A power distribution network self-healing method and system based on network scada

Abstract

The application discloses a power distribution network self-healing method and system based on network scada, comprising: data collection according to the scada system, and preprocessing; feature extraction on the preprocessed data, and abnormal situation detection by using an optimized LOF algorithm; fault isolation, power grid topology reconstruction, and realization of the self-healing of the power distribution network.The power distribution network self-healing method and system based on network scada provided by the application can improve the accuracy and efficiency of fault detection by feature extraction on data, introduction of the optimized LOF algorithm, and abnormality detection in combination with a genetic algorithm, and can quickly identify fault points.The automatic isolation of faults is realized through a SCADA system and an automatic switch, and a power grid reconstruction scheme is optimized in combination with a linear programming and an ant colony algorithm, so that load balance is ensured, and the reliability and stability of the power grid are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power automation, in particular to a power distribution network self-healing method and system based on a distribution network SCADA. BACKGROUND

[0002] With the development of smart grid technology, the automation and intelligence of power distribution networks are continuously improving, and SCADA (Supervisory Control and Data Acquisition) has been widely used in power distribution networks. SCADA systems monitor and control the operation of power grids in real time through sensors and communication networks, providing a large amount of operation data and laying a foundation for intelligent management and maintenance of power grids. In the prior art, the self-healing method of power distribution networks mainly relies on manual operation and pre-set rules, and realizes fault isolation and power grid reconstruction through the operation of switches and circuit breakers. However, the traditional self-healing method has problems such as slow response speed and low intelligence, which is difficult to meet the demand of modern power grids for fast and accurate fault handling.

[0003] At present, the research and application of power distribution network self-healing technology have made certain progress, mainly including automatic switch operation, fault detection and positioning, load transfer, etc. These technologies improve the efficiency and accuracy of fault handling through automation equipment and intelligent algorithms. However, the existing technology still has some deficiencies, such as the accuracy and efficiency of the fault detection algorithm need to be improved, the optimization method of power grid reconstruction is relatively simple, and it is difficult to cope with complex power grid topology and variable load conditions. At the same time, the existing technology lacks flexibility in data processing and analysis, and it is difficult to fully utilize the rich data provided by the SCADA system for intelligent decision-making. Therefore, it is of great application value and practical significance to develop a power distribution network self-healing method based on the SCADA system, and use optimization algorithms to improve the efficiency and accuracy of fault detection and power grid reconstruction. SUMMARY

[0004] In view of the above problems, the present application is proposed.

[0005] Therefore, the technical problem solved by the present application is that the fault detection algorithm in the prior art usually has problems of insufficient accuracy and efficiency. The traditional fault isolation and power grid reconstruction method relies on pre-set rules and manual operation, and has slow response speed, which is difficult to cope with complex power grid topology.

[0006] To solve the above technical problems, the present application provides the following technical scheme: a power distribution network self-healing method based on a distribution network SCADA, comprising: collecting data according to the SCADA system, and preprocessing.

[0007] Feature extraction is performed on the preprocessed data, and an optimized LOF algorithm is used to detect abnormal conditions.

[0008] Carrying out fault isolation, reconstructing power grid topology, realizing self-healing of distribution network.

[0009] As a preferred scheme of the distribution network SCADA-based power distribution network self-healing method, wherein: the data collection according to the SCADA system, the preprocessing includes that the SCADA system collects the operation data of the distribution network in real time through sensors and instruments, transmits the data through a communication network, and the collected data includes voltage, current, frequency, power, phase angle and power quality.

[0010] The data preprocessing includes data normalization, which is expressed as:

[0011]

[0012] Wherein, x i ′ represents the normalized data, x i represents the original data, x min represents the minimum value in the data, x max represents the maximum value in the data.

[0013] As a preferred scheme of the distribution network SCADA-based power distribution network self-healing method, wherein: the feature extraction of the preprocessed data includes voltage feature extraction, which is expressed as:

[0014]

[0015] Wherein, T V represents the voltage feature, V max represents the maximum value of the voltage, V min represents the minimum value of the voltage, V arg represents the average value of the voltage.

[0016] The current feature extraction is expressed as:

[0017]

[0018] Wherein, T I represents the current feature, I rms represents the root mean square value of the current, I peak represents the peak value of the current.

[0019] The frequency feature extraction formula is expressed as:

[0020] T f =f std

[0021] Wherein, T f represents the frequency feature, f std represents the standard deviation of the frequency.

