Intelligent operation and maintenance method for self-healing line of power distribution network based on terminal data and related device

Abstract

The embodiment of the invention relates to the field of data processing and power grid control, and provides a power distribution network self-healing line intelligent operation and maintenance method based on terminal data and a related device, and the method comprises the steps: obtaining the real-time operation data of a power grid from a terminal device disposed at a key node of the power distribution network; performing data preprocessing on the real-time operation data to obtain first operation data; performing operation state prediction processing on the power distribution network by adopting the first operation data to obtain predicted operation state information; generating control information of key nodes of the power distribution network according to the predicted operation state information; and sending the control information to a control device of a corresponding key node of the power distribution network, so as to indicate the control device to control the key node of the power distribution network through the control information, and carrying out state prediction according to the collected real-time operation data of the power grid to obtain predicted operation state information. And the node control information is generated to control the power distribution network nodes, so that the control accuracy of the power distribution network nodes is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data processing and power grid control, and specifically to a method and related device for intelligent operation and maintenance of self-healing lines in a distribution network based on terminal data. Background Art

[0002] With the increase in the coverage of self-healing lines, more and more self-healing lines and equipment need to be maintained. However, the traditional distribution network operation and maintenance mode mainly relies on manual regular inspection and maintenance, which has many limitations. First, manual inspection is not only inefficient, but also difficult to respond to the rapidly changing power grid conditions in real time, especially in remote areas or under severe weather conditions, resulting in long power outages and wide impact ranges, which seriously affects the stability and reliability of power supply. Secondly, the lack of effective adaptive configuration means makes it impossible for the system to actively adjust the operation strategy according to the load change trend and potential failure mode, further aggravating the difficulty and cost of operation and maintenance. In addition, with the increase in the proportion of new energy access and the advancement of power market reform, the distribution network operation environment has become more complex and changeable, which puts higher requirements on operation and maintenance management. Although a large number of research and practical results have emerged in the field of intelligent and automated distribution network operation and maintenance, there are still some problems that need to be solved. The research on adaptive configuration strategy is not deep and complete enough, and it is difficult to meet the complex and changeable distribution network operation requirements, which makes the accuracy of controlling the key nodes of the distribution network low. Summary of the invention

[0003] The embodiments of the present application provide a method and related devices for intelligent operation and maintenance of self-healing lines of a distribution network based on terminal data, which can perform status prediction based on the collected real-time operation data of the power grid to obtain predicted operation status information, and generate node control information to control the distribution network nodes, thereby improving the accuracy of controlling the distribution network nodes.

[0004] A first aspect of an embodiment of the present application provides a method for intelligent operation and maintenance of a self-healing line of a distribution network based on terminal data, the method comprising:

[0005] Obtain real-time operation data of the power grid from terminal devices deployed at key nodes of the distribution network;

[0006] Performing data preprocessing on the real-time operation data to obtain first operation data;

[0007] Using the first operating data to perform operating state prediction processing on the distribution network to obtain predicted operating state information;

[0008] Generate control information of key nodes of the distribution network according to the predicted operating status information;

[0009] The control information is sent to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

[0010] In this example, real-time operation data of the power grid is obtained from terminal devices deployed at key nodes of the distribution network, data preprocessing is performed on the real-time operation data to obtain first operation data, the operation status of the distribution network is predicted using the first operation data to obtain predicted operation status information, control information of the key nodes of the distribution network is generated according to the predicted operation status information, and the control information is sent to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information. Therefore, state prediction can be performed based on the collected real-time operation data of the power grid to obtain predicted operation status information, so as to generate node control information to control the distribution network nodes, thereby improving the accuracy of controlling the distribution network nodes.

[0011] In a possible implementation, preprocessing the real-time operation data to obtain first operation data includes:

[0012] Performing data cleaning on the real-time operation data to obtain first reference operation data;

[0013] Normalizing the first reference running data to obtain second reference running data;

[0014] Perform feature extraction processing on the second reference operating data to obtain first operating data.

[0015] In a possible implementation, the predicted operating state information includes predicted operating load information and predicted power consumption information, and the using of the first operating data to perform operating state analysis on the distribution network to obtain the operating state information includes:

[0016] Using the first operation data to perform load forecasting through a preset operation load forecasting model to obtain forecast operation load information;

[0017] The power consumption prediction is performed by using the first operating data through a preset power consumption prediction model to obtain the predicted power consumption information.

[0018] In a possible implementation, generating control information of key nodes of the distribution network according to the predicted operating status information includes:

[0019] The optimal control sequence is solved according to the predicted operating load information, the predicted power consumption information and the operating status information of the current distribution network in the predicted operating status information to obtain the control information of the key nodes of the corresponding distribution network.

[0020] In a possible implementation, after sending the control information to the corresponding key node of the distribution network, the method further includes:

[0021] Obtaining grid control and operation feedback information from terminal devices deployed at key nodes of the distribution network;

[0022] The preset operation load prediction model and the preset power consumption prediction model are optimized according to the control operation feedback information to obtain an optimized preset operation load prediction model and an optimized preset power consumption prediction model.

[0023] A second aspect of an embodiment of the present application provides a distribution network self-healing line intelligent operation and maintenance device based on terminal data, the device comprising:

[0024] An acquisition unit, used to acquire real-time operation data of the power grid from terminal devices deployed at key nodes of the distribution network;

[0025] A preprocessing unit, used for performing data preprocessing on the real-time operation data to obtain first operation data;

[0026] A prediction unit, configured to use the first operation data to perform operation state prediction processing on the distribution network to obtain predicted operation state information;

[0027] A generating unit, configured to generate control information of key nodes of the distribution network according to the predicted operating status information;

[0028] The sending unit is used to send the control information to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

[0029] In a possible implementation, the preprocessing unit is specifically used to:

[0030] Performing data cleaning on the real-time operation data to obtain first reference operation data;

[0031] Normalizing the first reference running data to obtain second reference running data;

[0032] Perform feature extraction processing on the second reference operating data to obtain first operating data.

