Smart power grid online safety operation and maintenance management method and system

Abstract

The invention discloses an intelligent power grid online safety operation and maintenance management method and system, and relates to the technical field of intelligent power grids. A front-end sensor and an edge computing device are deployed to collect data and safely transmit the data, and a cloud server analyzes the data by using a machine learning model and generates a fault prediction report, intelligently schedules operation and maintenance tasks, records maintenance progress in real time and feeds back and adjusts an operation and maintenance plan. According to the invention, through secure transmission, cloud intelligent analysis, an adaptive learning mechanism and a real-time feedback mechanism, the efficiency and accuracy of online secure operation and maintenance of the smart power grid are significantly improved, and rapid identification and effective processing of a fault mode are realized.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and in particular to a method and system for online safe operation and maintenance management of a smart grid. Background Art

[0002] In recent years, with the rise of Internet of Things technology, sensors and smart devices have been used in power grid monitoring and maintenance. By uploading massive data to the cloud for centralized processing, smart grids can achieve real-time monitoring of power grid status and fault warning. However, although these technologies have brought significant advantages to smart grids, there are still some challenges in practical applications.

[0003] In the existing smart grid operation and maintenance management methods, data collection mainly relies on traditional monitoring equipment and lacks effective data transmission means. In addition, the existing operation and maintenance management system lacks the ability to dynamically identify fault modes and intelligent scheduling mechanisms, resulting in slow and inefficient fault response. Therefore, how to solve the problems of high data transmission delay, insufficient security guarantees, and inaccurate fault mode identification in traditional operation and maintenance management systems has become an important step in improving online safe operation and maintenance management methods. Summary of the invention

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

[0005] Therefore, the present invention provides a smart grid online safe operation and maintenance management method and system to solve the problems of accurate identification of fault modes and intelligent operation and maintenance scheduling.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for online safe operation and maintenance management of a smart grid, which includes deploying front-end sensors at key locations of a transmission line, and transmitting the collected environmental data of the transmission line to an edge computing device through the Internet of Things technology;

[0008] The collected environmental data of the power transmission line is preliminarily preprocessed on the edge computing device, and the preprocessed data is encrypted and transmitted to the cloud server through a security authentication mechanism;

[0009] The pre-processed data is analyzed using a machine learning model on the cloud server, and the model parameters are adjusted through an adaptive learning mechanism to identify the fault mode, while the fault prediction report is sent to the operation and maintenance scheduling unit;

[0010] Start the intelligent operation and maintenance task scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand it over to the operation and maintenance personnel;

[0011] The operation and maintenance personnel perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism;

[0012] Adjust future online security operation and maintenance management plans based on feedback from operation and maintenance personnel.

[0013] As a preferred solution of the smart grid online security operation and maintenance management method of the present invention, the front-end sensors are deployed at key positions of the transmission lines, and the collected environmental data of the transmission lines are transmitted to the edge computing device through the Internet of Things technology, including the following steps:

[0014] According to the actual layout and operation characteristics of the transmission line, select key locations such as substations, roads, forests and lightning-prone areas where faults are prone to occur, and select current and voltage sensors, temperature and humidity sensors, lightning monitoring sensors and wind speed sensors according to the monitoring requirements of the specific locations where faults occur;

[0015] Install sensors at selected key locations and in close contact with the transmission lines, and install front-end sensors on the towers and cables of the transmission lines;

[0016] After the front-end sensor is installed, the collected environmental data of the power transmission line will be transmitted to the edge computing device through the Internet of Things technology of wired communication and wireless communication.

[0017] As a preferred solution of the smart grid online security operation and maintenance management method of the present invention, the environmental data of the collected transmission line is preliminarily preprocessed on the edge computing device, and the preprocessed data is encrypted and transmitted to the cloud server through a security authentication mechanism, including the following steps:

[0018] The edge computing device receives the environmental data of the power transmission line through wireless and wired interfaces. After receiving the data, it removes the erroneous outliers and missing values, and uses the checksum and cyclic redundancy check methods to verify the integrity of the environmental data of the power transmission line, and extracts the average and maximum values. The expression is:

[0019] y(t i )=mean(x(t i )*h);

[0020]

[0021] M(t i )=max(y(t i ));

[0022]

