the particle position is represented as... Where u is a random number, w is the aforementioned inertia weight parameter, and the convergence factor β controls the balance between exploration and utilization in the algorithm, and its dynamic adjustment is expressed as: Where βmin and βmax are the minimum and maximum values ​​of the convergence factor, respectively, ensuring that the search process gradually transitions from extensive exploration to precise utilization; t represents the current iteration number; λ is the adjustment rate parameter, controlling the rate at which the convergence factor is adjusted, and its value depends on the expected search behavior and the complexity of the problem; the above learning factors are adjusted to obtain the movement direction of the particles. The learning factors include a first learning factor and a second learning factor. The first learning factor controls the movement direction of the particles towards the historical optimal position of the individual, and the second learning factor controls the movement direction of the particles towards the global optimal position. The learning factors are expressed as follows: Among them, c start c represents the parameters generated in the initial stage of the learning factor search mentioned above. end The method uses the parameters generated at the end of the learning factor search to adjust the algorithm parameters, making fault location more accurate and thus further improving the accuracy of fault detection.

[0051] In another embodiment, a fault recovery plan is determined based on the fault type and the optimal fault location, and the corresponding fault recovery plan is executed. This includes: if the fault type is a short-circuit fault, determining the fault recovery plan as fault isolation, and executing the fault isolation fault recovery plan according to the optimal fault location; if the fault type is an open-circuit fault, determining the fault recovery plan as power restoration, and executing the power restoration fault recovery plan according to the optimal fault location; if the fault type is a ground fault, determining the fault recovery plan as load transfer, and executing the load transfer fault recovery plan according to the optimal fault location. This method executes the corresponding fault recovery plan for each fault type to restore the fault.

[0052] To further improve fault recovery, in one embodiment of this application, the above objective function is: Where, r ij Let x represent the line resistance from node i to node j in the aforementioned power system. ij Let c represent the decision variable. k y represents the unit load cost of node k in the above power system.k The above-mentioned node k in the power system represents the operating status index after network reconfiguration; the above-mentioned constraints are voltage stability constraints, power balance constraints, and equipment operation limits. The above-mentioned voltage stability constraints mean that the voltage of any node is maintained between the maximum voltage and the minimum voltage. The above-mentioned power balance constraints mean that the total power input is the same as the total power output. The above-mentioned equipment operation limits mean that the actual current between any two of the above-mentioned nodes is less than the maximum allowable current between the two nodes.

[0053] Specifically, node i and node j in the objective function are two different nodes in the power system, and y in the objective function... k Let be the operational status index of node k after network reconstruction. Network reconstruction refers to dynamically adjusting the parameters and structure of the particle swarm optimization algorithm based on the characteristics and circumstances of the current problem to optimize the algorithm's performance and convergence speed. The operational status after network reconstruction depends on the specific adjustment strategy and the adjustment results, and generally includes: faster convergence speed, improved convergence accuracy, and enhanced stability.

[0054] Specifically, the constraints for distribution network fault recovery include: voltage stability constraints, power balance constraints, and equipment operation limitations. The voltage stability constraint is represented by V... min ≤V i ≤V max The power balance constraint is expressed as Among them, P load，j Given the load size of node j, the device operating limit is I. ij ≤I max,ij .

[0055] like Figure 7 As shown, by setting the parameters of the Adaptive Quantum Particle Swarm Optimization (A-QPSO) algorithm to the following values: particle swarm size of 50, maximum number of iterations of 200, quantum behavior parameters of [0.5, 1.0], initial convergence factor of 1.0, and final convergence factor of 0.1, the comprehensive performance of different algorithms is compared. A-QPSO significantly outperforms PSO, GA, and traditional methods in fault management and grid reconfiguration. In terms of response time, detection accuracy, positioning accuracy, positioning time, and power restoration time, A-QPSO scores 0.9, 0.98, 0.95, 0.92, and 0.91, respectively, all higher than PSO's 0.7, 0.9, 0.85, 0.75, and 0.78, GA's 0.6, 0.85, 0.8, 0.7, and 0.68, and traditional methods' 0.5, 0.75, 0.7, 0.65, and 0.6. This demonstrates the significant advantages of A-QPSO in overall performance, enabling it to detect and locate faults more accurately in a shorter time and restore power more quickly.