[0033] In a possible implementation, the predicted operating state information includes predicted operating load information and predicted power consumption information, and the prediction unit is specifically used to:

[0034] Using the first operation data to perform load forecasting through a preset operation load forecasting model to obtain forecast operation load information;

[0035] The power consumption prediction is performed by using the first operating data through a preset power consumption prediction model to obtain the predicted power consumption information.

[0036] In a possible implementation, the generating unit is specifically configured to:

[0037] The optimal control sequence is solved according to the predicted operating load information, the predicted power consumption information and the operating status information of the current distribution network in the predicted operating status information to obtain the control information of the key nodes of the corresponding distribution network.

[0038] In a possible implementation, after sending the control information to the corresponding key node of the distribution network, the device is further used to:

[0039] Obtaining grid control and operation feedback information from terminal devices deployed at key nodes of the distribution network;

[0040] The preset operation load prediction model and the preset power consumption prediction model are optimized according to the control operation feedback information to obtain an optimized preset operation load prediction model and an optimized preset power consumption prediction model.

[0041] A third aspect of an embodiment of the present application provides a server, comprising a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0042] The fourth aspect of the embodiments of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application.

[0043] A fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described in the first aspect of the embodiments of the present application. The computer program product may be a software installation package. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0045] Figure 1 A schematic diagram of the structure of a distribution network self-healing line intelligent operation and maintenance system based on terminal data is provided for an embodiment of the present application;

[0046] Figure 2 A schematic diagram of a process flow of a distribution network self-healing line intelligent operation and maintenance method based on terminal data is provided for an embodiment of the present application;

[0047] Figure 3 A schematic diagram of the structure of a server provided in an embodiment of the present application;

[0048] Figure 4 A structural schematic diagram of a distribution network self-healing line intelligent operation and maintenance device based on terminal data is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0051] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments.

[0052] In order to better understand the intelligent operation and maintenance method of distribution network self-healing lines based on terminal data provided by an embodiment of the present application, the following is a brief introduction to the distribution network operation and maintenance method in the existing scheme. Intelligent operation and maintenance of distribution network self-healing lines involves multiple aspects of technology. In terms of adaptive configuration, an intelligent distributed protection method for adaptive distribution network topology and switch configuration is provided in the existing scheme. The method first uses online topology analysis technology to capture the operating dynamics of the distribution network in real time and deeply understand the changing trend of the network structure; then, based on the coordination requirements between the switching devices, the timing distance of each switch is scientifically defined, and the action timing constant that meets all timing coordination requirements is determined by accurately calculating the maximum timing distance. This method provides a new research direction and practical path for the development of distribution network protection technology.

[0053] Although this method aims to capture the operating dynamics of the distribution network in real time, in actual applications, due to the large scale of the network and the large amount of data, real-time processing and response may face delay problems; once the timing distance and action timing setting of the switch are set, the system may find it difficult to quickly adapt to emergencies or unexpected network changes.

[0054] In terms of distribution network operation and maintenance, the existing solution provides a method for improving distribution network operation and maintenance technology based on deep learning. This method constructs an upgraded version of the Residual Neural Network (ResNet) architecture by optimizing the residual module in the Residual Neural Network (ResNet) model, effectively enhancing the model's ability to capture complex fault signals. In the specific implementation, the distribution network operation and maintenance fault signal characteristics processed by signal processing technology (E-VMD) are used as input and sent to the improved ResNet model for deep learning and analysis, thereby achieving high-precision recognition of common fault types such as single-phase grounding, two-phase short circuit and three-phase short circuit in distribution network operation and maintenance.

[0055] The deep learning models of this method, especially complex neural networks, are often regarded as "black boxes" and their decision-making process lacks transparency, which is not conducive to fault diagnosis and trust building; without appropriate regularization measures, deep learning models may overfit the training data, resulting in poor performance on new or unseen data.

[0056] In order to solve the above-mentioned technical problems, an embodiment of the present application provides a method for intelligent operation and maintenance of distribution network self-healing lines based on terminal data, which can perform status prediction based on the collected real-time operation data of the power grid to obtain predicted operation status information, generate node control information to control the distribution network nodes, and improve the accuracy of control of the distribution network nodes.

[0057] Figure 1 The figure shows a schematic diagram of the structure of a distribution network self-healing line intelligent operation and maintenance system based on terminal data. Figure 1As shown, the terminal data-based distribution network self-healing line intelligent operation and maintenance system includes: a server 1 and a terminal device 2, the terminal device 2 is arranged at a key node 3 of the distribution network, and the key node 3 of the distribution network includes a substation outlet, a main branch point, a trunk line, a user access point and a specific environmental area. The terminal device 2 can be an intelligent switch, a fault indicator, a distribution automation terminal, etc. The control equipment of the key node 3 of the distribution network includes switches, circuit breakers, etc. The terminal device 2 can obtain the real-time operation data of the power grid, and the real-time operation data includes the voltage, current, fault signal, environmental detection data, remote control operation feedback data, etc. of the key node 3 of the distribution network. After the terminal device 2 performs preliminary processing on the acquired real-time operation data, it sends it to the server 1. After receiving the real-time operation data, the server 1 pre-processes the real-time operation data to obtain the first operation data, and then uses the first operation data to predict the operation state of the distribution network to obtain the predicted operation state information, and then generates the control information of the key node 3 of the distribution network according to the predicted operation state information, and finally sends the control information to the control device of the corresponding key node 3 of the distribution network to instruct the control device to control the key node 3 of the distribution network through the control information. Therefore, it is possible to perform state prediction based on the real-time operation data of the collected power grid to obtain the predicted operation state information, and generate node control information to control the distribution network nodes, thereby improving the accuracy of the distribution network nodes when being controlled.

