Power distribution automation-based power grid fault self-recovery method and system
By collecting and analyzing real-time data in the distribution automation system, using deep learning models to predict faults and constructing network topology maps, rapid fault identification and isolation of distribution networks are achieved, and the problem of slow response of traditional distribution networks is solved, which improves the The stability of the power grid and the reliability of the power supply.
Patent Information
- Application Number
- CN202410963837.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-18
- Publication Date
- 2024-12-03
AI Technical Summary
Traditional distribution networks respond slowly in the face of faults, require manual intervention, and the power supply time is long. The existing technology has limitations in achieving comprehensive automation of fault self-healing, especially in the complex power grid structure to accurately predict faults, quickly locate them, and Intelligent decision-making.
By collecting real-time data in the distribution automation system, building a deep learning model to analyze historical fault data and current grid status, generating predicted probability of potential faults, establishing a network topology diagram, combining the prediction results and topology diagram to determine the fault segment, and Start the fault handler to isolate the fault point and perform contact switch operation to restore power supply.
It realizes rapid fault identification and isolation, reduces the risk of sudden failures, reduces unplanned downtime, enhances grid stability and safety, reduces maintenance costs, and significantly enhances power supply reliability and user experience.
Smart Images

Figure CN119070469A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of power system engineering, and in particular to a method and system for self-healing power grid faults based on distribution automation. Background Art
[0002] In recent years, with the transformation of power systems towards intelligence, distribution automation technology has become the key to improving the reliability, efficiency and flexibility of power grids. The main challenge facing traditional distribution networks is their passive response mode, that is, repairs can only be carried out after a fault occurs. This mode not only increases maintenance costs, but also affects the continuity and stability of power supply. The introduction of smart grids aims to achieve active management and optimization of distribution networks by integrating advanced information technology, control theory and communication technology. Among them, fault detection and self-healing capabilities based on real-time data collection and analysis are regarded as core competitiveness. Existing technologies still have limitations in achieving comprehensive automated fault self-healing, especially in accurately predicting faults, quickly locating faults and making intelligent decisions under complex power grid structures. Summary of the invention
[0003] In view of the above existing problems, the present invention is proposed.
[0004] Therefore, the present invention provides a method and system for self-healing power grid faults based on distribution automation to solve the problems of slow response, high demand for manual intervention and long power supply restoration time of traditional power grids when facing faults.
[0005] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0006] In a first aspect, an embodiment of the present invention provides a method for self-healing a power grid fault based on distribution automation, which includes collecting real-time data in a distribution automation system;
[0007] Upload real-time data to the power distribution substation through the wired network and pre-process it, then aggregate and send it to the power distribution master station;
[0008] Build a deep learning model to analyze historical fault data and current grid status to generate predictions of potential faults and their probability of occurrence;
[0009] The power distribution master station establishes a network topology diagram based on real-time data and prediction results;
[0010] Predict potential failures and their probability of occurrence and determine the fault section based on the network topology diagram;
[0011] The distribution master station starts the fault handling procedure, isolates the fault point, and at the same time closes the interconnecting switch in the non-fault section to restore power supply.
[0012] As a preferred solution of the method for self-healing power grid faults based on distribution automation described in the present invention, the real-time data includes voltage, current, active power, reactive power, power factor and electric energy of the power grid.
[0013] As a preferred solution of the method for self-healing power grid faults based on distribution automation described in the present invention, wherein: uploading real-time data to the distribution substation via the wired network and pre-processing and then summarizing and sending to the distribution master station, the specific steps are as follows:
[0014] Define the real-time data vector as: X(t) = [Xv(t), X i (t),X p (t),X q (t),X f (t),X e (t)];
[0015] Where X(t) represents the real-time data vector collected from the distribution automation system at time t, X v Indicates voltage, X i represents the current, X p Indicates active power, X q Represents reactive power, X f Indicates the power factor, X e Indicates electrical energy;
[0016] The collected raw data is preprocessed, and the expression is:
[0017]
[0018] in, represents the processed data vector, X(t) represents the real-time data vector collected at time t, x represents a random variable, μ represents the mean value of the data set, σ 2 represents variance;
[0019] Through the wired network, the distribution substation packages the pre-processed data and transmits it to the main distribution station.
