A classification method, device, equipment and medium for performing a protection action strategy

Abstract

A kind of classification method, device, equipment and medium for executing protection action strategy are disclosed, by obtaining power distribution network data when fault, according to the power distribution network data and power distribution network distribution data, construct the quasi-state power distribution network model in virtual simulation space;Determine the target data of fault area section in power distribution network, load the target data to the quasi-state power distribution network model;Obtain multiple execution protection action strategies, based on the quasi-state power distribution network model, the execution protection action strategy is periodically frequency tested, and the test data corresponding to the execution protection action strategy is obtained;Based on the test data corresponding to the execution protection action strategy, determine the security level of the execution protection action strategy.The embodiment of the present application can quickly divide the security level of the execution protection action strategy, solve the problem of lacking the security analysis of power distribution network fault recovery execution action, reduce the risk of power distribution network operation after fault recovery scheme execution.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of power system dispatch automation and power grid simulation, and in particular to a classification method, device, equipment and medium for executing a protection action strategy. BACKGROUND

[0002] With the continuous expansion of the distribution network and the access of a large number of distributed power sources, the distribution network topology is complex and prone to failure.

[0003] The existing distribution network is usually configured with current sampling elements, and the protection principle adopts overcurrent protection, optical fiber longitudinal differential protection, etc. to detect faults on the line, according to the connection cascade of the line, and establishes a multi-level backup protection scheme.

[0004] However, when the protection action strategy is executed in the actual application of the current distribution network fault, due to the uncertainty of the pros and cons of the distribution network operation after the execution of the recovery scheme, it not only hides the potential danger for the safe operation of the distribution network, but also brings intangible economic losses. SUMMARY

[0005] The present application provides a classification method, device, equipment and medium for executing a protection action strategy to solve the problem of lack of safety analysis of the execution of the distribution network fault recovery action, which can realize the rapid division of the security level of the execution of the protection action strategy, guarantee the reliability of the execution of the distribution network protection action, and reduce the risk of the operation of the distribution network after the execution of the fault recovery scheme.

[0006] According to an aspect of the present application, a classification method for executing a protection action strategy is provided, comprising:

[0007] Obtaining distribution network data at the time of distribution network fault, and constructing a quasi-state distribution network model in a virtual simulation space according to the distribution network data and distribution network distribution data;

[0008] Determining the target data of the fault area segment in the distribution network, and loading the target data to the quasi-state distribution network model;

[0009] Obtaining a plurality of execution protection action strategies, performing periodic frequency testing on the execution protection action strategies based on the quasi-state distribution network model, and obtaining test data corresponding to the execution protection action strategies;

[0010] Based on the test data corresponding to the execution protection action strategy, the security level of the execution protection action strategy is determined.

[0011] According to another aspect of the present application, a classification device for executing a protection action strategy is provided, comprising:

[0012] The model construction module is configured to acquire power distribution network data at the time of a fault of the power distribution network, and construct a quasi-state power distribution network model in a virtual simulation space according to the power distribution network data and power distribution network distribution data.

[0013] The target data loading module is configured to determine target data of a fault area segment in the power distribution network, and load the target data to the quasi-state power distribution network model.

[0014] The test data acquisition module is configured to acquire a plurality of execution protection action strategies, perform periodic frequency testing on the execution protection action strategies based on the quasi-state power distribution network model, and obtain test data corresponding to the execution protection action strategies.

[0015] The grade determination module is configured to determine a security grade of the execution protection action strategies based on the test data corresponding to the execution protection action strategies.

[0016] According to another aspect of the present application, an electronic device is provided, which comprises:

[0017] at least one processor; and

[0018] a memory in communication with the at least one processor; wherein

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to perform the classification of the execution protection action strategies according to any one of the embodiments of the present application.

[0020] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to implement the classification of the execution protection action strategies according to any one of the embodiments of the present application when executed by the processor.