[0058] See also Figure 2 , Figure 2 The present application provides a flow chart of a method for intelligent operation and maintenance of a distribution network self-healing line based on terminal data. Figure 2 As shown, the method is applied to the intelligent operation and maintenance system of the distribution network self-healing line based on terminal data, and the method includes:

[0059] 201. Obtain real-time operation data of the power grid from terminal devices deployed at key nodes of the distribution network.

[0060] In the process of intelligentization of power distribution network, terminal equipment is an important foundation for realizing the automation of power distribution network. It can transmit power distribution information in real time and accurately, thereby greatly improving the safety performance and operation efficiency of power distribution network. These terminal equipments are of various types, mainly including intelligent switches, fault indicators, distribution automation terminals, etc. They are carefully arranged at each key node of the power grid, such as substation exit, main branch points, trunk lines, user access points and specific environmental areas, forming a monitoring network covering the entire power grid. These terminal equipments are responsible for collecting a series of key information (real-time operation data), including voltage, current, fault signals, environmental monitoring data, self-healing switch feeder information and remote control operation feedback. These data are a direct reflection of the operation status of the power grid, which is crucial for real-time monitoring, fault diagnosis and subsequent data analysis.

[0061] Among them, after the terminal device obtains the real-time operation data, it performs preliminary processing on the real-time operation data. Specifically, the terminal device uses edge computing and cloud computing technology to statistically summarize the collected real-time operation data, effectively eliminate noise and outliers, and thus significantly improve the quality and availability of the data. This process lays a solid foundation for the subsequent distribution network operation feature extraction, adaptive configuration, and automated control execution.

[0062] The process of using edge computing and cloud computing technologies to process and analyze real-time operation data is as follows:

[0063] Edge computing technology is used to perform preliminary processing on the real-time operation data collected by terminal devices, including data cleaning, denoising, outlier detection, etc., to improve the accuracy and reliability of the data.

[0064] The pre-processed real-time operation data is uploaded to the server for centralized storage and management. The cloud computing platform provides powerful storage capacity and efficient data processing capabilities to ensure data security and accessibility.

[0065] The server can receive real-time operation data sent by the terminal device after preliminary processing. The real-time operation data includes voltage, current, fault signals, environmental detection data, remote control operation feedback data, etc. at key nodes of the distribution network.

[0066] 202. Perform data preprocessing on the real-time operation data to obtain first operation data.

[0067] After receiving the real-time operation data, the server pre-processes it to obtain first operation data, specifically, it can perform data cleaning, normalization and feature extraction on the real-time operation data to obtain the first operation data. The first operation data is feature data obtained by feature extraction.

[0068] After data cleaning and normalization of the real-time operation data, useful information and patterns can be extracted from the massive real-time operation data, including descriptive statistics (such as mean, variance, etc.) and inferential statistics (such as regression analysis, hypothesis testing, etc.), so as to obtain the first operation data.

[0069] Specifically, the method for extracting useful information and patterns can be:

[0070] Through in-depth analysis of key parameters such as voltage, current, and power factor, characteristic information such as load change trends and fault modes can be discovered. For example, during peak load periods, by monitoring changes in voltage and current, potential overload risks can be identified; and when a fault occurs, by analyzing abnormal fluctuations in current and power factor, the fault point can be quickly located and corresponding emergency measures can be taken, and preparations can be made for self-healing when necessary.

[0071] By collecting statistics and analyzing the self-healing switches, self-healing lines and other information involved in the self-healing information (first operation data), the operation strategy and maintenance plan of the distribution network can be further optimized. For example: if a self-healing switch frequently fails to operate or the response time is too long, it may be necessary to inspect it or replace other switches for self-healing; if a line triggers the self-healing function multiple times in a short period of time, but the self-healing fails, it may be necessary to reselect the switch or line. In this regard, the self-healing type of the switch is divided into local self-healing type, master station self-healing type, emergency control type, and recovery control type to facilitate the subsequent adaptive configuration of the self-healing type of the distribution network.

[0072] 203. Use the first operating data to perform operating status prediction processing on the distribution network to obtain predicted operating status information.

[0073] The predicted operation state information may be obtained by using a preset prediction model to perform prediction processing based on the first operation data. The predicted operation state information includes predicted operation load information and predicted power consumption information. The preset prediction model includes a preset operation load prediction model and a preset power consumption prediction model, and the preset prediction model is a pre-trained model used to predict the corresponding predicted operation state information.

[0074] Specifically, based on the extracted distribution network operation characteristic information, the model predictive control (MPC) algorithm is used to construct a mathematical model of the power grid operation and predict the state of the power grid in the future. Based on these prediction results (predicted operation status information), the MPC algorithm can accurately adjust the operation strategy of the distribution network, such as power generation plan, load distribution, etc. For example: when it is predicted that the load demand will increase in a certain period of time in the future, the power generation will be adjusted in advance to meet the demand; when it is predicted that the load risk is high, the load distribution will be optimized to reduce the probability of failure.