[0020] As a preferred solution of the method for self-healing power grid faults based on distribution automation described in the present invention, a deep learning model is constructed to analyze historical fault data and current power grid status to generate predicted potential faults. The specific steps are as follows:
[0021] Through feature engineering, valuable features for fault prediction are extracted, and the expression is:
[0022]
[0023] in, represents the extracted features, Φ represents a feature conversion function, F represents the linear model, W represents the weight matrix, and b represents the bias vector;
[0024] Build a deep learning model, input historical fault data into the model, and generate predicted potential faults. The expression is:
[0025]
[0026] Among them, P(F s |X(t)) represents the prediction of potential failures, S represents a set of feature data points, s′ represents the equipment in the set S, and D s (t) represents the real-time monitoring data of device s at time point t, μs represents the historical average value of the monitoring data of device s, and σs2 represents the variance of the monitoring data of device s.
[0027] As a preferred solution of the method for self-healing power grid faults based on distribution automation described in the present invention, the distribution master station establishes a network topology diagram based on real-time data and prediction results. The specific operation steps are as follows:
[0028] The distribution master station receives real-time monitoring data and prediction results from the distribution substation;
[0029] Construct a prototype of the network topology diagram based on the physical connection relationship of the power distribution equipment;
[0030] Use the depth-first search algorithm to traverse all device nodes to form a complete network topology map.
[0031] As a preferred solution of the method for self-healing power grid faults based on distribution automation described in the present invention, the fault section is determined by combining the predicted probability of occurrence of potential faults with the network topology diagram. The specific operation steps are as follows:
[0032] In the topology diagram, starting from the switch closest to the power supply, along the direction of current flow, check the status of each switch step by step, detect and report the current passing through, and find the fault detection switch that detects the fault current;
[0033] As a preferred solution of the method for self-healing a fault in a power distribution automation network according to the present invention, the power distribution master station starts a fault handling program to isolate the fault point and closes the tie switch in the non-fault section to restore power supply. The specific operation steps are as follows:
[0034] The power distribution master station automatically starts the fault isolation program, disconnects the switch equipment near the fault point through remote control, monitors the switch status, confirms that all designated switches are successfully disconnected, forms a fault isolation area, and updates the switch status through the network topology map;
[0035] After isolating the fault, the distribution master station will automatically find the optimal path, reconfigure the grid structure, restore power supply to the non-faulty sections, monitor the switch status, confirm that the interconnecting switch is successfully closed, restore normal power supply to the non-faulty sections, and update the switch status through the network topology diagram.
[0036] In a second aspect, the present invention provides a self-healing system for power grid faults based on distribution automation, including: a data transmission and preprocessing module: collecting real-time data in the distribution automation system, uploading the real-time data to the distribution substation through a wired network and preprocessing the data, and then aggregating and sending the data to the distribution master station;
[0037] Deep learning analysis module: Build a deep learning model to analyze historical fault data and current grid status, and generate predictions of potential faults and their probability of occurrence;
[0038] Network topology building module: The power distribution master station builds a network topology map based on real-time data and prediction results;
[0039] Fault determination and isolation module: predicts potential faults and their probability of occurrence and determines the fault section based on the network topology diagram. The power distribution master station starts the fault handling procedure and isolates the fault point.
[0040] Power supply restoration control module: closes the contact switch in the non-fault section to restore power supply.
[0041] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the method for self-healing of distribution automation power grid faults based on the first aspect of the present invention is implemented.
[0042] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the method for self-healing of distribution automation power grid faults based on the first aspect of the present invention is implemented.
[0043] The beneficial effects of the present invention are as follows: through real-time data collection and preprocessing, the immediate feedback of the power grid status is enhanced, the data quality and accuracy are improved, and a solid foundation is laid for fault prediction. Deep learning technology is used to extract key features and build a prediction model to achieve forward-looking identification of power grid anomalies, reduce the risk of sudden failures, reduce unplanned downtime, enhance power grid stability and security, and reduce maintenance costs. The dynamic network topology map assists in accurately locating faults, combines predictions with measured data, accelerates fault determination, and improves the efficiency and intelligence of fault management. Automated isolation and rapid recovery strategies can effectively curb the spread of faults, ensure continuous power supply in non-fault areas, significantly reduce the scope of power outages, achieve self-healing of the power grid, significantly enhance power supply reliability, optimize user experience, and reduce operational risks. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use 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 ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0045] Figure 1 This is a flow chart of the method for self-healing power grid faults based on distribution automation in Example 1.
[0046] Figure 2 This is a determination diagram based on distribution automation grid fault in Example 1. DETAILED DESCRIPTION
[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0050] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a method for self-healing a fault in a power distribution automation network, comprising the following steps:
[0051] S1. Collect real-time data in the distribution automation system, including the voltage, current, active power, reactive power, power factor and electric energy of the power grid.