[0056] To enable those skilled in the art to better understand the technical solution of this application, the implementation process of the power system fault recovery method of this application will be described in detail below with reference to specific embodiments.

[0057] This embodiment relates to a specific fault recovery method for a power system, such as... Figure 8 As shown, it includes the following steps:

[0058] Step S1: Analyze the abnormal change data of the power system to obtain the current fault characteristics of the power system;

[0059] Step S2: Input the above fault characteristics into the fault model to obtain the current fault type;

[0060] Step S3: Determine the corresponding fault recovery model based on the current fault type;

[0061] Step S4: In the above fault recovery model, a quantum particle swarm is randomly generated, and the position and velocity of each particle are initialized to obtain the initial position and initial velocity of the particles;

[0062] Step S5: Calculate the first fitness value of the particles according to the objective function in the above fault recovery model, and update the individual historical best position of all particles using the first fitness value.

[0063] Step S6: By analyzing the individual historical best positions of all the above particles, obtain the individual historical best position of the best particle.

[0064] Step S7: Based on the initial velocity of the above-mentioned particle row number, the above-mentioned initial position, and quantum behavior, obtain the current position of the above-mentioned particle;

[0065] Step S8: Based on the individual historical best position of the particle and the current position of the particle, update the global best position of the particle and calculate the second fitness value of the global best position of the particle.

[0066] Step S9: Compare the first fitness value and the second fitness value to analyze the trend of the fitness value of the particle, and determine whether the algorithm parameters are appropriate based on the change of the fitness value of the particle.

[0067] Step S10: If the above algorithm parameters are not suitable, use an adaptive strategy to dynamically adjust the above algorithm parameters until the above adaptive quantum particle swarm algorithm meets the termination condition and outputs the above optimal fault location.

[0068] Step S11: Determine the fault recovery plan based on the above fault type and the above optimal fault location, and execute the corresponding fault recovery plan.

[0069] It should be noted that the steps shown in the flowchart in 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 may be executed in a different order than that shown here.

[0070] This application also provides a power system fault recovery device. It should be noted that the power system fault recovery device of this application can be used to execute the power system fault recovery method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0071] The following describes the power system fault recovery device provided in the embodiments of this application.

[0072] Figure 9 This is a schematic diagram of a power system fault recovery device according to an embodiment of this application. Figure 9 As shown, the device includes:

[0073] The acquisition unit 10 is used to acquire the fault characteristics in the current power system and input the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0074] Specifically, a fault model refers to a model used to describe the possible faults and causes of a system or device. By establishing a fault model, we can better understand the problems the system may face, thereby taking corresponding preventive and remedial measures to improve the reliability and stability of the system.

[0075] Specifically, abnormal changes in power system data refer to data that show sudden or unexpected changes compared to normal operating conditions. These abnormal changes may include sudden increases or decreases in power load, voltage fluctuations, frequency anomalies, equipment failures, and other situations.

[0076] The execution unit 20 is used to determine the corresponding fault recovery model according to the current fault type, solve the fault recovery model using the adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, the optimal fault location being the global optimal location of the particles, the fault recovery model including the objective function and constraints, determine the fault recovery scheme based on the fault type and the optimal fault location, and execute the corresponding fault recovery scheme.

[0077] Specifically, in the adaptive quantum particle swarm optimization algorithm, the position and velocity of the particles are dynamically adjusted according to the current search situation and the characteristics of the problem, in order to explore the search space more effectively and find the optimal solution. At the same time, the quantum state of the quantum particles is also dynamically adjusted according to the characteristics of the problem, in order to improve the search efficiency and convergence speed.

[0078] In the above embodiments, firstly, the fault characteristics of the current power system are acquired and input into the fault model to obtain the current fault type. Secondly, a corresponding fault recovery model is determined based on the current fault type, and an adaptive quantum particle swarm optimization (IPS) algorithm is used to solve the fault recovery model to obtain the optimal fault location. Based on the fault type and the optimal fault location, a fault recovery scheme is determined and executed. Compared with existing automated fault detection methods based on sensor networks and smart meters, which lack accuracy in identifying abnormal states in complex power grid environments, the scheme of this application utilizes the adaptive quantum particle swarm optimization algorithm to provide faster global search capabilities by considering the probability distribution of qubits and adaptively adjusting search parameters to adapt to the dynamic changes of complex networks. By searching for the globally optimal position of particles, the optimal fault location is obtained, thereby improving the accuracy of fault detection.