[0021] The technical scheme of the embodiments of the present application can acquire power distribution network data at the time of a fault of the power distribution network, and construct a quasi-state power distribution network model in a virtual simulation space according to the power distribution network data and power distribution network distribution data; determine target data of a fault area segment in the power distribution network, and load the target data to the quasi-state power distribution network model; acquire a plurality of execution protection action strategies, perform periodic frequency testing on the execution protection action strategies based on the quasi-state power distribution network model, and obtain test data corresponding to the execution protection action strategies; and determine a security grade of the execution protection action strategies based on the test data corresponding to the execution protection action strategies, so that the security grade of the classification of the execution protection action strategies can be quickly divided, the problem of lacking safety analysis of the execution action of the power distribution network fault recovery is solved, the reliability of the execution action of the power distribution network protection is ensured, and the risk of the operation of the power distribution network after the execution of the fault recovery scheme is reduced.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a classification method for executing protection action strategies provided in Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a classification method for executing protection action strategies provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of a classification device for executing protection action strategies provided in Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the classification method for executing protection action strategies according to embodiments of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention 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 so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a 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.

[0030] Example 1

[0031] Figure 1 This is a flowchart of a classification method for executing protection action strategies provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of distribution network fault recovery. The method can be executed by a classification device for executing protection action strategies. This classification device for executing protection action strategies can be implemented in hardware and / or software, and can be configured in electronic devices such as computers or servers. Figure 1 As shown, the method includes:

[0032] S110. Obtain distribution network data when a distribution network fault occurs, and construct a simulated distribution network model in the virtual simulation space based on the distribution network data and distribution network distribution data.

[0033] In this embodiment, when the distribution network data indicates a distribution network fault, the current fault value at all locations in the distribution network is obtained through fault detection. This current fault value can be the voltage and current values ​​of the current faulty section of the distribution network. The faulty section is a faulty feeder segment where a fault exists between two switches. The distribution network distribution data includes data on the paths of current and voltage transmission in the distribution network and the data on the line layout of the distribution network. The simulated distribution network model is a simulation model established based on the distribution network data and the distribution network distribution data. Distribution network faults include, but are not limited to, various fault types such as single-phase grounding and phase-to-phase short circuits; various fault addresses such as the power supply side, network side, and load side; various fault depths such as high-resistance grounding faults and metallic grounding faults; and various fault levels such as feeder level, equipment level, and system level.

[0034] Specifically, relevant data on the distribution network collected from the network database can be used to verify and collect distribution network data and distribution network data. One or more faulty sections can be identified using fault location techniques (e.g., matrix methods and artificial intelligence methods). Voltage and current values ​​in the faulty sections can be monitored in real time using instrument transformers to quickly collect the current fault values ​​of the distribution network and determine the fault type. The real-time collected distribution network data and distribution network data can be transmitted to computers or servers via wired or wireless means. Virtual reality and digital twin technologies can then be used to establish simulated digital models based on the actual physical areas of the distribution network under different fault types in a virtual simulation space.

[0035] For example, the distribution network is monitored in real time, and the collected distribution network data and distribution data are wirelessly transmitted to a classification device that executes protection action strategies. A faulty segment is identified using a neural network-based fault location technology. Current transformers are used to monitor this faulty segment in real time, obtaining the corresponding current voltage and current values ​​to determine the fault type. By fusing the real-time collected distribution network data and distribution data, a digital twin is created based on virtual reality and digital twin technologies to obtain a simulated digital model. This model provides a visual representation of the real-time acquired distribution network data and distribution data, and can also simulate the distribution network's operating state to obtain simulated data.

[0036] The technical solution in this embodiment ensures the accuracy of the established operational data by verifying the collected distribution network data and distribution network distribution data, reducing test value errors caused by biased data. By constructing a digital twin, it achieves highly real-time dynamic reconfiguration of the distribution network, enabling rapid detection of distribution network faults and providing a reference for maintenance cycles, thus improving the reliability of analysis results.

[0037] S120. Determine the target data for the faulty area section in the distribution network and load the target data into the mimicry distribution network model.

[0038] In this embodiment, the target data refers to multiple data points used to analyze changes in the faulty section of the distribution network after the relevant execution action protection strategy is performed, such as voltage and current values.