[0052] S2, upload real-time data to the power distribution substation through the wired network and pre-process it, then send it to the power distribution master station after aggregation. The specific steps are as follows:
[0053] Define the real-time data vector as: X(t) = [Xv(t), X i (t),X p (t),X q (t),X f(t),X e (t)];
[0054] Where X(t) represents the real-time data vector collected from the distribution automation system at time t, X v Indicates voltage, X i represents the current, X p Indicates active power, X q Reactive power, X f Power factor, X e Indicates electrical energy;
[0055] The collected raw data is preprocessed, and the expression is:
[0056]
[0057] in, represents the processed data vector, X(t) represents the real-time data vector collected at time t, x represents a random variable, μ represents the mean value of the data set, σ 2 represents variance;
[0058] Through the wired network, the distribution substation packages the pre-processed data and transmits it to the main distribution station.
[0059] S3. Build a deep learning model to analyze historical fault data and current grid status and generate predictions of potential faults. The specific steps are as follows:
[0060] Through feature engineering, valuable features for fault prediction are extracted, and the expression is:
[0061]
[0062] in, represents the extracted features, Φ represents a feature conversion function, F represents the linear model, W represents the weight matrix, and b represents the bias vector;
[0063] Build a deep learning model, input historical fault data into the model, and generate predicted potential faults. The expression is:
[0064]
[0065] Among them, P(F s |X(t)) represents the prediction of potential failures, S represents a set of devices, s′ represents a device in the set S, s′ represents a device in the set S, D s (t) represents the real-time monitoring data of device s at time point t, μ s represents the historical average value of monitoring data of device s, σ s 2 Indicates the variance of the monitoring data of device s.
[0066] S4. The power distribution master station establishes a network topology diagram based on real-time data and prediction results. The specific steps are as follows:
[0067] The distribution master station receives real-time monitoring data and prediction results from the distribution substation.
[0068] Based on the physical connection relationship of the power distribution equipment, a prototype of the network topology is constructed.
[0069] Furthermore, the distribution master station collects the location and connection methods of transformers, circuit breakers, disconnectors, capacitors, and reactors, analyzes the physical connection relationships between the devices, determines the devices that need to be directly connected, and based on the collected connection relationships, preliminarily draws a sketch of the network, where each node represents a device and the edge represents the direct connection between the devices.
[0070] Use the depth-first search algorithm to traverse all device nodes to form a complete network topology map.
[0071] Furthermore, the depth-first search algorithm will help us start from a starting point, explore each path until we encounter a visited node, and then backtrack and continue to explore other unvisited paths until all nodes have been visited. At this point, the depth-first search algorithm effectively traverses all device nodes and forms a complete network topology graph.
[0072] S5. By combining the predicted probability of potential faults with the network topology, the fault section is determined. The specific steps are as follows:
[0073] In the topology diagram, starting from the switch closest to the power supply, along the direction of current flow, check the status of each switch step by step, detect and report the current passing through, and find the fault detection switch that detects the fault current;
[0074] After finding the fault detection switch, continue to detect the next level switch adjacent to the fault detection switch to find the non-fault detection switch that cannot detect the fault current;
[0075] Furthermore, the system starts from the switch closest to the power source, and checks the switch status and current conditions in the power grid step by step along the normal flow direction of the current, that is, from the power source to the load. Searching along the current path can locate the fault point more effectively. The system will check the status of each switch one by one. For each switch checked, the system will detect and report the current passing through. If the current value deviates significantly from the normal range, it is a signal of a fault. If an abnormal current is detected, the system will mark the switch as a fault detection switch, which means that a fault has occurred downstream of the switch. The system will mark the location of the fault detection switch on the topology map and record its status and current readings as a basis for fault location and analysis. After identifying the fault detection switch, the system will continue to detect the next-level switch adjacent to the fault detection switch along the direction of current flow. Normal current is detected in the next-level switch, which means that the switch is not part of the fault but a non-fault detection switch.
[0076] The line between the fault detection switch and the non-fault detection switch is defined as a fault section.
[0077] S6. The distribution master station starts the fault handling procedure, isolates the fault point, and closes the tie switch in the non-fault section to restore power supply. The specific operation steps are as follows:
[0078] The power distribution master station automatically starts the fault isolation program, disconnects the switch equipment near the fault point through remote control, monitors the switch status, confirms that all designated switches are successfully disconnected, forms a fault isolation area, and updates the switch status through the network topology map;
[0079] After isolating the fault, the distribution master station will automatically find the optimal path, reconfigure the grid structure, restore power supply to the non-faulty sections, monitor the switch status, confirm that the interconnecting switch is successfully closed, restore normal power supply to the non-faulty sections, and update the switch status through the network topology diagram.