[0075] However, when a line fault is detected, the system can automatically switch to the backup line to ensure the continuity of power supply. This involves the adaptive configuration of the self-healing type, including the adaptive selection of self-healing switches and feeders:

[0076] Matching the self-healing type of the switch: Through the extraction of the distribution network operation feature in step 202, the self-healing switch type in the feature is compared with the current switch self-healing type to find the most matching self-healing type of these switches; if a switch has four functions of telemetry, telesignaling, remote control, and remote adjustment, the self-healing type of the switch can be determined directly by calling the "switch self-healing type" constant. For example: there is a switch S1 in the distribution network, and its feature extracts key parameters such as the action time, recovery time and success rate of the switch. Comparing these data with the current self-healing type, it is found that the characteristics of S1 are closest to the characteristics of the voltage-time type self-healing type, so the self-healing type of S1 is determined to be the local type. If switch S1 has been transformed into a four-remote system, then its "switch self-healing type" constant can be directly read through remote communication. Assuming that the constant called from S1 shows that its self-healing type is the main station self-healing type, then it can be determined that the self-healing type of S1 is the main station self-healing type.

[0077] Feeder self-healing type matching: The self-healing type of a feeder is determined based on the self-healing type of each switch on it. If all switches on a feeder belong to the same self-healing type, then the self-healing type of the feeder is this type; if there are two or more different self-healing types on a feeder, then the feeder is defined as a mixed self-healing type.

[0078] Self-healing type matching in special cases: In some areas, if the feature information extracted by all terminal devices is consistent with the current type, the self-healing type of the feeder can be configured according to actual needs. The switches along the line will automatically match and adjust according to this type, which facilitates the configuration of the self-healing type.

[0079] 204. Generate control information of key nodes of the distribution network according to the predicted operating status information.

[0080] Among them, the optimal control sequence can be solved according to the predicted operating load information, predicted power consumption information and the operating status information of the current distribution network in the predicted operating status information to obtain the control information of the key nodes of the distribution network. The optimal control sequence can be solved by adopting a general liberation assumption to obtain the control information of the key nodes of the distribution network.

[0081] Specifically, based on the predicted operating load information, predicted power consumption information and the current operating status information of the distribution network, the model predictive control (MPC) algorithm can accurately adjust the operating strategy of the distribution network, such as power generation plan, load distribution, etc. For example, when a line fault is detected, the system can automatically switch to the backup line to ensure the continuity of power supply. When it is predicted that the load demand will increase in a certain period of time in the future, the power generation will be adjusted in advance to meet the demand; when it is predicted that the load risk is high, the load distribution will be optimized to reduce the probability of failure.

[0082] By adaptively configuring the control information of key nodes in the distribution network, the distribution network can respond to various complex situations more flexibly and improve the adaptability and flexibility of the system. Adaptive configuration can realize intelligent management of the distribution network and improve the operating efficiency and economy of the distribution network. Adaptive configuration helps to reduce the failure rate of the distribution network and improve the stability and reliability of power supply.

[0083] Specifically, based on these prediction results (predicted operating status information), the MPC algorithm can accurately adjust the distribution network's operating strategy, such as power generation planning, load distribution, etc. For example, when it is predicted that the load demand will increase in a certain period of time in the future, the power generation will be adjusted in advance to meet the demand; when it is predicted that the load risk is high, the load distribution will be optimized to reduce the probability of failure.

[0084] However, when a line fault is detected, the system can automatically switch to the backup line to ensure the continuity of power supply. This involves the adaptive configuration of the self-healing type, including the adaptive selection of self-healing switches and feeders:

[0085] Matching the self-healing type of the switch: Through the extraction of the distribution network operation feature in step 202, the self-healing switch type in the feature is compared with the current switch self-healing type to find the most matching self-healing type of these switches; if a switch has four functions of telemetry, telesignaling, remote control, and remote adjustment, the self-healing type of the switch can be determined directly by calling the "switch self-healing type" constant. For example: there is a switch S1 in the distribution network, and its feature extracts key parameters such as the action time, recovery time and success rate of the switch. Comparing these data with the current self-healing type, it is found that the characteristics of S1 are closest to the characteristics of the voltage-time type self-healing type, so the self-healing type of S1 is determined to be the local type. If switch S1 has been transformed into a four-remote system, then its "switch self-healing type" constant can be directly read through remote communication. Assuming that the constant called from S1 shows that its self-healing type is the main station self-healing type, then it can be determined that the self-healing type of S1 is the main station self-healing type.

[0086] Feeder self-healing type matching: The self-healing type of a feeder is determined based on the self-healing type of each switch on it. If all switches on a feeder belong to the same self-healing type, then the self-healing type of the feeder is this type; if there are two or more different self-healing types on a feeder, then the feeder is defined as a mixed self-healing type.

[0087] Self-healing type matching in special cases: In some areas, if the feature information extracted by all terminal devices is consistent with the current type, the self-healing type of the feeder can be configured according to actual needs. The switches along the line will automatically match and adjust according to this type, which facilitates the configuration of the self-healing type.

[0088] 205. Send the control information to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

[0089] In order to reduce manual intervention and improve operational efficiency and safety, remote communication technology can be used to send the control information of the adaptive configuration of the distribution network to the control devices of each key node of the distribution network, such as switches and circuit breakers, in real time, to achieve remote control and automated operation of them; then the Internet of Things technology can be used to connect each control device to a unified platform to achieve centralized management and automated control of them. This platform can collect and analyze the data of each control device in real time, and automatically adjust the control strategy as needed to achieve the best operating effect. By combining remote communication technology and Internet of Things technology, intelligent management of the distribution network can be achieved, which can not only improve operational efficiency and safety, but also provide powerful data analysis functions to help managers better understand and control their systems.

[0090] The Internet of Things technology can also be used to provide a user interface to display control information, control effects, etc. on the user interface to provide convenience.

[0091] Specifically, after key node control, periodic inspections can also be performed.