[0023] Among them, y(ti ) indicates t i The filtered data within the time period, mean means the mean, x(t i ) indicates t i The original data in the time period, h represents the calculation t i The similarity of the original data within the time period, Indicates t i The average value in the time period, M(t i ) indicates t i The maximum value in the time period, Indicates t i The normalized average value within the time period, μ represents the average value of the collected data, and σ represents the standard deviation of the collected data. Indicates t i The normalized maximum value within the time period, μ M represents the average value of the historical maximum value, σ M represents the standard deviation of the historical maximum value, and i represents the identifier of the data point in the time series;

[0024] According to the average and maximum values ​​of the environmental data of the transmission line, a symmetric encryption algorithm is selected to encrypt the environmental data of the transmission line of the front-end sensor, and identity authentication is performed through a security protocol. The pre-processed data is transmitted to the cloud server using the security protocol after identity authentication.

[0025] As a preferred solution of the smart grid online safety operation and maintenance management method of the present invention, the pre-processed data is analyzed by using a machine learning model on a cloud server, and the model parameters are adjusted by an adaptive learning mechanism to identify the fault mode, and the fault prediction report is sent to the operation and maintenance scheduling unit, including the following steps:

[0026] Import the pre-processed data on the edge computing device and store it in the database of the cloud server;

[0027] By using the Pandas library to read the preprocessed data files stored in the cloud server database, two machine learning models, random forest and support vector machine, are selected, and the cross-validation method in the machine learning model is used to analyze the preprocessed data, and the accuracy and recall are calculated. The expression is:

[0028]

[0029] Among them, Acc j represents the accuracy, x i represents the feature vector of the i-th sample, y i represents the label of the i-th sample, (x i ,y i) represents a sample consisting of a feature vector and a corresponding label, Represents the test data set used in the jth round of cross validation, j represents the index variable identifying the round in the cross validation, Rec i Indicates call

[0030] Return rate, Indicates whether the predicted label is equal to the actual label. Indicates that both the predicted label and the actual label are equal to one; [y i =1] indicates the number of samples whose label of the i-th sample is equal to one;

[0031] According to the accuracy and recall of the preprocessed data, an adaptive learning mechanism is used to evaluate the performance of the machine learning model, so as to adjust the machine learning model parameters to identify the failure mode. The expression is:

[0032]

[0033] Among them, θ j+1 represents the model parameters updated after adaptive learning after the j+1th round, θ j represents the model parameters of the jth round, η represents the learning rate, and Perf j represents the performance metric of the model in the jth iteration, and c represents the adjustment of Perf j The constant factor of represents the training data set used in the jth round of cross validation, represents the gradient of the loss term L, represents the model parameters θ obtained from the training dataset used in the jth round of cross validation j ;

[0034] A fault prediction report is generated based on the results of identifying the fault mode, and the fault prediction report is sent to the operation and maintenance scheduling unit using a message queue.

[0035] As a preferred solution of the smart grid online safety operation and maintenance management method of the present invention, wherein: starting the operation and maintenance task intelligent scheduling system to analyze the information in the fault prediction report, automatically generating a detailed operation and maintenance task list, and handing the detailed operation and maintenance task list to the operation and maintenance personnel, including the following steps,

[0036] Use the intelligent scheduling system for operation and maintenance tasks to extract key information such as fault type, fault location, and timestamp from the fault prediction report, and analyze the impact scope and severity based on different fault types;

[0037] Based on the scope and severity of the impact, a task template database is created to automatically generate a detailed operation and maintenance task list, and the detailed operation and maintenance task list is delivered to the operation and maintenance personnel in the form of an email.

[0038] As a preferred solution of the smart grid online security operation and maintenance management method of the present invention, the operation and maintenance personnel perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information of maintenance work progress to the cloud server through a security authentication mechanism, including the following steps:

[0039] The operation and maintenance personnel receive the operation and maintenance task list via email and formulate a detailed action plan based on the steps in the task list;

[0040] Arrive at the specific location of the fault as directed in the action plan, perform maintenance tasks, and use handheld terminal devices to record the progress of maintenance work;

[0041] The information on the progress of maintenance work is uploaded to the cloud server through a secure authentication mechanism involving identity verification, encrypted transmission, and hash verification.