[0022] Power feature extraction is expressed as:

[0023]

[0024] wherein T P represents the active power feature, P max represents the active power maximum value, P min represents the active power minimum value, P arg represents the active power average value. T Q represents the reactive power feature, Q max represents the reactive power maximum value, Q min represents the reactive power minimum value, Q arg represents the reactive power average value.

[0025] Phase angle feature extraction is expressed as:

[0026] T θ = cos(θ avg )

[0027] wherein T θ represents the phase angle feature, θ avg represents the phase angle average value.

[0028] Power quality feature extraction is expressed as:

[0029]

[0030] wherein T PQ represents the power quality feature, H total represents the total harmonic distortion, V rms represents the root mean square value of voltage.

[0031] As a preferred scheme of the power distribution network self-healing method based on distribution network SCADA, wherein: the abnormal situation is detected by using the optimized LOF algorithm, which includes fusing features, expressed as:

[0032]

[0033] wherein F i represents the normalized feature, T i represents the value of feature i, μ i represents the mean value of feature i, σ i represents the standard deviation of feature i.

[0034] The LOF algorithm calculation formula is expressed as:

[0035]

[0036] wherein lrd k(p) denotes the local reachable density, denoted as:

[0037]

[0038] where p denotes the point to be detected, N k (p) denotes the k-nearest neighbor set of point p, reach_dist k (p, o) denotes the reachable distance, reach_dist k (p, o) = max{dist(p, o), min_dist k (o)}. dist k (p, o) denotes the distance between points p and o, min_dist k (o) denotes the k-th nearest neighbor distance of point o to its k-nearest neighbors.

[0039] The genetic algorithm is used to optimize the calculation process of the LOF algorithm, improve the accuracy and computational efficiency of the algorithm, and the genetic algorithm includes initialization, fitness calculation, selection of part of the individuals as parents of the next generation according to the fitness, crossover operation on the selected individuals to generate new individuals, mutation to introduce randomness, and iteration.

[0040] The initialization includes randomly generating an initial population, and each individual represents a local reachable density calculation scheme. The initial population is {C1, C2,..., C N}, and each individual Ci contains a parameter set {α i , β i}. The fitness calculation includes calculating the local reachable density of each individual in the current population based on the formula of the local anomaly factor, and comparing with other individuals. The fitness function is represented as:

[0041]

[0042] where f(C i ) denotes the fitness function, represents the LOF value calculated based on the parameters of Ci.

[0043] The optimized parameters are obtained through the genetic algorithm, α represents the voltage difference adjustment factor determined by the genetic algorithm, and β represents the current difference adjustment factor determined by the genetic algorithm. The distance calculation formula after optimization according to the optimized parameters is represented as:

[0044]

[0045] where dist opt (p, o) denotes the physical distance between points p and o, V p denotes the voltage of point p, V o denotes the voltage of point o, and I pThe current of point p, I o The current of point o.

[0046] The optimized local reachable density according to the optimization parameter is expressed as:

[0047]

[0048] The LOF value of each point is calculated using the optimized local reachable density, and whether it is an abnormal point is judged, expressed as:

[0049]

[0050] Wherein, The optimized reachable distance is expressed as:

[0051] As a preferred scheme of the power distribution network self-healing method based on the distribution network SCADA, wherein: the abnormal situation detected by the optimized LOF algorithm further comprises: combining the fused features and the optimized LOF algorithm, and comprehensively calculating the abnormal score, expressed as:

[0052]

[0053] Wherein, A p The comprehensive abnormal score of point p is expressed as: N represents the number of features, F i The normalized value of feature i is expressed as: LOF k The abnormal score of point p is expressed as: λ i The weight of feature i is expressed as:

[0054] The comprehensive abnormal score A p When A>0.5, the point is judged as an abnormal situation. Otherwise, it is a normal situation.

[0055] As a preferred scheme of the power distribution network self-healing method based on the distribution network SCADA, wherein: the fault isolation comprises: the points with comprehensive abnormal score A p >0.5 are isolated, the SCADA system sends instructions to the automatic switch, and the automatic switch disconnects the connection with the fault device and line, and cuts off the power supply of the fault area.