[0092] In order to steadily improve the efficiency of intelligent operation and maintenance of distribution network self-healing lines, it is necessary to conduct periodic inspections on the related functions of the self-healing configuration, including: verifying the self-healing configuration of equipment, adaptive configuration of switch and feeder self-healing mode, and batch activation / exit of self-healing feeders, to avoid system failures and performance degradation due to configuration errors. The specific inspection contents are as follows:

[0093] Verify the self-healing configuration of the equipment: Regularly inspect the self-healing consistency, controllability of the self-healing switches, integrity of the self-healing signals, and relevance of the self-healing feeders of the distribution network system to verify the unreasonable configuration that affects the self-healing function. The verification functions implemented include but are not limited to the following table contents:

[0094]

[0095]

[0096] Verify the adaptive configuration of the switch and feeder self-healing mode: Select the switch and line to be put into self-healing mode, and check whether the automatic switch and each automatic switch on the line automatically matches the terminal information. If there is no automatic match, manual modification is supported. The implemented verification functions include but are not limited to the following table contents:

[0097]

[0098] Verify batch input and output of self-healing feeders: When severe weather such as typhoons or power grid risks occur, dispatchers can block or exit self-healing in batches, and support batch blocking / exit settings of self-healing lines by global and county bureaus to ensure circuit safety in emergencies. The implemented verification functions include but are not limited to the following table contents:

[0099]

[0100] The self-healing configuration periodic inspection can improve the transparency and controllability of the operation and maintenance process and reduce the operation and maintenance risks through visual operation and maintenance operations. In addition, the visual self-healing type adaptive modification, classification and statistical query of self-healing configuration abnormal inspection results, and support for exporting query results can improve the operation and maintenance efficiency of operation and maintenance personnel.

[0101] In this example, real-time operation data of the power grid is obtained from terminal devices deployed at key nodes of the distribution network, data preprocessing is performed on the real-time operation data to obtain first operation data, the operation status of the distribution network is predicted using the first operation data to obtain predicted operation status information, control information of the key nodes of the distribution network is generated according to the predicted operation status information, and the control information is sent to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information. Therefore, state prediction can be performed based on the collected real-time operation data of the power grid to obtain predicted operation status information, so as to generate node control information to control the distribution network nodes, thereby improving the accuracy of controlling the distribution network nodes.

[0102] In one possible implementation, the data preprocessing of the real-time operation data to obtain the first operation data includes: performing data cleaning on the real-time operation data to obtain the first reference operation data; normalizing the first reference operation data to obtain the second reference operation data; and performing feature extraction on the second reference operation data to obtain the first operation data.

[0103] Among them, a general data cleaning method can be used to clean the real-time operation data to obtain first reference operation data, and a general normalization processing method can be used to normalize the first reference operation data to obtain second reference operation data.

[0104] When extracting features from the second reference operating data, the specific method may be: the second reference operating data may be statistically analyzed, including descriptive statistical analysis and inferential statistical analysis. Descriptive statistical analysis includes solving mean, variance, etc., and inferential statistical analysis includes regression analysis, hypothesis testing, etc. By conducting in-depth analysis of key parameters such as voltage, current, and power factor, characteristic information such as load change trends and failure modes can be obtained. Therefore, the first operating data may include the mean, variance, etc. of the corresponding data category, and the regression analysis results, hypothesis testing results, etc. of the corresponding data.

[0105] In a possible implementation, the predicted operating state information includes predicted operating load information and predicted power consumption information, and the using of the first operating data to perform operating state analysis on the distribution network to obtain the operating state information includes:

[0106] B1. Using the first operation data to perform load forecasting through a preset operation load forecasting model to obtain forecast operation load information;

[0107] B2. Using a preset power consumption prediction model and the first operating data to perform power consumption prediction, obtain the predicted power consumption information.

[0108] The preset prediction model includes a preset operation load prediction model and a preset power consumption prediction model, and the preset prediction model is a pre-trained model used to predict the corresponding predicted operation status information. The specific training process can be a general model training process, in which the sample data is trained to obtain the preset operation load prediction model and the preset power consumption prediction model.

[0109] In a possible implementation, after sending the control information to the corresponding key node of the distribution network, the method further includes:

[0110] C1. Obtaining control and operation feedback information of the power grid from terminal devices deployed at key nodes of the distribution network;

[0111] C2. Optimizing the preset operation load prediction model and the preset power consumption prediction model according to the control operation feedback information to obtain an optimized preset operation load prediction model and an optimized preset power consumption prediction model.

[0112] The control operation feedback information can be understood as the operation data of the key nodes of the distribution network collected after the control information is executed. The operation data of the key nodes of the distribution network collected and the control information corresponding to the control can be used as feedback samples to optimize the preset operation load prediction model and the preset power consumption prediction model to obtain the optimized preset operation load prediction model and the optimized preset power consumption prediction model. Specifically, a general optimization method can be used for optimization processing to obtain the optimized preset operation load prediction model and the optimized preset power consumption prediction model.

[0113] In a specific implementation, the embodiment of the present application provides another intelligent operation and maintenance method for self-healing lines of a distribution network based on terminal data, which is as follows:

[0114] The present invention provides a method for intelligent operation and maintenance of self-healing lines in a distribution network based on terminal collection features. The technical solution is described from five aspects: First, by deploying advanced equipment such as intelligent switches, fault indicators, and distribution automation terminals at key nodes of the power grid, such as substation outlets, main branch points, trunk lines, user access points, and specific environmental areas, comprehensive collection of voltage, current, fault signals, environmental monitoring data, and remote control operation feedback is achieved. Combined with edge computing and cloud computing technologies, massive data can be efficiently processed and analyzed to eliminate noise and outliers, improve data quality, and ensure the accuracy and consistency of information; secondly, the recurrent neural network (RNN) algorithm is used to deeply explore the load change trend, and combined with descriptive statistics and inferential statistical analysis, the fault mode, load characteristics, and distribution network self-healing information can be accurately identified; then, on this basis, the model predictive control (MPC) algorithm is introduced to dynamically adjust the power generation plan and load distribution strategy according to the feature information extracted in real time, so as to realize the adaptive optimization and forward-looking management of the distribution network operation; finally, with the help of remote communication and Internet of Things technology, the adaptive configuration instructions are accurately transmitted to each control node, including switches and circuit breakers, to realize remote control and automatic operation; in addition, the self-healing configuration is regularly inspected to respond to emergencies and ensure the stability of the distribution network. In this way, the overall design builds a highly integrated and intelligent smart operation and maintenance system method. The specific technical solutions are explained in points as follows:

[0115] 1. Terminal device data collection.