[0042] As a preferred solution of the smart grid online safety operation and maintenance management method of the present invention, wherein: adjusting the future online safety operation and maintenance management plan according to the information fed back by the operation and maintenance personnel includes the following steps:

[0043] Collect the opinions and experiences of operation and maintenance personnel through questionnaires, summarize the feedback information according to the categories of security vulnerabilities, system performance and tool defects, and record all feedback information in the database of the cloud server after the summary is completed;

[0044] Prioritize the problems according to their severity, impact, and difficulty to resolve, identify the root causes of the problems, and conduct in-depth analysis using the fishbone diagram and five-question method;

[0045] Develop a detailed adjustment plan and gradually implement it in phased tasks. During the implementation process, continuously monitor changes in various indicators, conduct regular effectiveness evaluations, and use quantitative indicators to measure the improvement effects again to form a closed-loop management, thereby continuously iterating and optimizing the security operation and maintenance management plan.

[0046] In a second aspect, the present invention provides a smart grid online security operation and maintenance management system, including a front-end sensing and data acquisition module, which is responsible for deploying front-end sensors at key locations of transmission lines and transmitting the collected environmental data of transmission lines to edge computing devices through Internet of Things technology;

[0047] The edge computing and preliminary preprocessing module is responsible for preprocessing the collected environmental data on the edge computing device, and encrypting and transmitting the preprocessed data to the cloud server through a security authentication mechanism;

[0048] The cloud data processing and analysis module is responsible for analyzing the pre-processed data using the machine learning model on the cloud server, adjusting the model parameters through the adaptive learning mechanism to identify the fault mode, and sending the fault prediction report to the operation and maintenance scheduling unit;

[0049] The operation and maintenance task intelligent scheduling module is responsible for starting the operation and maintenance task intelligent scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand over the detailed operation and maintenance task list to the operation and maintenance personnel;

[0050] The on-site operation and maintenance execution and feedback module is responsible for the operation and maintenance personnel to perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism.

[0051] 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 smart grid online safe operation and maintenance management method as described in the first aspect of the present invention is implemented.

[0052] 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 smart grid online safe operation and maintenance management method as described in the first aspect of the present invention is implemented.

[0053] The beneficial effects of the present invention are as follows: by combining edge computing with the Internet of Things technology, real-time data collection and preprocessing are realized. The preprocessed data is efficiently analyzed by using an adaptive learning mechanism and a cross-validation method, and the machine learning model parameters are dynamically adjusted, which significantly improves the accuracy and recall rate of fault pattern recognition. This not only enhances the efficiency and reliability of the online safety operation and maintenance management of the smart grid, but also significantly reduces the fault response time and maintenance costs, thereby improving the stability and security of the entire safety operation and maintenance management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] 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.

[0055] Figure 1 This is a flow chart of a smart grid online security operation and maintenance management method in Example 1.

[0056] Figure 2This is a decision diagram of a smart grid online safety operation and maintenance management method in Example 1. DETAILED DESCRIPTION

[0057] 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.

[0058] 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.

[0059] 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.

[0060] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a smart grid online security operation and maintenance management method, comprising the following steps:

[0061] S1. Deploy front-end sensors at key locations of the transmission line and transmit the collected environmental data of the transmission line to the edge computing device through the Internet of Things technology, including the following steps:

[0062] According to the actual layout and operation characteristics of the transmission line, select key locations such as substations, roads, forests and lightning-prone areas where faults are prone to occur, and select current and voltage sensors, temperature and humidity sensors, lightning monitoring sensors and wind speed sensors according to the monitoring requirements of the specific locations where faults occur;

[0063] Install sensors at selected key locations and in close contact with the transmission lines, and install front-end sensors on the towers and cables of the transmission lines;

[0064] After the front-end sensor is installed, the collected environmental data of the power transmission line is transmitted to the edge computing device through the IoT technology of wired communication and wireless communication;

[0065] Wired communication is a communication method that transmits information by connecting cables and optical fibers. It mainly relies on physical media such as wires and optical fibers to transmit signals. Because wired communication relies on physical connections, the transmitted signals are relatively stable and not easily interfered with by the outside world. It can support higher data transmission rates and is suitable for application scenarios that require large amounts of data transmission, such as interconnection between data centers, video streaming transmission, etc. Compared with wireless communication, wired communication data transmission is more private and less susceptible to eavesdropping or interference.