[0056] As a preferred scheme of the power distribution network self-healing method based on the distribution network SCADA, wherein: the reconstruction of the power grid topology comprises: the target is to minimize the load imbalance and the reconstruction cost, and the power grid reconstruction objective function and constraint condition based on linear programming are expressed as:

[0057]

[0058] subject to

[0059]

[0060]

[0061]

[0062] where, denotes the load of the ith line after reconfiguration, denotes the load of the ith line before reconfiguration, C j denotes the cost of the jth reconfiguration operation, x j denotes the binary variable of the jth reconfiguration operation, 1 indicates that the reconfiguration operation is performed, and 0 indicates that the reconfiguration operation is not performed. Capacity i denotes the capacity of the ith line, denotes the load of the kth transformer after reconfiguration, Capacity k denotes the capacity of the kth transformer.

[0063] The method of optimizing power grid reconfiguration based on linear programming by introducing ant colony algorithm is introduced, the ant colony is initialized, and the initial pheromone concentration is set. On the power grid topology, each line and transformer is allocated an initial pheromone concentration τ0.

[0064] In the power grid reconfiguration problem, the selection of each line and transformer constitutes a solution space, and each ant selects a path according to the pheromone concentration τ and the heuristic information η. The selection probability P ij is represented as:

[0065]

[0066] where, τ ij denotes the pheromone concentration of line i to j, η ij denotes the heuristic information of line i to j, including line capacity and current load. allowed denotes the set of paths available to ants, α' denotes the pheromone weight, and β' denotes the heuristic information weight.

[0067] After each iteration, the pheromone concentration is updated according to the path selection of the ants, which is represented as:

[0068]

[0069] where, ρ denotes the pheromone evaporation coefficient, denotes the amount of pheromone released by the kth ant on path i to j.

[0070] The path selection and pheromone update process is repeated until a good solution is obtained, and the optimal reconfiguration scheme is determined, including the switches and circuit breakers that need to be operated, as well as the load transfer path.

[0071] A power distribution network self-healing system based on network configuration SCADA, characterized in that it comprises,

[0072] The data acquisition module acquires data according to the SCADA system and performs preprocessing.

[0073] The abnormality detection module extracts features from the preprocessed data and detects abnormal conditions using an optimized LOF algorithm.

[0074] The self-healing module isolates faults, reconstructs the power grid topology, and realizes self-healing of the power distribution network.

[0075] A computer device comprising a memory and a processor, the memory storing a computer program, and the processor executing the computer program to realize the steps of the method described above.

[0076] A computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to realize the steps of the method described above.

[0077] The beneficial effects of the present application: the present application extracts features from data and introduces an optimized LOF algorithm combined with a genetic algorithm for anomaly detection, significantly improving the accuracy and efficiency of fault detection, and can quickly identify fault points. Through the SCADA system and automatic switches, the automatic isolation of faults is realized, and combined with linear programming and ant colony algorithm, the power grid reconstruction scheme is optimized to ensure load balancing and improve the reliability and stability of the power grid. BRIEF DESCRIPTION OF DRAWINGS

[0078] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor. Among them:

[0079] Figure 1 The overall flowchart of a power distribution network self-healing method and system based on network configuration SCADA is provided for the first embodiment of the present application. DETAILED DESCRIPTION

[0080] In order to make the above-mentioned purposes, features and advantages of the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the present application.

[0081] Embodiment 1, reference Figure 1 For an embodiment of the present application, a power distribution network self-healing method based on network scada is provided, comprising:

[0082] S1: data collection according to scada system, pretreatment.

[0083] SCADA system collects the operation data of power distribution network in real time through sensors and instruments, transmits data through communication network, and the collected data includes voltage, current, frequency, power, phase angle and power quality.

[0084] Data preprocessing includes data normalization, which is expressed as:

[0085]

[0086] Wherein, x i ′ represents the normalized data, x i represents the original data, x min represents the minimum value in the data, x max represents the maximum value in the data.

[0087] S2: feature extraction is carried out on the pretreated data, and optimized LOF algorithm is used to detect abnormal situation.

[0088] Voltage feature extraction is expressed as:

[0089]

[0090] Wherein, T V represents voltage feature, V max represents voltage maximum value, V min represents voltage minimum value, V arg represents voltage average value.

[0091] Current feature extraction is expressed as:

[0092]

[0093] Wherein, T I represents current feature, I rms represents the root mean square value of current, I peak represents the peak value of current.

[0094] The formula of frequency feature extraction is expressed as:

[0095] T f = f std

[0096] Wherein, T f represents frequency feature, f stdStandard deviation of frequency.

[0097] Power feature extraction is represented as:

[0098]

[0099] where T P represents the active power feature, P max represents the active power maximum value, P min represents the active power minimum value, P arg represents the active power average value. T Q represents the reactive power feature, Q max represents the reactive power maximum value, Q min represents the reactive power minimum value, Q arg represents the reactive power average value.