[0039] Specifically, multiple data points required for distribution network fault analysis are identified as target data. By establishing a historical database, data related to the target data in the faulty area of ​​the distribution network are detected at a certain frequency, stored in the historical database, and analyzed and calculated to obtain one or more target data points. These target data points are then dynamically loaded into the mimicry distribution network model along with one or more target data points acquired in real time.

[0040] Optionally, the target data may include the position of each switch, the historical frequency of switch action, the time of the most recent switch action, the current voltage value, and the current current value.

[0041] In this embodiment, the switch position refers to the position of all switches within the fault area in the simulated distribution network model; the historical switch operation frequency is the switch operation frequency calculated by the switching element at each switch position based on the number of switch operations and the duration of the time period recorded in the historical target database before the current time point; the most recent switch operation time is the time of the previous switch operation recorded in the historical target database before the current switch operation time; the current voltage value and the current current value are the voltage and current values ​​of the fault area detected in real time by the instrument transformer, respectively.

[0042] The technical solution of this embodiment uses the positions of each switch, the historical frequency of switch operation, the time of the most recent switch operation, the current voltage value, and the current current value as target data to accurately reflect the working status of the fault area in the distribution network, making the analysis results comprehensive and reliable.

[0043] S130. Obtain multiple execution protection action strategies, and perform periodic frequency tests on the execution protection action strategies based on the mimicry distribution network model to obtain the test data corresponding to the execution protection action strategies.

[0044] In this embodiment, the protection action strategy is based on the reference fault action protection strategy corresponding to each fault type pre-stored in the distribution network fault type action database. The protection action strategy database is a pre-established database composed of reference fault action protection strategies corresponding to different fault types. Periodic frequency testing is a simulation test in a simulated distribution network model to measure the frequency of faults occurring during the operation of multiple protection action strategies for the same duration. The test data consists of multiple result data from the periodic frequency test of the protection action strategies in the simulated distribution network model.

[0045] Specifically, based on the fault type of the faulty section in the distribution network, multiple corresponding protection action strategies are selected from the protection action strategy database. Based on the protection action strategies, corresponding simulation operations are performed in the simulated distribution network model. Periodic frequency tests are conducted on the fault recovery operation of the distribution network. By continuously collecting operational data and performing intelligent analysis on the collected data, such as time series analysis and periodic analysis, test data corresponding to the protection action strategies are obtained.

[0046] The technical solution in this embodiment continuously collects and intelligently analyzes operational data, performing periodic optimal prediction analysis. This allows for the prediction of the optimal execution point in the adopted protection action strategy and provides a reference for maintenance cycles, improving the reliability of the analysis results. By conducting tests on multiple protection action strategies at the same periodic frequency, the consistency of the periodic frequency is ensured, guaranteeing the accuracy of the analysis results.

[0047] Optionally, multiple protection action strategies can be implemented, including application strategies and backup strategies, which are obtained based on the fault types of the distribution network.

[0048] In this embodiment, the application strategy is the current fault execution action protection strategy corresponding to each fault type, and the backup strategy is one or more alternative fault execution action protection strategies corresponding to each fault type.

[0049] Specifically, for each fault type in the distribution network, there can be one application strategy and one or more backup strategies in the protection action strategy database that match that fault type.

[0050] For example, the application strategies in the protection action strategy include, but are not limited to: circuit breaker operation, which, when a system fault or abnormal situation occurs, triggers the circuit breaker to isolate the faulty part from the power grid, protecting the safe operation of other equipment and the power grid; alarm signal issuance, which notifies operators or monitoring systems through alarm signals; and automated operation of protection devices, which automatically determines the fault type and executes corresponding protection actions based on preset protection strategies and parameters. Alternative strategies in the protection action strategy include, but are not limited to: power switching, which isolates the faulty part from the power grid by switching power to a backup power supply or other reliable power source; trip protection, which disconnects the power supply to the entire distribution network or a portion of the area; isolating switch operation, which isolates the faulty equipment or area from the power grid by operating the isolating switch, preventing the fault from spreading and affecting the normal operation of other equipment; remote control operation, which remotely controls the switching status of equipment to achieve fault isolation, power restoration, and other operations, improving operational convenience and safety; and automatic restart.