[0066] Wireless communication is a communication method that does not rely on physical connections but transmits information through the propagation of electromagnetic waves in space. Wireless communication can span longer distances and cover larger geographical areas, especially in places where it is difficult to lay cables. The signal is easily interfered by external factors, such as buildings, weather conditions, etc., resulting in unstable signals.

[0067] S2. Perform preliminary preprocessing on the collected environmental data of the power transmission line on the edge computing device, and encrypt and transmit the preprocessed data to the cloud server through a security authentication mechanism, including the following steps:

[0068] The edge computing device receives the environmental data of the power transmission line through wireless and wired interfaces. After receiving the data, it removes the erroneous outliers and missing values, and uses the checksum and cyclic redundancy check methods to verify the integrity of the environmental data of the power transmission line, and extracts the average and maximum values. The expression is:

[0069] y(t i )=mean(x(t i )*h);

[0070]

[0071] M(t i )=max(y(t i ));

[0072]

[0073] Among them, y(t i ) indicates t i The filtered data within the time period, mean means the mean, x(t i ) indicates t i Environmental data of the transmission line within the time period, h represents the calculation t i The similarity of the environmental data of the transmission line within the time period, Indicates t i The average value in the time period, M(t i ) indicates t i The maximum value in the time period, Indicates ti The normalized average value within the time period, μ represents the average value of the collected data, and σ represents the standard deviation of the collected data. Indicates t i The normalized maximum value within the time period, μ M represents the average value of the historical maximum value, σ M represents the standard deviation of the historical maximum value, and i represents the identifier of the data point in the time series;

[0074] Checksum is a simple algorithm for detecting data transmission errors. Its basic principle is to perform mathematical operations on the data before data transmission and attach the calculation results to the data and send them together. After receiving the data, the receiving end also performs the same operation on the data and compares it with the received checksum. If the two are consistent, the data transmission is considered to be correct; if they are inconsistent, it indicates that an error occurred during the transmission process.

[0075] Cyclic redundancy check is a complex algorithm for detecting data transmission errors. It divides the data by a predefined mathematical formula to obtain a check code, which is then attached to the data and sent together. After receiving the data, the receiver also divides the data using the same mathematical formula to check whether the result is zero to determine whether the data is correct.

[0076] According to the average and maximum values ​​of the environmental data of the power transmission line, a symmetric encryption algorithm is selected to encrypt the environmental data of the power transmission line of the front-end sensor, and identity authentication is performed through a security protocol, and the pre-processed data is transmitted to the cloud server using the security protocol after identity authentication;

[0077] Symmetric encryption is a method of encryption that uses the same key for encryption and decryption. The sender and receiver must share the same key, and both parties must keep the key secret. Since the algorithm is relatively simple, the processing speed of symmetric encryption is fast and it is suitable for encrypting large amounts of data. The main problem of symmetric encryption is the distribution and management of the key. Once the key is leaked, the data may be cracked, so the security of the symmetric encryption depends on the security of the key.

[0078] S3. Analyze the preprocessed data using the machine learning model on the cloud server, adjust the model parameters through the adaptive learning mechanism to identify the fault mode, and send the fault prediction report to the operation and maintenance scheduling unit, including the following steps:

[0079] Import the pre-processed data on the edge computing device and store it in the database of the cloud server;

[0080] By using the Pandas library to read the preprocessed data files stored in the cloud server database, two machine learning models, random forest and support vector machine, are selected, and the cross-validation method in the machine learning model is used to analyze the preprocessed data and calculate the accuracy and recall rate;

[0081] The derivation process of the expression of accuracy is:

[0082] Accuracy j ) is defined as the ratio of correctly classified samples to the total number of samples. In binary or multi-classification problems, the accuracy can be expressed as,

[0083]

[0084] In cross validation, each round has an independent test set Therefore, the accuracy is expressed as,

[0085]

[0086] Specifically, the number of correctly classified samples is expressed as,

[0087]

[0088] When predicting labels Equal to the true label y i It returns 1 when , otherwise it returns 0. Therefore, the sum represents the number of correctly classified samples in the test set;