[0079] In one embodiment of this application, the acquisition unit includes a first acquisition module, a first analysis module, and a second analysis module. The first acquisition module acquires current power system operating data; the first analysis module analyzes the operating data to obtain abnormal change data; and the second analysis module performs time-domain and / or frequency-domain analysis on the abnormal change data to obtain the aforementioned fault characteristics in the current power system. In this scheme, by collecting various operating data of the current power system, analyzing this data, comparing historical and real-time data, identifying abnormal change data, and performing time-domain and frequency-domain analysis on the abnormal change data, the possible fault characteristics in the current power system can be obtained based on the results of the time-domain and frequency-domain analysis. The fault types include short-circuit faults, open-circuit faults, and ground faults. The fault characteristics of short-circuit faults include sudden current increases, voltage drops, and high temperatures; the fault characteristics of open-circuit faults include current interruptions, voltage imbalances, and changes in line reactive power; and the fault characteristics of ground faults include ground current, voltage drops, and changes in the fault current path.

[0080] To further improve the accuracy of fault location during fault detection after fault type detection, in one embodiment of this application, the execution unit includes a generation module, an initialization module, a first calculation module, a first update module, a second acquisition module, a second calculation module, a second update module, a third calculation module, a first judgment module, a second judgment module, and an adjustment module. The generation module is used to randomly generate a quantum particle swarm in the aforementioned fault recovery model; the initialization module is used to initialize the state of each particle in the quantum particle swarm, obtaining the initial position and initial velocity of the particles. The initial positions are randomly distributed in the solution space and can be represented as X. i (0) = X min +rand()×(X max -X min ), where X min and X maxLet represent the lower and upper bounds of the solution space, respectively. `rand()` is a function used to generate a random number between [0,1]. The initial velocity is a random number or zero. The first calculation module calculates the first fitness value of the particle based on the objective function in the fault recovery model. The first update module updates the individual historical optimal positions of all particles using the first fitness value. The second acquisition module analyzes the individual historical optimal positions of all particles to obtain the individual historical optimal position of the optimal particle. The optimal particle is the particle corresponding to the individual historical optimal position, and the individual historical optimal position of the optimal particle is the global optimal position. The second calculation module obtains the current position of the particle based on its initial velocity, initial position, and quantum behavior. The second update module updates the global optimal position of the particle based on its individual historical optimal position and current position. The third calculation module... The first judgment module is used to calculate the second fitness value of the particle's global optimal position based on the updated global optimal position; the second judgment module is used to compare the first fitness value and the second fitness value to determine the trend of the particle's fitness value; the second judgment module is used to determine whether the parameters of the adaptive quantum particle swarm optimization algorithm meet predetermined conditions based on the trend of the particle's fitness value, the predetermined conditions being at least that the convergence curve of the objective function in the adaptive quantum particle swarm optimization algorithm converges to the solution corresponding to the optimal fault position, the parameters including convergence factor, inertia weight parameter and learning factor; the adjustment module is used to dynamically adjust the parameters using an adaptive strategy when the parameters of the adaptive quantum particle swarm optimization algorithm do not meet the predetermined conditions, until the adaptive quantum particle swarm optimization algorithm meets the termination condition and outputs the optimal fault position, the termination condition being one of the iteration number reaching a threshold and the second fitness value being less than or equal to the fitness value threshold.

[0081] Specifically, before the algorithm begins, the position and velocity of each particle in the particle swarm are initialized. For each particle, its fitness at its current position is evaluated using a predefined fitness function. This fitness function, designed based on the requirements of fault detection and localization, is used to measure the quality of the solution. Afterward, the individual's historical best position P is updated. best and the global optimal position G best If the current particle's fitness is better than its historical best fitness, update its P. best If the current particle's fitness is better than the global optimal fitness, update G. bestDuring the iteration process, the particle's current position is updated according to quantum behavior and calculated based on the concept of qubit probability clouds. Simultaneously, the algorithm parameters are dynamically adjusted according to the number of iterations or changes in the particle's fitness. Finally, the algorithm checks whether it has reached the maximum number of iterations or the fitness has reached a preset threshold. If the conditions are met, the algorithm stops and outputs the current global position as the fault location. This allows for rapid and accurate fault location, obtaining the optimal fault location and further improving the accuracy and response time of fault detection.