[0051] Optionally, the periodic frequency test is a periodic frequency test that executes a single protection action strategy. The test data obtained from any periodic frequency test includes the switching action frequency, the switching action frequency interval, and the voltage and current values ​​of the fault segment before and after each switching.

[0052] In this embodiment, the switching frequency is the periodic frequency test phase, and the switching frequency of each switching element at each switching position in the target data is calculated based on the number of switching operations and the duration of the time period; the switching frequency interval is the time interval between two adjacent switching operations during the periodic frequency test phase; the voltage value is the voltage value of the fault section in the simulated distribution network model at two moments before and after the switching operation; the current value is the current value of the fault section in the simulated distribution network model at two moments before and after the switching operation.

[0053] Specifically, in the mimicry distribution network model, each protection action strategy corresponding to each fault type in the protection action strategy database is tested once or multiple times. Each periodic frequency test continuously collects and intelligently analyzes the operating data to obtain test data including the switching action frequency, the switching action frequency interval, and the voltage and current values ​​of the fault segment before and after each switching.

[0054] S140. Based on the test data corresponding to the execution protection action strategy, determine the security level of the execution protection action strategy.

[0055] In this embodiment, the security level is determined by classifying the execution of each protection action strategy based on the fault indicators. The fault indicators are one or more indicators that indicate the possibility of failure of the protection action strategy in the future, obtained by analyzing and calculating the test data obtained when the protection action strategy is periodically tested in the simulated distribution network model.

[0056] Specifically, the security level of the execution protection action strategy can be pre-divided into multiple levels. That is, the multiple execution protection action strategies corresponding to each fault type can be divided into multiple security level types. The test data of multiple execution protection action strategies can be analyzed and calculated using manual, deep learning or traditional machine learning methods to classify the corresponding multiple execution protection action strategies, and each execution protection action strategy corresponds to a security level type.

[0057] For example, based on the test data corresponding to the execution of protection action strategies, the security levels of these strategies can be divided into two main categories: high and low. Within the low-security category, the optimal type can be further distinguished. A neural network-based method can be used to classify all protection action strategies according to the test data.

[0058] To more intuitively measure the degree of fault in the distribution network, fault indicators can be used to reflect the operation of the distribution network after fault recovery using protection action strategies in the faulty section.

[0059] Optionally, fault indicators for the execution of protection action strategies are determined based on test data corresponding to the execution of protection action strategies. Fault indicators include one or more of the following: fault rate, number of faults, fault point data, and repeated fault point data. Evaluation data for the execution of protection action strategies are determined based on the fault indicators. The security level of the execution of protection action strategies is determined based on the evaluation data and the security level threshold.

[0060] In this embodiment, the failure rate is the percentage of failure time during the periodic frequency testing phase in the mimicry distribution network model to the total periodic frequency testing time, i.e., failure rate = [(downtime + maintenance time) / planned total usage time] × 100%. The number of failures is the number of times a failure occurs during the periodic frequency testing phase. Fault point data or repeated fault point data are the test data for each faulty area segment that occurs or repeats during the periodic frequency testing of the mimicry distribution network model. Evaluation data is the result of a comprehensive analysis of fault indicators, used to evaluate the safety of the protection action strategy. The safety level threshold is a pre-set threshold for classifying the safety level of the protection action strategy.

[0061] Specifically, the test data obtained from periodic frequency tests in a simulated distribution network model are analyzed and calculated to determine the execution status, route execution status, and action execution probability of the corresponding fault type protection action. These are represented by fault indices. The fault indices are then used to conduct a comprehensive safety analysis of the fault frequency, fault causes, and fault severity of the distribution network during periodic frequency tests, resulting in evaluation data for the protection action strategy. This evaluation data is then compared with a pre-set safety level threshold to classify the safety level of the protection action strategy. The safety level category to which the strategy belongs is the safety level of the protection action strategy.