[0080] This embodiment also provides a distribution automation-based power grid fault self-healing system, including:
[0081] Data transmission and preprocessing module: collects real-time data in the distribution automation system, uploads the real-time data to the distribution substation through the wired network and preprocesses it, and then aggregates and sends it to the distribution master station;
[0082] Deep learning analysis module: Build a deep learning model to analyze historical fault data and current grid status, and generate predictions of potential faults and their probability of occurrence;
[0083] Network topology building module: The power distribution master station builds a network topology map based on real-time data and prediction results;
[0084] Fault determination and isolation module: predicts potential faults and their probability of occurrence and determines the fault section based on the network topology diagram. The power distribution master station starts the fault handling procedure and isolates the fault point.
[0085] Power supply restoration control module: closes the contact switch in the non-fault section to restore power supply.
[0086] This embodiment also provides a computer device, which is suitable for the case of a self-healing method for power grid faults based on distribution automation, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the self-healing method for power grid faults based on distribution automation as proposed in the above embodiment.
[0087] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0088] The present embodiment also provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for self-healing of power grid faults based on distribution automation as proposed in the above embodiment; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk.
[0089] In summary, the present invention improves data quality and accuracy by strengthening the instant feedback of the power grid status, laying a solid foundation for fault prediction. Deep learning technology is used to extract key features and build a prediction model to achieve forward-looking identification of power grid anomalies, reduce the risk of sudden failures, reduce unplanned downtime, enhance power grid stability and security, and reduce maintenance costs. Dynamic network topology maps assist in accurately locating faults, combine predictions with measured data, accelerate fault determination, and improve fault management efficiency and intelligence. Automated isolation and rapid recovery strategies can effectively curb the spread of faults, ensure continuous power supply in non-fault areas, significantly reduce the scope of power outages, achieve self-healing of the power grid, significantly enhance power supply reliability, optimize user experience, and reduce operational risks.
[0090] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data based on the distribution automation grid fault self-healing method are provided.
[0091] Firstly, the fault self-healing process of a small urban power grid is simulated, which contains three substations, ten feeders, twenty switches and one hundred user nodes. In the experiment, in order to verify the effectiveness of the fault self-healing method based on distribution automation.
[0092] We designed a fault scenario: Feeder 3 suddenly short-circuited at a certain moment, causing power outages for some users. The real-time data used in the experiment include voltage, current, active power, reactive power, power factor, and electric energy. These data are collected once a second by the real-time data acquisition module, as shown in the following table:
[0093] Table 1 Experimental object data classification and marking table before and after failure
[0094]
[0095] By comparing the data of the normal feeder and the faulty feeder, it can be seen that the parameters of feeder 3 changed significantly before and after the fault occurred. Before the fault, the average voltage of feeder 3 was 220.0V and the average current was 2.5A, which are similar to those of the normal feeder. However, after the fault occurred, the average voltage of feeder 3 dropped sharply to 100.2V, the average current surged to 15.0A, the active power and reactive power also increased significantly, and the power factor dropped significantly to 0.60. These data show that feeder 3 did suffer a serious short circuit fault, resulting in a decrease in voltage and a sharp increase in current.
[0096] In contrast, the parameters of normal feeders such as feeder 1 and feeder 2 change slightly and remain stable, showing good power supply quality. Through this experiment, the effectiveness of the self-healing method based on distribution automation grid faults was verified, especially in fault detection and isolation. This method can identify the fault point in a timely and accurate manner, quickly isolate the fault through remote control operation, avoid the spread of the fault, and ensure the normal power supply of users in the non-fault section, fully demonstrating its significant advantages in improving the stability of grid operation and reducing the time and scope of power outages.
[0097] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention 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 invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A self-healing method for power grid faults based on distribution automation, It is characterized in that include: Collect real-time data in distribution automation systems; Upload real-time data to the power distribution substation through the wired network and pre-process it, then aggregate and send it to the power distribution master station; Build a deep learning model to analyze historical fault data and current grid status to generate predictions of potential faults and their probability of occurrence; The power distribution master station establishes a network topology diagram based on real-time data and prediction results; Predict potential failures and their probability of occurrence and determine the fault section based on the network topology diagram; The distribution master station starts the fault handling procedure, isolates the fault point, and at the same time closes the interconnecting switch in the non-fault section to restore power supply.
2. The method for self-healing a power grid fault based on distribution automation as claimed in claim 1, It is characterized in that The real-time data includes the voltage, current, active power, reactive power, power factor and electric energy of the power grid.