[0116] In the process of intelligentization of power distribution network, terminal equipment is an important foundation for realizing the automation of power distribution network. It can transmit power distribution information in real time and accurately, thereby greatly improving the safety performance and operation efficiency of power distribution network. There are many types of these terminal equipment, mainly including intelligent switches, fault indicators, distribution automation terminals, etc. They are carefully arranged at each key node of the power grid, such as substation exit, main branch point, trunk line, user access point and specific environmental area, forming a monitoring network covering the entire power grid. These terminal devices are responsible for collecting a series of key information, including voltage, current, fault signal, environmental monitoring data, self-healing switch feeder information and remote control operation feedback. These data are a direct reflection of the operation status of the power grid and are crucial for real-time monitoring, fault diagnosis and subsequent data analysis. Through edge computing and cloud computing technology, the collected data is statistically summarized to effectively eliminate noise and outliers, thereby significantly improving the quality and availability of data. This process lays a solid foundation for the subsequent distribution network operation feature extraction, self-healing type adaptive configuration and automatic control execution.

[0117] The process of using edge computing and cloud computing technologies to achieve data processing and analysis is as follows:

[0118] Data preprocessing: Use edge computing technology to perform preliminary processing on the raw data collected by terminal devices, including data cleaning, denoising, outlier detection, etc., to improve the accuracy and reliability of the data.

[0119] Data upload and storage: Upload pre-processed data to the cloud server for centralized storage and management. The cloud computing platform provides powerful storage capacity and efficient data processing capabilities to ensure data security and accessibility.

[0120] Data statistics and summary: On the cloud platform, the collected data is summarized and statistically analyzed, including the calculation of the average, maximum, and minimum values ​​of each indicator, as well as the analysis of the changing trends and distribution characteristics of the data.

[0121] Noise and outlier elimination: Through the big data analysis algorithm of the cloud computing platform, noise and outliers in the data are identified and eliminated, further improving the quality and availability of the data. This helps reduce errors and uncertainties in subsequent analysis and decision-making.

[0122] 2. Extraction of distribution network operation characteristics.

[0123] Distribution network operation feature extraction is to deeply explore and understand the operation status and rules of the distribution network based on the data collected by the terminal equipment. Through this process, valuable information can be extracted from massive data, such as load change trends, failure modes, etc. This not only helps to improve the safety performance and operation efficiency of the distribution network, but also realizes early warning and prevention of potential problems, ensuring the stable operation of the power grid. The specific implementation method is as follows:

[0124] Data preprocessing: It is the process of cleaning, normalizing and transforming raw data, with the aim of eliminating noise and outliers, thereby significantly improving the quality and availability of data and ensuring the accuracy and consistency of data.

[0125] Statistical analysis: Extracting useful information and patterns from massive amounts of data. This includes descriptive statistics (such as mean, variance, etc.) and inferential statistics (such as regression analysis, hypothesis testing, etc.).

[0126] 1) Through in-depth analysis of key parameters such as voltage, current, and power factor, characteristic information such as load change trends and fault modes can be discovered. For example, during peak load periods, by monitoring changes in voltage and current, potential overload risks can be identified; and when a fault occurs, by analyzing abnormal fluctuations in current and power factor, the fault point can be quickly located and corresponding emergency measures can be taken, and preparations can be made for self-healing if necessary.

[0127] 2) By collecting statistics and analyzing the self-healing switches and self-healing lines involved in the self-healing information, the operation strategy and maintenance plan of the distribution network can be further optimized. For example, if a self-healing switch frequently fails to operate or takes too long to respond, it may be necessary to overhaul it or replace it with another switch for self-healing; if a line triggers the self-healing function multiple times in a short period of time but fails to heal, it may be necessary to reselect the switch or line. In this regard, the self-healing types of switches are divided into local self-healing type, master station self-healing type, emergency control type, and recovery control type to facilitate the subsequent adaptive configuration of the self-healing type of the distribution network.

[0128] The recurrent neural network (RNN) algorithm is used to identify load change trends. This algorithm can effectively process time series data and provide strong support for subsequent distribution network adaptive configuration and automatic control by learning patterns and rules in historical data.

[0129] 3. Adaptive configuration of distribution network self-healing type.

[0130] Based on the extracted distribution network operation characteristic information, the model predictive control (MPC) algorithm is used to construct a mathematical model of the power grid operation and predict the state of the power grid in the future. Based on these prediction results, the MPC algorithm can accurately adjust the operation strategy of the distribution network, such as power generation plan, load distribution, etc. For example: when it is predicted that the load demand will increase in a certain period of time in the future, the power generation will be adjusted in advance to meet the demand; when it is predicted that the load risk is high, the load distribution will be optimized to reduce the probability of failure.