[0062] For example, assume that fault indicators include fault rate, number of faults, fault point data, and repeated fault point data; the evaluation data is a comprehensive value calculated using neural network analysis; and the safety level threshold is a standard threshold for classifying the safety level of the execution protection action strategy based on deep learning. A safety level classification model is pre-trained, with its input being test data obtained from periodic frequency tests of the execution protection action strategy in a simulated distribution network model. The safety level threshold is determined based on the training data. The calculated evaluation data of the execution protection action strategy is compared with the safety level threshold, and the safety level type of the execution protection action strategy is output. The trained safety level classification model is used to classify the safety level of the execution protection action strategy. If the evaluation data is greater than the safety level threshold, the execution protection action strategy is considered to have a low safety level and is classified as a low-safety-level type. If the evaluation data is less than the safety level threshold, the execution protection action strategy is considered to have a high safety level and is classified as a high-safety-level type. If the evaluation data is less than the safety level threshold but exceeds 10% of the threshold value, the execution protection action strategy is considered to have the best safety level and is further classified as the best-safety-level type.

[0063] To more accurately determine the fault indicators of the protection action strategy, test data can be analyzed to make the fault indicators more consistent with the classification requirements of the protection action strategy and more reliable.

[0064] Optionally, fault identification is performed on the test data obtained from multiple periodic frequency tests of the protection action strategy, and the fault indicators of the protection action strategy are determined based on the fault identification results of the multiple periodic frequency tests.

[0065] In this embodiment, fault identification is performed by identifying whether a distribution network fault has occurred in the simulated distribution network model based on the test results obtained during periodic frequency testing.

[0066] Specifically, the test results of multiple tests with the same periodic frequency can be analyzed to identify the test data when a distribution network fault occurs in the simulated distribution network model and use it as the fault identification result. A comprehensive analysis of one or more test data points from the fault identification result is then performed to obtain the calculation relationship between the test results and fault indicators, thereby determining the fault indicators for executing protection action strategies.

[0067] For example, a comprehensive analysis of one or more test data items in the fault identification results can be performed using artificial intelligence algorithms (e.g., machine learning) and / or traditional mathematical model algorithms (e.g., factor analysis) to assign a weight to each test data item.

[0068] The technical solution of this embodiment acquires distribution network data during a distribution network fault, constructs a simulated distribution network model in a virtual simulation space based on the distribution network data and distribution network distribution data; determines the target data of the faulty area segment in the distribution network, and loads the target data into the simulated distribution network model; acquires multiple protection action strategies, performs periodic frequency tests on the protection action strategies based on the simulated distribution network model, and obtains the test data corresponding to the protection action strategies; and determines the security level of the protection action strategies based on the test data corresponding to the protection action strategies. This enables rapid classification of the security level of the protection action strategies, solves the problem of lacking security analysis for distribution network fault recovery actions, ensures the reliability of distribution network protection actions, and reduces the risk of distribution network operation after the fault recovery plan is implemented.

[0069] Example 2

[0070] Figure 2 This is a flowchart of a classification method for executing protection action strategies provided in Embodiment 2 of the present invention. The technical solution of the present invention is further optimized based on any of the above embodiments. Figure 2 As shown, the method includes:

[0071] S210. Obtain distribution network data when a distribution network fault occurs, and construct a simulated distribution network model in the virtual simulation space based on the distribution network data and distribution network distribution data.

[0072] S220. Determine the target data for the faulty area section in the distribution network and load the target data into the mimicry distribution network model.

[0073] S230: Obtain multiple execution protection action policies.

[0074] S240. Classify the execution protection action strategies to obtain at least two types of execution protection action strategy groups.

[0075] In this embodiment, the execution protection action strategy group is a group of execution protection action strategies divided according to the degree of similarity between them.

[0076] Specifically, based on the degree of similarity between the protection action strategies, the protection action strategies are classified into two or more similarity categories, and each protection action strategy is assigned to the corresponding protection action strategy group according to the similarity category.

[0077] For example, a similarity threshold range can be set, and the execution protection action strategies with similarity within the similarity threshold range can be classified into the optimal similar execution protection action strategy group, while other execution protection action strategies can be classified into the secondary similar execution protection action strategy group.

[0078] Classifying protective action strategies can rely on subjective judgment by personnel, or it can be done by setting similarity evaluation indicators to determine classification criteria.

[0079] Optionally, similarity data between backup strategies and application strategies can be determined, and backup strategies can be classified based on similarity data and type classification thresholds.