[0082] In another embodiment, the first update module includes a first update submodule, wherein the first update submodule is used to update the individual's historical best position to the particle's current position if the first fitness value of the particle's current position is better than the fitness of the individual's historical best position. In this scheme, the particle continuously updates its individual historical best position based on its previous position and fitness value so that it can find the optimal solution more quickly in subsequent searches. By continuously updating the individual historical best position, the adaptive quantum particle swarm optimization algorithm can search the solution space more effectively and find better solutions, thus better locating the individual historical best position of the particle.

[0083] To better locate the optimal fault position and further optimize the accuracy and time of fault location in fault detection, in one embodiment of this application, the second update module includes a second update submodule. The second update submodule is used to update the global optimal position to the optimal position between the current fitness value of the particle and the fitness value of the individual's historical best position, provided that one of these is better than the fitness value of the global optimal position. The optimal position is the position with the best fitness value between the current position of the particle and the individual's historical best position. This scheme prevents the particle swarm from getting trapped in local optima during the search process. By updating the particle's position, the particle searches along the direction of the global optimal position, thereby further improving the accuracy of fault location detection.

[0084] Specifically, dynamically adjusting the algorithm parameters includes: adjusting the convergence factor to obtain the particle position change rate parameter, wherein the adjustment of the convergence factor varies according to the preset search behavior and the complexity of the fault problem; and adjusting the inertia weight parameter to obtain the particle position, wherein the particle position is represented as... Where u is a random number, and w is the aforementioned inertia weight parameter; the learning factor is adjusted to obtain the movement direction of the particle. The learning factor includes a first learning factor and a second learning factor. The first learning factor controls the movement direction of the particle towards the individual's historical optimal position, and the second learning factor controls the movement direction of the particle towards the global optimal position. The learning factor is expressed as follows: Among them, c start c represents the parameters generated in the initial stage of the learning factor search mentioned above. end The method uses the parameters generated at the end of the learning factor search to adjust the algorithm parameters, making fault location more accurate and thus further improving the accuracy of fault detection.

[0085] In another embodiment, the execution unit further includes a first execution module, a second execution module, and a third execution module. The first execution module is configured to determine, in the case of a short-circuit fault, that the fault recovery scheme is fault isolation, and execute the fault recovery scheme of fault isolation according to the optimal fault location. The second execution module is configured to determine, in the case of an open-circuit fault, that the fault recovery scheme is power restoration, and execute the fault recovery scheme of power restoration according to the optimal fault location. The third execution module is configured to determine, in the case of a ground fault, that the fault recovery scheme is load transfer, and execute the fault recovery scheme of load transfer according to the optimal fault location. This scheme executes the corresponding fault recovery scheme for each fault type, thereby restoring the fault.

[0086] To further improve fault recovery, in one embodiment of this application, the above objective function is: Where, r ij Let x represent the line resistance from node i to node j in the aforementioned power system. ij Let c represent the decision variable. k y represents the unit load cost of node k in the above power system. k The above-mentioned node k in the power system represents the operating status index after network reconfiguration; the above-mentioned constraints are voltage stability constraints, power balance constraints, and equipment operation limits. The above-mentioned voltage stability constraints mean that the voltage of any node is maintained between the maximum voltage and the minimum voltage. The above-mentioned power balance constraints mean that the total power input is the same as the total power output. The above-mentioned equipment operation limits mean that the actual current between any two of the above-mentioned nodes is less than the maximum allowable current between the two nodes.

[0087] Specifically, node i and node j in the objective function are two different nodes in the power system, and y in the objective function... k Let be the operational status index of node k after network reconstruction. Network reconstruction refers to dynamically adjusting the parameters and structure of the particle swarm optimization algorithm based on the characteristics and circumstances of the current problem to optimize the algorithm's performance and convergence speed. The operational status after network reconstruction depends on the specific adjustment strategy and the adjustment results, and generally includes: faster convergence speed, improved convergence accuracy, and enhanced stability.