[0131] However, when a line fault is detected, the system can automatically switch to the backup line to ensure the continuity of power supply. This involves the adaptive configuration of the self-healing type, including the adaptive selection of self-healing switches and feeders:

[0132] Matching the self-healing type of the switch: Through the distribution network operation feature extraction in step 2, the self-healing switch type in the feature is compared with the current switch self-healing type to find the most matching self-healing type of these switches; if a switch has four functions of telemetry, telesignaling, remote control, and remote adjustment, the self-healing type of the switch can be determined directly by calling the "switch self-healing type" constant. For example: There is a switch S1 in the distribution network, and its features extract key parameters such as the action time, recovery time, and success rate of the switch. Comparing these data with the current self-healing type, it is found that the characteristics of S1 are closest to the characteristics of the voltage-time type self-healing type, so the self-healing type of S1 is determined to be the local type. If switch S1 has been transformed into a four-remote control, then its "switch self-healing type" constant can be directly read through remote communication. Assuming that the constant called from S1 shows that its self-healing type is the main station self-healing type, then it can be determined that the self-healing type of S1 is the main station self-healing type.

[0133] Feeder self-healing type matching: The self-healing type of a feeder is determined based on the self-healing type of each switch on it. If all switches on a feeder belong to the same self-healing type, then the self-healing type of the feeder is this type; if there are two or more different self-healing types on a feeder, then the feeder is defined as a mixed self-healing type.

[0134] Self-healing type matching in special cases: In some areas, if the feature information extracted by all terminal devices is consistent with the current type, the self-healing type of the feeder can be configured according to actual needs. The switches along the line will automatically match and adjust according to this type, which facilitates the configuration of the self-healing type.

[0135] The use of model predictive control (MPC) algorithm can realize real-time adjustment of distribution network operation strategy, including: power generation plan, load distribution, selection of fault self-healing type, etc.

[0136] Through the adaptive configuration of the self-healing type of the distribution network, the distribution network can respond to various complex situations more flexibly and improve the adaptability and flexibility of the system. The adaptive configuration can realize the intelligent management of the distribution network and improve the operating efficiency and economy of the distribution network. The adaptive configuration helps to reduce the failure rate of the distribution network and improve the stability and reliability of power supply.

[0137] 4.Automated control execution.

[0138] In order to reduce manual intervention and improve operational efficiency and safety, remote communication technology can be used to send the results of the adaptive configuration of the distribution network to various control nodes, such as switches and circuit breakers, in real time to achieve remote control and automated operation of them; then the Internet of Things technology can be used to connect various control nodes to a unified platform to achieve centralized management and automated control of them. This platform can collect and analyze data from various control nodes in real time and automatically adjust control strategies as needed to achieve the best operating results. By combining remote communication technology and the Internet of Things technology, intelligent management of the distribution network can be achieved, which can not only improve operational efficiency and safety, but also provide powerful data analysis functions to help managers better understand and control their systems.

[0139] 5. Periodic inspection of self-healing configuration. In order to steadily improve the efficiency of intelligent operation and maintenance of distribution network self-healing lines, it is necessary to conduct periodic inspections on the related functions of self-healing configuration, including: verifying the self-healing configuration of equipment, adaptive configuration of switch and feeder self-healing mode, and batch activation / exit of self-healing feeders, to avoid system failures and performance degradation due to configuration errors. The specific inspection contents are as follows:

[0140] Verify the self-healing configuration of the equipment: Regularly inspect the self-healing consistency, controllability of the self-healing switches, integrity of the self-healing signals, and relevance of the self-healing feeders of the distribution network system to verify the unreasonable configuration that affects the self-healing function. The verification functions implemented include but are not limited to the following table contents:

[0141]

[0142]

[0143] Verify the adaptive configuration of the switch and feeder self-healing mode: Select the switch and line to be put into self-healing mode, and check whether the automatic switch and each automatic switch on the line automatically matches the terminal information. If there is no automatic match, manual modification is supported. The implemented verification functions include but are not limited to the following table contents:

[0144]

[0145] Verify batch input and output of self-healing feeders: When severe weather such as typhoons or power grid risks occur, dispatchers can block or exit self-healing in batches, and support batch blocking / exit settings of self-healing lines by global and county bureaus to ensure circuit safety in emergencies. The implemented verification functions include but are not limited to the following table contents:

[0146]

[0147] The self-healing configuration periodic inspection can improve the transparency and controllability of the operation and maintenance process and reduce the operation and maintenance risks through visual operation and maintenance operations. In addition, the visual self-healing type adaptive modification, classification and statistical query of self-healing configuration abnormal inspection results, and support for exporting query results can improve the operation and maintenance efficiency of operation and maintenance personnel.

[0148] For the above embodiments, please refer to Figure 3 , Figure 3 A schematic diagram of the structure of a server provided in an embodiment of the present application, such as Figure 3 As shown, it includes a processor, an input device, an output device and a memory, which are connected to each other, wherein the memory is used to store a computer program, the computer program includes program instructions, the processor is configured to call the program instructions, and the program includes instructions for executing the following steps;

[0149] Obtain real-time operation data of the power grid from terminal devices deployed at key nodes of the distribution network;

[0150] Performing data preprocessing on the real-time operation data to obtain first operation data;

[0151] Using the first operating data to perform operating state prediction processing on the distribution network to obtain predicted operating state information;

[0152] Generate control information of key nodes of the distribution network according to the predicted operating status information;

[0153] The control information is sent to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

[0154] The above mainly introduces the scheme of the embodiment of the present application from the perspective of the execution process on the method side. It is understandable that in order to realize the above functions, the terminal includes a hardware structure and / or software module corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithm steps of each example described in the embodiments provided herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0155] The embodiment of the present application can divide the terminal into functional units according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0156] In line with the above, see Figure 4 , Figure 4 The present application provides a schematic diagram of a structure of a distribution network self-healing line intelligent operation and maintenance device based on terminal data. Figure 4 As shown, the device comprises:

[0157] The acquisition unit 401 is used to acquire the real-time operation data of the power grid from the terminal devices deployed at the key nodes of the distribution network;

[0158] A preprocessing unit 402 is used to perform data preprocessing on the real-time operation data to obtain first operation data;

[0159] A prediction unit 403 is used to perform operation state prediction processing on the distribution network using the first operation data to obtain predicted operation state information;

[0160] A generating unit 404, configured to generate control information of key nodes of the distribution network according to the predicted operation status information;

[0161] The sending unit 405 is used to send the control information to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

[0162] In a possible implementation, the preprocessing unit 402 is specifically configured to:

[0163] Performing data cleaning on the real-time operation data to obtain first reference operation data;

[0164] Normalizing the first reference running data to obtain second reference running data;

[0165] Perform feature extraction processing on the second reference operating data to obtain first operating data.