[0100] Phase angle feature extraction is represented as:

[0101] T θ = cos(θ avg )

[0102] where T θ represents the phase angle feature, θ avg represents the phase angle average value.

[0103] Power quality feature extraction is represented as:

[0104]

[0105] where T PQ represents the power quality feature, H total represents the total harmonic distortion, V rms represents the root mean square value of voltage.

[0106] Fusion of features is represented as:

[0107]

[0108] where F i represents the normalized feature, T i represents the value of feature i, μ i represents the mean value of feature i, σ i represents the standard deviation of feature i.

[0109] The LOF algorithm calculation formula is represented as:

[0110]

[0111] where lrd k (p) represents the local reachable density, represented as:

[0112]

[0113] where p represents the point to be detected, N k (p) represents the k-nearest neighbors set of point p, reach_dist k (p,o) represents the reachable distance, reach_dist k (p,o) = max{dist(p,o), min_dist k (o)}. dist k (p,o) represents the distance between point p and o, min_dist k (o) represents the kth nearest neighbor distance of point o to its k-nearest neighbors.

[0114] The genetic algorithm includes initialization, fitness calculation, selecting part of individuals as parents of the next generation according to fitness, performing crossover operation on the selected individuals to generate new individuals, introducing randomness through mutation, and iteration.

[0115] Initialization includes randomly generating an initial population, each individual representing a local reachable density calculation scheme. The initial population is {C1, C2,..., C N}, each individual Ci contains a parameter set {α i , β i}. Fitness calculation includes calculating the local reachable density of each individual in the current population based on the formula of the local outlier factor, and comparing it with other individuals. The fitness function is represented as:

[0116]

[0117] where f(C i ) represents the fitness function, represents the LOF value calculated based on the parameters of Ci.

[0118] It should be noted that the fitness function is based on the formula of the local outlier factor, by calculating the local reachable density of each individual in the current population, and comparing it with other individuals.

[0119] Selecting part of individuals as parents of the next generation according to fitness. The selection strategy is roulette selection to ensure that individuals with high fitness have a greater probability of being selected.

[0120] Performing crossover operation on the selected individuals to generate new individuals. The crossover operation is multi-point crossover, and the generated new individuals will inherit part of the characteristics of the parent individuals.

[0121] Some new individuals are subjected to mutation operation to introduce randomness. The mutation operation can be a numerical variation to increase the diversity of the population.

[0122] Further, the genetic algorithm steps are repeated until a predetermined number of iterations 100 is reached. After each iteration, the individuals in the population are updated so that the calculation scheme of the local reachable density is gradually optimized. The optimization parameters obtained by the genetic algorithm are α, which represents the voltage difference adjustment factor determined by the genetic algorithm, and β, which represents the current difference adjustment factor determined by the genetic algorithm. The distance calculation formula after optimization according to the optimization parameters is represented as:

[0123]

[0124] where dist opt (p,o) represents the physical distance between points p and o, V p represents the voltage of point p, V o represents the voltage of point o, I p represents the current of point p, and I o represents the current of point o.

[0125] The local reachable density formula after optimization according to the optimization parameters is represented as:

[0126]

[0127] The LOF value of each point is calculated using the optimized local reachable density, and it is determined whether it is an abnormal point, which is represented as:

[0128]

[0129] where represents the optimized reachable distance,

[0130] The abnormal score is calculated by combining the fused features and the optimized LOF algorithm, which is represented as:

[0131]

[0132] where A p represents the comprehensive abnormal score of point p, N represents the number of features, F i represents the normalized value of feature i, LOF k (p) represents the abnormal score of point p, and λ i represents the weight of feature i.

[0133] When the comprehensive abnormal score A p is greater than 0.5, the point is determined to be abnormal. Otherwise, it is normal.

[0134] It should be noted that the genetic algorithm (Genetic Algorithm, GA) is an optimization algorithm based on natural selection and genetic mechanism, which finds the optimal solution by simulating the biological evolution process. In optimizing the LOF (Local Outlier Factor) algorithm, we first randomly generate an initial population, and each individual represents a possible local reachable density (LRD) calculation scheme. Each individual contains a set of parameters (such as voltage difference adjustment factor and current difference adjustment factor), which will affect the distance calculation of the LOF algorithm. The pros and cons of each individual are evaluated by the fitness function, which is based on the accuracy of the LOF value. Select individuals with high fitness as parents for the next generation, and perform crossover and mutation operations to generate new individuals. The population is updated iteratively to gradually optimize the calculation formula of the local reachable density.