[0089] The total number of samples is

[0090] Combining the two, we get the expression for accuracy:

[0091]

[0092] The derivation process of the expression of recall rate is:

[0093] Recall j ) is defined as the proportion of samples that are actually positive and are correctly classified as positive. In binary or multi-classification problems, recall is expressed as,

[0094]

[0095] In cross validation, each round has an independent test set Therefore, the recall rate is expressed as,

[0096]

[0097] When predicting labels Equal to the true label yi And the true label y i If it is a positive class, it returns 1, otherwise it returns 0. Therefore, the sum represents the number of samples correctly classified as positive in the test set;

[0098] The total number of samples that are actually positive is,

[0099]

[0100] Combining all the steps together, we get the expression for recall:

[0101]

[0102] Among them, Acc j represents the accuracy, x i represents the feature vector of the i-th sample, y i represents the label of the i-th sample, (x i ,y i ) represents a sample consisting of a feature vector and a corresponding label, Represents the test data set used in the jth round of cross-validation. It is used to evaluate the performance of the machine learning model during the cross-validation process, so as to gain a more comprehensive understanding of the model's generalization ability and ability to identify failure modes. j represents the index variable that identifies the round in the cross-validation. Rec j represents the recall rate, Indicates whether the predicted label is equal to the actual label, which is used to count the number of labels in the test set. The number of samples correctly predicted by the model, Indicates that the predicted label and the actual label are equal to one, which is used to count the number of labels in the test set. The number of samples correctly predicted as positive by the model, [y i =1] indicates the number of samples whose label of the i-th sample is equal to one, which is used to calculate the test set The number of samples that are actually positive in ;

[0103] Pandas is a Python data analysis library, which provides high-performance, easy-to-use data structures and data analysis tools for Python. It can handle large amounts of tabular data and supports data cleaning, processing, visualization, and modeling.

[0104] Random forest is a learning method that completes the classification task integration by building multiple decision trees. When predicting, the final result is obtained by classification and regression tasks. Random forest extracts multiple sample sets from the original data set through the bootstrap method. Each sample set is used to train and build a decision tree. For classification tasks, the majority class is selected as the prediction result by majority voting. For regression tasks, the average of all tree prediction values ​​is taken as the final prediction.

[0105] Support vector machine is a supervised learning model, mainly used for classification and regression analysis. The core idea of ​​support vector machine is to find a hyperplane that maximizes the interval between positive and negative samples, thereby achieving classification.

[0106] Cross-validation is a technique for evaluating the performance of machine learning models. It provides an accurate estimate of the generalization ability of the model by dividing the dataset into several mutually exclusive subsets for multiple training and testing. The most common cross-validation method is K-fold cross-validation, in which the dataset is randomly divided into K subsets of equal size for K iterations. In each iteration, one subset is selected as the test set, and the remaining K-1 subsets are combined as the training set. The model is trained on these K-1 subsets and tested on a reserved subset. The final performance indicator is obtained by averaging the K test results.

[0107] Based on the accuracy and recall of the preprocessed data, an adaptive learning mechanism is used to evaluate the performance of the machine learning model, thereby adjusting the machine learning model parameters to identify the failure mode;

[0108] The derivation of the expression for identifying the failure mode is:

[0109] Initialize machine model parameters θ;

[0110] In the jth iteration, using the training dataset Train the model and calculate the model's performance metric Perf j ,The performance measures are precision and recall;

[0111] Calculate the training data set About the current parameter θ j Gradient

[0112] Putting all the steps together, we form an expression that adjusts the machine learning model parameters to identify failure modes.

[0113]

[0114] Among them, θ j+1 represents the model parameters updated after adaptive learning after the j+1th round, θ j represents the model parameters of the jth round, η represents the learning rate, which is used to control the amplitude of the model parameter change. A larger η will lead to a larger amplitude change and the parameters will converge faster. A smaller η will make the update smoother but the convergence speed will be slower. Perf j It represents the performance metric of the model in the jth iteration, which is used to adjust the direction and size of parameter updates to optimize model performance. c represents the adjustment of Prerfj Constant factor used to adjust the performance metric Perf j The weight in the model parameter update is to balance the performance by adjusting c. j The impact of the update process, represents the training data set used in the jth round of cross-validation to ensure the generalization ability of the model on different data subsets. Represents the gradient of the loss term L. The gradient points to the direction where the loss term increases fastest, so the negative gradient points to the direction where the loss function decreases fastest. By using the gradient descent method, the loss term can be minimized by updating the parameters along the negative gradient direction. represents the gradient of the loss term on the training dataset, represents the model parameters θ obtained from the training dataset used in the jth round of cross validation j , used to calculate gradients and update model parameters;