[0088] Specifically, the constraints for distribution network fault recovery include: voltage stability constraints, power balance constraints, and equipment operation limitations. The voltage stability constraint is represented by V... min ≤V i ≤V max The power balance constraint is expressed as Equipment operation is limited to I ij ≤I max,ij .

[0089] It should be noted that the steps shown in the flowchart in 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 may be executed in a different order than that shown here.

[0090] The aforementioned power system fault recovery device includes a processor and a memory. The acquisition unit, execution unit, etc., are all stored as program units in the memory, and the processor executes these program units to achieve the corresponding functions. All of the above modules reside in the same processor; alternatively, the modules may be located in different processors in any combination.

[0091] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured; adjusting kernel parameters can address the issue of low accuracy in fault detection methods.

[0092] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0093] This invention provides a computer-readable storage medium including a stored program, wherein, when the program runs, it controls the device containing the computer-readable storage medium to execute the power system fault recovery method, the method comprising:

[0094] Step S201: Obtain the fault characteristics in the current power system and input the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0095] Step S202: Determine the corresponding fault recovery model based on the current fault type, solve the fault recovery model using the adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Determine the fault recovery scheme based on the fault type and the optimal fault location, and execute the corresponding fault recovery scheme.

[0096] This invention provides a processor for running a program, wherein the program executes the power system fault recovery method, the method comprising:

[0097] Step S201: Obtain the fault characteristics in the current power system and input the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0098] Step S202: Determine the corresponding fault recovery model based on the current fault type, solve the fault recovery model using the adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Determine the fault recovery scheme based on the fault type and the optimal fault location, and execute the corresponding fault recovery scheme.

[0099] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps:

[0100] Step S201: Obtain the fault characteristics in the current power system and input the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0101] Step S202: Determine the corresponding fault recovery model based on the current fault type, solve the fault recovery model using the adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Determine the fault recovery scheme based on the fault type and the optimal fault location, and execute the corresponding fault recovery scheme.

[0102] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0103] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps:

[0104] Step S201: Obtain the fault characteristics in the current power system and input the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system.

[0105] Step S202: Determine the corresponding fault recovery model based on the current fault type, solve the fault recovery model using the adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Determine the fault recovery scheme based on the fault type and the optimal fault location, and execute the corresponding fault recovery scheme.

[0106] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0107] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0109] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0111] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0112] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0113] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic cassette tape or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0114] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0115] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0116] In the above embodiments, firstly, the fault characteristics of the current power system are acquired and input into the fault model to obtain the current fault type. Secondly, a corresponding fault recovery model is determined based on the current fault type, and an adaptive quantum particle swarm optimization (IPS) algorithm is used to solve the fault recovery model to obtain the optimal fault location. Based on the fault type and the optimal fault location, a fault recovery scheme is determined and executed. Compared with existing automated fault detection methods based on sensor networks and smart meters, which lack accuracy in identifying abnormal states in complex power grid environments, the scheme of this application utilizes the adaptive quantum particle swarm optimization algorithm to provide faster global search capabilities by considering the probability distribution of qubits and adaptively adjusting search parameters to adapt to the dynamic changes of complex networks. By searching for the globally optimal position of particles, the optimal fault location is obtained, thereby improving the accuracy of fault detection.