[0135] Further, the genetic algorithm gradually optimizes the parameters through the evolution mechanism, which can more accurately adjust the distance calculation in the LOF algorithm and improve the accuracy of anomaly detection. Genetic algorithm has global search capability and can avoid falling into local optimal solution, so as to find better parameter combination and improve the performance of LOF algorithm. Genetic algorithm does not depend on specific initial parameter setting, and automatically optimizes parameters through evolution process, reducing human intervention and improving the adaptability and robustness of the algorithm.

[0136] S3: Perform fault isolation, reconstruct the power grid topology, and realize the self-healing of the distribution network.

[0137] The points with comprehensive anomaly score A p > 0.5 are isolated, and the SCADA system sends instructions to the automation switch to disconnect the connection with the faulty device and line, and cut off the power supply of the fault area.

[0138] The goal is to minimize the load imbalance and reconstruction cost, and the power grid reconstruction objective function and constraint conditions based on linear programming are expressed as:

[0139]

[0140] subject to

[0141]

[0142]

[0143]

[0144] wherein, represents the load of the i-th line after reconstruction, represents the load of the i-th line before reconstruction, C j represents the cost of the j-th reconstruction operation, xj Binary variable representing the jth reconstruction operation, 1 means to perform the reconstruction operation, 0 means not to perform the reconstruction operation. i Capacity Load of the kth transformer after reconstruction. k Capacity of the kth transformer.

[0145] The method of introducing ant colony algorithm to optimize the power grid reconstruction based on linear programming is introduced, and the ant colony is initialized and the initial pheromone concentration is set. On the power grid topology, each line and transformer is allocated an initial pheromone concentration τ0.

[0146] In the power grid reconstruction problem, the selection of each line and transformer constitutes a solution space, and each ant selects a path according to the pheromone concentration τ and the heuristic information η. The selection probability P ij is represented as:

[0147]

[0148] where τ ij represents the pheromone concentration of line i to j, η ij represents the heuristic information of line i to j, including line capacity and current load. allowed represents the set of paths that ants can choose, α' represents the pheromone weight, and β' represents the heuristic information weight.

[0149] After each iteration, the pheromone concentration is updated according to the path selection of the ants, represented as:

[0150]

[0151] where ρ represents the pheromone evaporation coefficient, represents the amount of pheromone released by the kth ant on path i to j.

[0152] The path selection and pheromone update process is repeated until a good solution is obtained, and the optimal reconstruction scheme is determined, including the switches and circuit breakers that need to be operated and the load transfer path.

[0153] It should be noted that the ant colony optimization (ACO) is an optimization algorithm that simulates the foraging behavior of ants. It uses pheromone updating and path selection to find the optimal solution. In the power grid reconstruction problem, we combine the ant colony optimization with linear programming. First, we establish a linear programming model with the objective of minimizing load imbalance and reconstruction cost. Then, we initialize the ant colony and distribute the initial pheromone concentration on the power grid topology. Each ant selects a path based on the pheromone concentration and heuristic information, and calculates the reconstruction scheme. Through multiple iterations, the ants continuously update the pheromone concentration on the path, gradually optimizing the power grid reconstruction scheme. Finally, according to the optimization results of the ant colony algorithm, the optimal reconstruction scheme is determined, including the switches that need to be operated and the load transfer path.

[0154] The ant colony optimization algorithm has global optimization capability through the pheromone propagation and updating mechanism, which can effectively avoid falling into local optimal solution and improve the overall quality of the power grid reconstruction scheme. The ant colony optimization algorithm can dynamically adjust the pheromone concentration according to the power grid operating state, adapt to different load conditions and topology structure, and ensure the flexibility and robustness of the reconstruction scheme. The ant colony optimization algorithm combines heuristic information (line capacity and current load) to more intelligently evaluate the pros and cons of path selection, improving the efficiency and accuracy of the reconstruction scheme.

[0155] By introducing the ant colony optimization algorithm, the power grid reconstruction method can more efficiently handle complex power grid topology and load distribution, achieve fast and intelligent power grid reconstruction, ensure the stability and reliability of power supply in non-fault areas, and improve the self-healing ability of the distribution network.

[0156] Further, all weight parameters, coefficients, and other imaginary parameters of the present application are obtained through experiments and set according to the experience of relevant personnel.