[0166] In a possible implementation, the predicted operating state information includes predicted operating load information and predicted power consumption information, and the prediction unit 403 is specifically used to:

[0167] Using the first operation data to perform load forecasting through a preset operation load forecasting model to obtain forecast operation load information;

[0168] The power consumption prediction is performed by using the first operating data through a preset power consumption prediction model to obtain the predicted power consumption information.

[0169] In a possible implementation, the generating unit 404 is specifically configured to:

[0170] The optimal control sequence is solved according to the predicted operating load information, the predicted power consumption information and the operating status information of the current distribution network in the predicted operating status information to obtain the control information of the key nodes of the corresponding distribution network.

[0171] In a possible implementation, after sending the control information to the corresponding key node of the distribution network, the device is further used to:

[0172] Obtaining grid control and operation feedback information from terminal devices deployed at key nodes of the distribution network;

[0173] The preset operation load prediction model and the preset power consumption prediction model are optimized according to the control operation feedback information to obtain an optimized preset operation load prediction model and an optimized preset power consumption prediction model.

[0174] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute part or all of the steps of any one of the methods for intelligent operation and maintenance of distribution network self-healing lines based on terminal data as recorded in the above method embodiments.

[0175] An embodiment of the present application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program enables a computer to execute part or all of the steps of any one of the methods for intelligent operation and maintenance of self-healing lines in a distribution network based on terminal data as recorded in the above method embodiments.

[0176] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0177] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0178] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0179] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0180] In addition, the functional units in the various embodiments of the application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0181] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0182] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which can include: a flash drive, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0183] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A distribution network self-healing line intelligent operation and maintenance method based on terminal data, characterized in that: The method comprises: Obtain real-time operation data of the power grid from terminal devices deployed at key nodes of the distribution network; Performing data preprocessing on the real-time operation data to obtain first operation data; Using the first operating data to perform operating state prediction processing on the distribution network to obtain predicted operating state information; Generate control information of key nodes of the distribution network according to the predicted operating status information; The control information is sent to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

2. The intelligent operation and maintenance method for self-healing lines of a distribution network based on terminal data according to claim 1 is characterized in that: The performing data preprocessing on the real-time operation data to obtain first operation data includes: Performing data cleaning on the real-time operation data to obtain first reference operation data; Normalizing the first reference running data to obtain second reference running data; Perform feature extraction processing on the second reference operating data to obtain first operating data.

3. The intelligent operation and maintenance method for self-healing lines of a distribution network based on terminal data according to claim 2 is characterized in that: The predicted operation status information includes predicted operation load information and predicted power consumption information. The operation status information is obtained by analyzing the operation status of the distribution network using the first operation data, including: Using the first operation data to perform load forecasting through a preset operation load forecasting model to obtain forecast operation load information; The power consumption prediction is performed by using the first operating data through a preset power consumption prediction model to obtain the predicted power consumption information.

4. The intelligent operation and maintenance method for self-healing lines of a distribution network based on terminal data according to claim 3 is characterized in that: The generating control information of key nodes of the distribution network according to the predicted operation status information comprises: The optimal control sequence is solved according to the predicted operating load information, the predicted power consumption information and the operating status information of the current distribution network in the predicted operating status information to obtain the control information of the key nodes of the corresponding distribution network.

5. The intelligent operation and maintenance method for self-healing lines of a distribution network based on terminal data according to any one of claims 1 to 4, characterized in that: After sending the control information to the corresponding key node of the distribution network, the method further includes: Obtaining grid control and operation feedback information from terminal devices deployed at key nodes of the distribution network; The preset operation load prediction model and the preset power consumption prediction model are optimized according to the control operation feedback information to obtain an optimized preset operation load prediction model and an optimized preset power consumption prediction model.

6. A distribution network self-healing line intelligent operation and maintenance device based on terminal data, characterized in that: The device comprises: An acquisition unit, used to acquire real-time operation data of the power grid from terminal devices deployed at key nodes of the distribution network; A preprocessing unit, used for performing data preprocessing on the real-time operation data to obtain first operation data; A prediction unit, configured to use the first operation data to perform operation state prediction processing on the distribution network to obtain predicted operation state information; A generating unit, configured to generate control information of key nodes of the distribution network according to the predicted operating status information; The sending unit is used to send the control information to the control device of the corresponding key node of the distribution network to instruct the control device to control the key node of the distribution network through the control information.

7. The intelligent operation and maintenance device for self-healing lines of a distribution network based on terminal data according to claim 6 is characterized in that: The pre-processing unit is specifically used for: Performing data cleaning on the real-time operation data to obtain first reference operation data; Normalizing the first reference running data to obtain second reference running data; Perform feature extraction processing on the second reference operating data to obtain first operating data.

8. The intelligent operation and maintenance device for self-healing lines of a distribution network based on terminal data according to claim 7 is characterized in that: The predicted operation state information includes predicted operation load information and predicted power consumption information, and the prediction unit is specifically used for: Using the first operation data to perform load forecasting through a preset operation load forecasting model to obtain forecast operation load information; The power consumption prediction is performed by using the first operating data through a preset power consumption prediction model to obtain the predicted power consumption information.

9. A server, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 5.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 5.

Images