[0080] In this embodiment, the similarity data is the distance data between the application strategy and the backup strategy, which is used to evaluate the degree of similarity between the application strategy and the backup strategy.

[0081] Specifically, text classification, statistical methods, machine learning, and deep learning methods can be used to extract features from application strategies and backup strategies to obtain application strategy features x and backup strategy features y. Similarity data d between application strategy features x and backup strategy features y can be obtained using methods such as Manhattan distance, Chebyshev distance, and Euclidean distance. Based on a pre-set similarity threshold range and the similarity data d between each backup strategy and the application strategy, each backup strategy is classified and assigned to the corresponding execution protection action strategy group.

[0082] For example, the similarity data d between application strategy feature x and backup strategy feature y can be calculated using the following formula:

[0083]

[0084] Backup strategies with similarity data d∈[0,1] are classified as the optimal similarity execution protection action strategy group, and other backup strategies are classified as the secondary similarity execution protection action strategy group.

[0085] The technical solution of this embodiment improves the classification accuracy and makes the security analysis results more reliable by classifying the execution protection action strategies with high similarity into the same execution protection action strategy group, and classifying the execution protection action strategies of the same execution protection action strategy group according to their security level.

[0086] S250. For the same protection action strategy group, perform periodic frequency tests on multiple protection action strategies within the protection action strategy group to obtain test data corresponding to each protection action strategy.

[0087] Specifically, all execution protection action strategies in each execution protection action strategy group can be tested at the same periodic frequency to obtain test data for each execution protection action strategy in that execution protection action strategy group.

[0088] Optionally, within the same group of protection action strategies, a representative protection action strategy can be used to represent all protection action strategies. Periodic frequency tests can be performed on the representative protection action strategy to obtain the test data corresponding to the representative protection action strategy.

[0089] Specifically, for each protection action strategy group, any one of the protection action strategy groups within that group can be used as the representative protection action strategy for that group. Alternatively, a representative protection action strategy can be generated by analyzing all the protection action strategies within the group. This embodiment does not impose any restrictions on this. The representative protection action strategy is only simulated and tested in a simulated distribution network model, and the test data obtained is used to determine the representative protection action strategy.

[0090] The technical solution of this embodiment saves computing resources, improves classification efficiency, and greatly improves the safety analysis efficiency of the distribution network operation after the implementation of the recovery plan by using the security level classification of the representative execution protection action strategy of the execution protection action strategy group as the security level classification of all execution protection action strategies in the execution protection action strategy group.

[0091] S260. Based on the test data corresponding to the execution of the protection action strategy, determine the security level of the execution of the protection action strategy.

[0092] The technical solution of this embodiment acquires distribution network data during a distribution network fault, constructs a simulated distribution network model in a virtual simulation space based on the distribution network data and distribution network distribution data; determines the target data of the faulty area segment in the distribution network and loads the target data into the simulated distribution network model; acquires multiple execution protection action strategies; classifies the execution protection action strategies to obtain at least two types of execution protection action strategy groups; for the same execution protection action strategy group, performs periodic frequency tests on multiple execution protection action strategies within the group to obtain test data corresponding to each execution protection action strategy; and determines the security level of the execution protection action strategy based on the test data corresponding to the execution protection action strategy. This allows for a more refined division of the security level of the execution protection action strategy, making the safety analysis of distribution network fault recovery execution actions more comprehensive and reliable, and further reducing the risk of distribution network operation after the fault recovery plan is implemented.

[0093] Example 3

[0094] Figure 3 This is a schematic diagram of the structure of a classification device for executing protection action strategies provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0095] The model building module 310 is used to acquire distribution network data when a distribution network fault occurs, and to build a simulated distribution network model in the virtual simulation space based on the distribution network data and distribution network distribution data.

[0096] The target data loading module 320 is used to determine the target data of the fault area section in the distribution network and load the target data into the mimic distribution network model.

[0097] The test data acquisition module 330 is used to acquire multiple execution protection action strategies, perform periodic frequency tests on the execution protection action strategies based on the mimicry distribution network model, and obtain the test data corresponding to the execution protection action strategies.

[0098] The level determination module 340 is used to determine the security level of the protection action strategy based on the test data corresponding to the protection action strategy.