[0157] In the above embodiments, a power distribution network self-healing system based on a power distribution network SCADA is also included, specifically:

[0158] The data acquisition module acquires data from the SCADA system and performs preprocessing.

[0159] The anomaly detection module extracts features from the preprocessed data and detects abnormal conditions using an optimized LOF algorithm.

[0160] The self-healing module isolates faults, reconstructs the power grid topology, and realizes self-healing of the power distribution network.

[0161] The computer device can be a server. The computer device comprises a processor, a memory, an input / output interface (I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The database of the computer device is configured to store data cluster data of a power monitoring system. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through a network connection. The computer program is executed by the processor to implement a method.

[0162] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of each method can be included. Any reference to memory, database or other medium used in each embodiment provided by the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (Read-Only Memory, ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric memory (Ferroelectric Random Access Memory, FRAM), phase change memory (Phase Change Memory, PCM), graphene memory, etc. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The database involved in each embodiment provided by the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in each embodiment provided by the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0163] In one embodiment of the present application, a power distribution network self-healing method and system based on network configuration SCADA are provided. In order to verify the beneficial effects of the present application, a simulation experiment is carried out for scientific demonstration.

[0164] The test object selects a section of power distribution network containing multiple lines and load points. The power distribution network has a SCADA system and can perform real-time data acquisition and monitoring.

[0165] The test equipment includes voltage sensors, current sensors, frequency sensors, power sensors, phase angle sensors and power quality monitors. All sensors are connected to the SCADA system through a communication network to ensure real-time data acquisition and transmission.

[0166] Test preparation:

[0167] Test equipment: includes voltage sensor, current sensor, frequency sensor, power sensor, phase angle sensor and power quality monitor. All sensors are connected to the SCADA system through a communication network, ensuring real-time data acquisition and transmission.

[0168] Test environment: a section of distribution network containing seven load points and five transmission lines is selected. Each load point is equipped with necessary measurement equipment to ensure detailed electrical parameters can be collected.

[0169] Fault simulation: during the test, artificial faults are introduced, including short circuit and ground fault, to test the effectiveness of the self-healing method.

[0170] Prior art steps include: collecting the operation data of the distribution network through the traditional monitoring system, including voltage, current, frequency, power, phase angle and power quality. The data is transmitted to the central control room through the communication network.

[0171] Use preset threshold for fault detection. When the voltage or current exceeds the preset threshold, it is judged as a fault. Manually operate switches and circuit breakers to isolate the fault area. By manual operation, adjust the power grid topology. Cannot combine real-time data and optimization algorithm for dynamic reconstruction.

[0172] Our invention steps include: the SCADA system collects the operation data of the distribution network in real time through the sensors, including voltage, current, frequency, power, phase angle and power quality. The data is transmitted to the central control room of the SCADA system through the communication network. Preprocess the collected data, use normalization method to standardize the data, ensure that data of different dimensions can be effectively compared.

[0173] Feature extraction is performed on the preprocessed data, extracting feature values of each parameter, such as maximum, minimum, mean value of voltage, root mean square value and peak value of current, standard deviation of frequency, maximum, minimum and average value of power, mean value of phase angle and total harmonic distortion of power quality, etc.

[0174] Use optimized LOF algorithm to detect abnormal situations, combine genetic algorithm to optimize parameters, ensure the accuracy and efficiency of detection. LOF algorithm calculates local reachable density (LRD) to evaluate the abnormality of each data point, and judges whether there is a fault according to the comprehensive abnormal score.

[0175] After detecting the fault point, the SCADA system issues instructions to the automated switches and circuit breakers, which disconnect the connection with the faulty equipment and lines, cutting off the power supply of the fault area.

[0176] According to real-time load data and power grid topology, the linear programming and ant colony algorithm are used to optimize the power grid reconstruction scheme, adjust the power grid topology structure, and transfer the load to the healthy power supply path. The ant colony algorithm finds the optimal reconstruction path through the update of pheromone and heuristic information, ensuring the balanced distribution of load.

[0177] The experimental results are shown in Table 1.

[0178]

[0179]

[0180] Through the table data, it can be clearly seen that the invention has significant advantages in the process of power grid self-healing. After fault handling, the voltage of the load point in the prior art fluctuates greatly, reaching 215V, 210V and 220V respectively, with a wide fluctuation range, which is easy to cause damage to power equipment and reduce power supply quality. The voltage of the load point in the invention using SCADA system for data acquisition and fault isolation is maintained in a relatively stable range, reaching 230V, 228V and 232V respectively, which significantly improves the stability of the voltage and ensures the quality of the power supply.