[0117] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A fault recovery method for a power system, characterized in that, include: The fault characteristics in the current power system are obtained and input into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system. Based on the current fault type, a corresponding fault recovery model is determined. An adaptive quantum particle swarm optimization algorithm is used to solve the fault recovery model to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Based on the fault type and the optimal fault location, a fault recovery scheme is determined and executed. The fault recovery model is solved using an adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, including: In the fault recovery model, a quantum particle swarm is randomly generated; Initialize the state of each particle in the quantum particle swarm to obtain the initial position and initial velocity of the particle. The initial positions are randomly distributed in the solution space, denoted as... ,in, and These represent the lower and upper bounds of the solution space, respectively. The initial velocity is a function used to generate a random number between [0,1], where the initial velocity is a random number or zero; Calculate the first fitness value of the particle based on the objective function in the fault recovery model; Using the first fitness value, update the individual historical best position of all the particles; Analyze the individual historical best position of all the particles to obtain the individual historical best position of the best particle. The best particle is the particle corresponding to the individual historical best position, and the individual historical best position of the best particle is the global best position. Based on the initial velocity, initial position, and quantum behavior of the particle, the current position of the particle is obtained; Update the global optimal position of the particle based on its individual historical optimal position and its current position. Based on the updated global optimal position, calculate the second fitness value of the global optimal position; By comparing the first fitness value and the second fitness value, the trend of the change in the fitness value of the particle can be determined; Based on the changing trend of the fitness value of the particle, it is determined whether the parameters of the adaptive quantum particle swarm algorithm meet the predetermined conditions. The predetermined conditions are at least that the convergence curve of the objective function in the adaptive quantum particle swarm algorithm converges to the solution corresponding to the optimal fault location. The parameters include convergence factor, inertia weight parameter and learning factor. If the parameters of the adaptive quantum particle swarm optimization algorithm do not meet the predetermined conditions, the parameters are dynamically adjusted using an adaptive strategy until the adaptive quantum particle swarm optimization algorithm meets the termination condition and outputs the optimal fault location. The termination condition is one of the following: the number of iterations reaches the iteration number threshold and the second fitness value is less than or equal to the fitness value threshold.

2. The power system fault recovery method according to claim 1, characterized in that, Obtain the fault characteristics of the current power system and input these fault characteristics into the fault model to obtain the current fault type, including: Obtain current power system operating data; The abnormal change data is obtained by analyzing the operational data; Time-domain and / or frequency-domain analysis is performed on the abnormal change data to obtain the fault characteristics in the current power system.

3. The power system fault recovery method according to claim 1, characterized in that, Using the first fitness value, update the individual historical best position of all the particles, including: If the fitness value of the particle's current position is less than or equal to the fitness value of the individual's historical best position, then the individual's historical best position is updated to the particle's current position.

4. The power system fault recovery method according to claim 1, characterized in that, Based on the particle's individual historical best position and the particle's current position, update the particle's global best position, including: If either the fitness value of the particle's current position or the fitness value of the individual's historical best position is better than the fitness value of the global best position, then the global best position is updated to the best position of the two, which is the position with the smallest fitness value between the particle's current position and the individual's historical best position.

5. The power system fault recovery method according to claim 1, characterized in that, Based on the fault type and the optimal fault location, a fault recovery plan is determined and executed, including: In the case where the fault type is a short-circuit fault, the fault recovery plan is determined to be fault isolation, and the fault recovery plan of the fault isolation is executed according to the optimal fault location; In the case where the fault type is an open circuit fault, the fault recovery plan is determined to be power restoration, and the fault recovery plan for power restoration is executed according to the optimal fault location; In the case where the fault type is a ground fault, the fault recovery plan is determined to be load transfer, and the fault recovery plan of load transfer is executed according to the optimal fault location.

6. The power system fault recovery method according to any one of claims 1 to 5, characterized in that, The objective function is: ,in, x represents the line resistance from node i to node j of the power system. ij Represents decision variables, This represents the unit load cost of node k in the power system. This represents the operating status index of node k in the power system after network reconfiguration; The constraints are voltage stability constraints, power balance constraints, and device operation limits. The voltage stability constraint means that the voltage of any node is maintained between the maximum and minimum voltages. The power balance constraint means that the total power input is the same as the total power output. The device operation limit means that the actual current between any two nodes is less than the maximum allowable current between the two nodes.

7. A power system fault recovery device applying the power system fault recovery method according to any one of claims 1 to 6, characterized in that, include: The acquisition unit acquires the fault characteristics in the current power system and inputs the current fault characteristics into the fault model to obtain the current fault type. The fault model is trained using multiple sets of historical data. Each set of historical data includes historical fault characteristics and corresponding historical fault types. The fault characteristics are abnormal change data of the power system. The execution unit determines the corresponding fault recovery model based on the current fault type, solves the fault recovery model using an adaptive quantum particle swarm optimization algorithm to obtain the optimal fault location, which is the global optimal location of the particles. The fault recovery model includes an objective function and constraints. Based on the fault type and the optimal fault location, the execution unit determines a fault recovery scheme and executes the corresponding fault recovery scheme.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the power system fault recovery method according to any one of claims 1 to 6.

9. An electronic device, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing a fault recovery method for a power system according to any one of claims 1 to 6.

Images