[0099] The technical solution of this embodiment acquires distribution network data during a distribution network fault, constructs a simulated distribution network model in a virtual simulation space based on the distribution network data and distribution network distribution data; determines the target data of the faulty area segment in the distribution network, and loads the target data into the simulated distribution network model; acquires multiple protection action strategies, performs periodic frequency tests on the protection action strategies based on the simulated distribution network model, and obtains the test data corresponding to the protection action strategies; and determines the security level of the protection action strategies based on the test data corresponding to the protection action strategies. This enables rapid classification of the security level of the protection action strategies, solves the problem of lacking security analysis for distribution network fault recovery actions, ensures the reliability of distribution network protection actions, and reduces the risk of distribution network operation after the fault recovery plan is implemented.

[0100] Based on the above embodiments, optionally, the target data includes each switch position, historical switch operation frequency, the time of the most recent switch operation, the current voltage value, and the current current value.

[0101] Based on the above embodiments, optionally, the multiple protection action strategies include application strategies and backup strategies, and the protection action strategies are obtained based on the fault type matching of the distribution network.

[0102] Based on the above embodiments, optionally, the periodic frequency test is a periodic frequency test that executes a single protection action strategy. The test data obtained from any periodic frequency test includes the switching action frequency, the switching action frequency interval, and the voltage and current values ​​of the fault segment before and after each switching.

[0103] Based on the above embodiments, optionally, the level determination module 340 specifically includes:

[0104] The fault indicator determination unit is used to determine the fault indicators of the protection action strategy based on the test data corresponding to the execution of the protection action strategy. The fault indicators include one or more of the following: fault rate, number of faults, fault point data, and repeated fault point data.

[0105] The safety level determination unit is used to determine the evaluation data for the execution of the protection action strategy based on the fault indicators of the protection action strategy, and to determine the safety level of the protection action strategy based on the evaluation data and the safety level threshold.

[0106] Based on the above embodiments, optionally, the fault index determination unit is specifically used to: identify faults in the test data obtained from multiple periodic frequency tests of the protection action strategy, and determine the fault index of the protection action strategy based on the fault identification results of the multiple periodic frequency tests.

[0107] Based on the above embodiments, optionally, the test data acquisition module 330 includes:

[0108] The policy acquisition unit is used to acquire multiple policies for executing protection actions.

[0109] The strategy classification unit is used to classify the execution protection action strategies to obtain at least two types of execution protection action strategy groups;

[0110] The test data acquisition unit is used to perform periodic frequency tests on multiple execution protection action strategies within the same execution protection action strategy group, and obtain test data corresponding to each execution protection action strategy.

[0111] Based on the above embodiments, optionally, the strategy classification unit is specifically used to determine the similarity data between the backup strategy and the application strategy, and to classify the backup strategy into types based on the similarity data and the type classification threshold.

[0112] The classification device for executing protection action strategies provided in the embodiments of the present invention can execute the classification method for executing protection action strategies provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0113] Example 4

[0114] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the classification method for executing protection action strategies according to embodiments of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0115] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0116] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0117] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as performing the classification of protection action strategies.

[0118] In some embodiments, the classification of protection action strategies can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the classification of protection action strategies described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform the classification of protection action strategies by any other suitable means (e.g., by means of firmware).

[0119] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0120] Computer programs used to implement the classification of protective action strategies of this invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0121] Example 5

[0122] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a classification method for implementing a protection action strategy, the method comprising:

[0123] Acquire distribution network data during distribution network faults, and construct a mimicry distribution network model in a virtual simulation space based on the distribution network data and distribution network distribution data; determine the target data for the faulty area segment in the distribution network, and load the target data into the mimicry distribution network model; acquire multiple protection action strategies, and conduct periodic frequency tests on the protection action strategies based on the mimicry distribution network model to obtain the test data corresponding to the protection action strategies; determine the security level of the protection action strategies based on the test data corresponding to the protection action strategies.