[0181] After fault handling, the current of the load point in the prior art fluctuates greatly, reaching 100A, 95A and 102A respectively, which cannot effectively balance the load. Through the optimized power grid reconstruction scheme, the current of the load point in the invention is evenly distributed, reaching 105A, 103A and 106A respectively, which ensures the consistency of the load of the power grid and reduces the loss of lines and equipment. The frequency of the load point in the prior art has a certain deviation, reaching 49.8Hz, 49.5Hz and 49.9Hz respectively, which may affect the stability of the power system. Through the application of the optimization algorithm, the frequency of the load point in the invention is stable around 50Hz, reaching 50.2Hz, 50.1Hz and 50.3Hz respectively, which improves the frequency accuracy of the power system and ensures the stable operation of the system.

[0182] After fault handling, the active power and reactive power in the prior art are not evenly distributed, reaching 20kW, 18kW and 22kW respectively, with low active power and reactive power of 5kVAR, 4.5kVAR and 5.5kVAR respectively, and low power factor. Through the optimization of power grid reconstruction and load adjustment, the active power in the invention reaches 24kW, 23kW and 25kW respectively, and the reactive power reaches 6kVAR, 5.8kVAR and 6.2kVAR respectively, which improves the power factor and overall power quality.

[0183] The phase angles of the prior art are 30°, 28° and 32° respectively, and the power quality (total harmonic distortion THD%) is 5.5%, 5.8% and 5.3% respectively, which affects the power supply quality and equipment life. Through feature extraction and optimization algorithm, the phase angles of our invention are 31°, 30° and 33° respectively, and the power quality is significantly improved, with THD% being 3.2%, 3.4% and 3.1% respectively, which improves the power supply quality and prolongs the service life of the equipment.

[0184] Through analysis, it can be seen that the power distribution network self-healing method based on distribution network SCADA of our invention realizes efficient self-healing of the power grid through data acquisition and preprocessing, feature extraction and anomaly detection, fault isolation and power grid reconstruction. Compared with the prior art, our invention significantly improves the stability of voltage and current, the accuracy of frequency, the optimization degree of power, and the phase angle and power quality, ensuring the reliability and quality of power supply. In particular, in the process of fault isolation and power grid reconstruction, the application of optimization algorithm improves the response speed and decision accuracy, effectively solving the shortcomings of the prior art in fault handling.

[0185] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit it. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application, and they should be covered in the scope of the claims of the present application.

Claims

1. A power distribution network self-healing method based on network configuration SCADA, characterized in that, The method comprises the following steps: Data acquisition and preprocessing according to the SCADA system; Feature extraction of the preprocessed data, and detection of abnormal conditions by using an optimized LOF algorithm; Fault isolation, reconstruction of the power grid topology, and self-healing of the distribution network; The detection of abnormal conditions by using the optimized LOF algorithm comprises the following steps: where F i denotes the normalized feature, T i denotes the value of feature i, μ i denotes the mean of feature i, σ i denotes the standard deviation of feature i; The calculation formula of the LOF algorithm is as follows: wherein lrd k (p) denotes the local reachable density, expressed as: where p denotes a point to be detected, N k (p) denotes the set of k-nearest neighbors of point p, reach_dist k (p, o) denotes the reachable distance, reach_dist k (p, o) = max{dist(p, o), min_dist k (o)}; dist k (p, o) denotes the distance between points p and o, min_dist k (o) denotes the k-th nearest neighbor distance of point o to its k-nearest neighbors; The genetic algorithm is used to optimize the calculation process of the LOF algorithm to improve the accuracy and efficiency of the algorithm. Initialization includes randomly generating an initial population, each individual represents a local reachable density calculation scheme; the initial population is {C1, C2,..., C N} , each individual Ci contains a parameter set {α i , β i} ; the fitness calculation includes calculating the local reachable density of each individual in the current population based on the formula of local anomaly factor, and comparing with other individuals, the fitness function is represented as: where f(C i ) denotes a fitness function, denotes the LOF value calculated based on the Ci parameters; The genetic algorithm comprises the following steps: where dist opt (p, o) denotes the physical distance between points p and o, V p denotes the voltage at point p, V o denotes the voltage at point o, I p denotes the current at point p, I o denotes the current at point o; The optimized parameters obtained by the genetic algorithm are as follows: The distance calculation formula after optimization according to the optimized parameters is as follows: wherein, represents the optimized reachable distance, 2. The power distribution network self-healing method based on network configuration SCADA of claim 1, characterized in that: The local reachable density formula after optimization according to the optimized parameters is as follows: The LOF value of each point is calculated using the optimized local reachable density, and it is determined whether it is an abnormal point or not. where x i represents normalized data, x i represents original data, x min represents the minimum value in the data, x max represents the maximum value in the data.