3. The method for self-healing a power grid fault based on distribution automation as claimed in claim 2, It is characterized in that The specific steps of uploading real-time data to the power distribution substation through the wired network and pre-processing and then summarizing and sending it to the power distribution master station are as follows: Define the real-time data vector as: X(t) = [Xv(t), X i (t),X p (t),X q (t),X f (t),X e (t)]; Where X(t) represents the real-time data vector collected from the distribution automation system at time t, X v Indicates voltage, X i represents the current, X p Indicates active power, X q Represents reactive power, X f Indicates the power factor, X e Indicates electrical energy; The collected raw data is preprocessed, and the expression is: in, represents the processed data vector, X(t) represents the real-time data vector collected at time t, x represents a random variable, μ represents the mean value of the data set, σ 2 represents variance; Through the wired network, the distribution substation packages the pre-processed data and transmits it to the main distribution station.
4. The method for self-healing a power grid fault based on distribution automation as claimed in claim 3, It is characterized in that Build a deep learning model to analyze historical fault data and current grid status to generate predictions of potential faults. The specific steps are as follows: Through feature engineering, valuable features for fault prediction are extracted, and the expression is: in, represents the extracted features, Φ represents a feature conversion function, F represents the linear model, W represents the weight matrix, and b represents the bias vector; Build a deep learning model, input historical fault data into the model, and generate predicted potential faults. The expression is: Among them, P(F s |X(t)) represents the prediction of potential failures, S represents a set of devices, s′ represents the device in the set S, and D s (t) represents the real-time monitoring data of device s at time point t, μs represents the historical average value of the monitoring data of device s, and σ s 2 Indicates the variance of the monitoring data of device s.
5. The method for self-healing a power grid fault based on distribution automation as claimed in claim 4, It is characterized in that The power distribution master station establishes a network topology diagram based on real-time data and prediction results. The specific steps are as follows: The distribution master station receives real-time monitoring data and prediction results from the distribution substation; Construct a prototype of the network topology diagram based on the physical connection relationship of the power distribution equipment; Use the depth-first search algorithm to traverse all device nodes to form a complete network topology map.
6. The method for self-healing a power grid fault based on distribution automation as claimed in claim 5, It is characterized in that By predicting the probability of potential faults and combining it with the network topology, the fault section can be determined. The specific steps are as follows: In the topology diagram, starting from the switch closest to the power supply, along the direction of current flow, check the status of each switch step by step, detect and report the current passing through, and find the fault detection switch that detects the fault current; After finding the fault detection switch, continue to detect the next level switch adjacent to the fault detection switch to find the non-fault detection switch that cannot detect the fault current; The line between the fault detection switch and the non-fault detection switch is defined as a fault section.
7. The method for self-healing a power grid fault based on distribution automation as claimed in claim 6, It is characterized in that The distribution master station starts the fault handling procedure, isolates the fault point, and closes the contact switch of the non-fault section to restore power supply. The specific operation steps are as follows: The power distribution master station automatically starts the fault isolation program, disconnects the switch equipment near the fault point through remote control, monitors the switch status, confirms that all designated switches are successfully disconnected, forms a fault isolation area, and updates the switch status through the network topology map; After isolating the fault, the distribution master station will automatically find the optimal path, reconfigure the grid structure, restore power supply to the non-faulty sections, monitor the switch status, confirm that the interconnecting switch is successfully closed, restore normal power supply to the non-faulty sections, and update the switch status through the network topology diagram.
8. A distribution automation grid fault self-healing system, based on the distribution automation grid fault self-healing method according to any one of claims 1 to 7, It is characterized in that include, Data transmission and preprocessing module: collects real-time data in the distribution automation system, uploads the real-time data to the distribution substation through the wired network and preprocesses it, and then aggregates and sends it to the distribution master station; Deep learning analysis module: Build a deep learning model to analyze historical fault data and current grid status, and generate predictions of potential faults and their probability of occurrence; Network topology building module: The power distribution master station builds a network topology map based on real-time data and prediction results; Fault determination and isolation module: predicts potential faults and their probability of occurrence and determines the fault section based on the network topology diagram. The power distribution master station starts the fault handling procedure and isolates the fault point. Power supply restoration control module: closes the contact switch in the non-fault section to restore power supply.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program. Features: When the processor executes the computer program, the steps of the method for self-healing of distribution automation power grid faults according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, Features: When the computer program is executed by a processor, the steps of the method for self-healing a distribution automation power grid fault according to any one of claims 1 to 7 are implemented.
Citation Information
Cited By
Beidou synchronous power distribution automation device and power distribution implementation method
CN120879612A