[0124] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0125] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0126] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication (e.g., communication networks) of any form or medium. Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0127] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0128] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0129] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A classification method for executing protective action strategies, characterized in that, include: Acquire distribution network data during distribution network faults, and construct a simulated distribution network model in a virtual simulation space based on the distribution network data and distribution network distribution data; Target data for the faulty section in the distribution network is determined and loaded into the simulated distribution network model. The target data includes the positions of each switch, historical switch operation frequencies, the time of the most recent switch operation, the current voltage value, and the current current value. The switch positions are the locations of all switches within the faulty section in the simulated distribution network model. The historical switch operation frequencies are the time period recorded in the historical target database prior to the current time point. The time of the most recent switch operation is the time of the switch operation preceding the current operation time recorded in the historical target database. The current voltage value and current value are the voltage and current values ​​of the faulty section detected in real time by the instrument transformers, respectively. Multiple execution protection action strategies are obtained, and the execution protection action strategies are periodically tested based on the simulated distribution network model to obtain the test data corresponding to the execution protection action strategies. Fault identification is performed on the test data obtained from multiple periodic frequency tests of the protection action strategy. Based on the fault identification results of the multiple periodic frequency tests, the fault indicators of the protection action strategy are determined. The fault indicators include one or more of the following: fault rate, number of faults, fault point data, and repeated fault point data. The evaluation data for the protection action strategy is determined based on the fault indicators of the protection action strategy, and the security level of the protection action strategy is determined based on the evaluation data and the security level threshold.

2. The method according to claim 1, characterized in that, After obtaining multiple protection action policies, the following is also included: The execution protection action strategies are classified to obtain at least two types of execution protection action strategy groups; Accordingly, the periodic frequency test of the protection action strategy based on the simulated distribution network model to obtain the test data corresponding to the protection action strategy includes: Within the same group of execution protection action strategies, periodic frequency tests are performed on multiple execution protection action strategies within the group to obtain test data corresponding to each execution protection action strategy.

3. The method according to claim 2, characterized in that, The multiple protection action strategies include application strategies and backup strategies, and the protection action strategies are obtained based on the fault types of the distribution network. The classification and processing of the protection action strategy includes: The similarity data between the backup strategy and the application strategy is determined, and the backup strategy is classified into different types based on the similarity data and the type classification threshold.

4. The method according to claim 1, characterized in that, The periodic frequency test is a periodic frequency test of a single protection action strategy. The test data obtained from any one of the periodic frequency tests includes the switching action frequency, the switching action frequency interval, and the voltage and current values ​​of the fault segment before and after each switching.

5. A classification device for executing a protective action strategy, characterized in that, include: The model building module is used to acquire distribution network data when a distribution network fault occurs, and to construct a simulated distribution network model in a virtual simulation space based on the distribution network data and distribution network distribution data. The target data loading module is used to determine the target data of the faulty area segment in the distribution network and load the target data into the simulated distribution network model. The target data includes the positions of each switch, historical switch operation frequencies, the time of the most recent switch operation, the current voltage value, and the current current value. The switch positions are the positions of all switches within the faulty area segment in the simulated distribution network model. The historical switch operation frequencies are the time period recorded in the historical target database prior to the current time point. The time of the most recent switch operation is the time of the switch operation preceding the current operation time recorded in the historical target database. The current voltage value and current current value are the voltage and current values ​​of the faulty area segment detected in real time by the instrument transformers, respectively. The test data acquisition module is used to acquire multiple execution protection action strategies, perform periodic frequency tests on the execution protection action strategies based on the mimicry distribution network model, and obtain test data corresponding to the execution protection action strategies. The level determination module includes: a fault indicator determination unit and a safety level determination unit; The fault indicator determination unit is used to identify faults in the test data obtained from multiple periodic frequency tests of the protection action strategy, and to determine the fault indicators of the protection action strategy based on the fault identification results of the multiple periodic frequency tests. The fault indicators include one or more of the following: fault rate, number of faults, fault point data, and repeated fault point data. The security level determination unit is used to determine the evaluation data of the execution protection action strategy based on the fault indicators of the execution protection action strategy, and to determine the security level of the execution protection action strategy based on the evaluation data and the security level threshold.

6. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the classification method for implementing protection action strategies as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the classification method of the execution protection action strategy according to any one of claims 1-4.

Images