3. The power distribution network self-healing method based on network configuration SCADA of claim 2, characterized in that: The data preprocessing comprises data normalization, and the formula is as follows: where T V represents the voltage characteristic, V max represents the voltage maximum, V min represents the voltage minimum, V arg represents the voltage average; The feature extraction of the voltage is as follows: where T I represents the current characteristic, I rms represents the root mean square value of the current, I peak represents the peak value of the current; The feature extraction of the current is as follows: T f = f std where T f represents the frequency characteristic, f std represents the standard deviation of the frequency; The frequency feature extraction formula is as follows: where T P represents the active power characteristic, P max represents the active power maximum, P min represents the active power minimum, P arg represents the active power average; T Q represents the reactive power characteristic, Q max represents the reactive power maximum, Q min represents the reactive power minimum, Q arg represents the reactive power average; The power feature extraction is as follows: T θ = cos(θ avg ) where T θ denotes the phase angle characteristic, θ avg denotes the phase angle average value; The phase angle feature extraction is as follows: where T PQ represents the power quality characteristic, H total represents the total harmonic distortion, V rms represents the root mean square value of the voltage.

4. The power distribution network self-healing method based on network configuration SCADA of claim 3, characterized in that: The power quality feature extraction is as follows: where A p represents the integrated anomaly score of point p, N represents the number of features, F i represents the normalized value of feature i, LOF k (p) represents the anomaly score of point p, λ i represents the weight of feature i; Abnormality score A p If the value is greater than 0.5, the point is judged to be an abnormal situation; otherwise, it is judged to be a normal situation.

5. The power distribution network self-healing method based on network configuration SCADA of claim 4, characterized in that: The performing of fault isolation includes, when the integrated abnormality score A p > 0.5, the SCADA system issues an instruction to an automation switch, which disconnects the connection to the faulty device and line, cutting off the power supply in the fault area.

6. The power distribution network self-healing method based on network configuration SCADA of claim 5, characterized in that: The detection of abnormal conditions by using the optimized LOF algorithm further comprises the following steps: wherein, Ci represents the load of the i-th line after reconstruction, Ci represents the load of the i-th line before reconstruction, j Cj represents the cost of the j-th reconstruction operation, j Cj represents the binary variable of the j-th reconstruction operation, 1 represents performing the reconstruction operation, and 0 represents not performing the reconstruction operation; Capacity i Ci represents the capacity of the i-th line, Ck represents the load of the k-th transformer after reconstruction, k Ck represents the capacity of the k-th transformer; The reconstruction of the power grid topology comprises the following steps: In the problem of power grid reconstruction, the selection of each line and transformer constitutes a solution space, and each ant selects a path according to the pheromone concentration τ and heuristic information η; the selection probability P ij is represented as: where τ ij denotes the pheromone concentration of the link i to j, η ij denotes the heuristic information of the link i to j, including link capacity and current load; allowed denotes the set of alternative paths available to the ant, a' denotes the pheromone weight, and β' denotes the heuristic information weight; The objective is to minimize the load imbalance and reconstruction cost. wherein p represents pheromone evaporation coefficient, denotes the amount of pheromone released by the kth ant on the path i to j; The power grid reconstruction objective function and constraint conditions based on linear programming are as follows: The ant colony algorithm is introduced to optimize the power grid reconstruction based on linear programming. The ant colony is initialized, and the initial pheromone concentration is set. After each iteration, the pheromone concentration is updated according to the path selection of the ants. The path selection and pheromone update process are repeated until a high-quality solution is obtained, and the optimal reconstruction scheme is determined, including the switches and circuit breakers that need to be operated and the load transfer path.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, 7. A distribution network SCADA-based self-healing system for distribution networks, which adopts the method according to any one of claims 1-6. The data acquisition module acquires data according to the SCADA system and preprocesses the data. The detection of abnormal conditions module extracts features from the preprocessed data and detects abnormal conditions by using an optimized LOF algorithm. The self-healing module isolates faults, reconstructs the power grid topology, and realizes self-healing of the distribution network. The processor executes the computer program to realize the steps of the method according to any one of claims 1-6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program, which is executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images