[0115] Adaptive learning mechanism is a technology used to improve model performance in the field of machine learning and artificial intelligence. The adaptive learning mechanism dynamically adjusts learning parameters according to different characteristics of data during the training process, and provides personalized learning strategies for different data sets and tasks to improve the adaptability of the model. Through adaptive adjustment, the model can better cope with noise and outliers in the data, and provide different learning strategies at different training stages, thereby optimizing the performance of the model.

[0116] If the fault mode is identified by the adjusted machine learning model parameters, the fault prediction report is sent to the operation and maintenance scheduling unit. If the fault mode is not identified, the accuracy and recall rate of the machine learning model are checked, and more training data is added to further improve the model's generalization ability and ability to identify fault modes;

[0117] Generate a fault prediction report based on the results of identifying the fault mode, and send the fault prediction report to the operation and maintenance scheduling unit using a message queue;

[0118] Message queue is a technology used to implement inter-process communication in distributed systems. It allows messages to be passed between applications, thereby improving the scalability and fault tolerance of the system. Its working principle is that the application generates a message and sends the message to the specified message queue. After the message queue receives the message, it stores the message and persists it or stores it in memory according to the configuration strategy. Another application pulls the message from the message queue or subscribes to the message and processes it. After processing the message, it confirms to the message queue that the message has been successfully processed so that the message queue can mark the message as processed or delete it.

[0119] S4. Start the operation and maintenance task intelligent scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand over the detailed operation and maintenance task list to the operation and maintenance personnel, including the following steps:

[0120] Use the intelligent scheduling system for operation and maintenance tasks to extract key information such as fault type, fault location, and timestamp from the fault prediction report, and analyze the impact scope and severity based on different fault types;

[0121] The intelligent scheduling system for operation and maintenance tasks is a system that manages and schedules operation and maintenance tasks through automation and intelligence. It can automatically detect system status, identify potential problems, plan operation and maintenance tasks, and assign tasks to appropriate operation and maintenance personnel.

[0122] Fault types include hardware faults, software faults, network faults, and application layer faults;

[0123] Create a task template database to automatically generate a detailed operation and maintenance task list based on the scope and severity of the impact, and send the detailed operation and maintenance task list to the operation and maintenance personnel in the form of an email;

[0124] The task template database is an information system used to store and manage task templates. In operation and maintenance, project management, and daily workflows, the task template database provides standardized task descriptions and execution guidelines, making task creation, assignment, and execution more efficient and consistent.

[0125] S5. The operation and maintenance personnel perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism, including the following steps:

[0126] The operation and maintenance personnel receive the operation and maintenance task list via email and formulate a detailed action plan based on the steps in the task list;

[0127] Arrive at the specific location of the fault as directed in the action plan, perform maintenance tasks, and use handheld terminal devices to record the progress of maintenance work;

[0128] Upload maintenance work progress information to the cloud server through a secure authentication mechanism involving identity verification, encrypted transmission, and hash verification;

[0129] Hash verification is a technology used to verify data integrity. It detects whether the data has been tampered with or damaged by calculating the hash value of the data and comparing it with the correct hash value. Hash verification is widely used in file transfer, software distribution, data storage and other fields. Its workflow is that the sender uses a hash function to hash the original data to generate a hash value, and provides the hash value together with the data to the receiver. The receiver uses the same hash function to hash the received data to generate a new hash value. If the two hash values ​​are consistent, the data is considered to be intact and not tampered with; if they are inconsistent, it indicates that the data may have been modified or damaged during transmission.

[0130] S6. Adjust the future online security operation and maintenance management plan based on the feedback from the operation and maintenance personnel, including the following steps:

[0131] Collect the opinions and experiences of operation and maintenance personnel through questionnaires, summarize the feedback information according to the categories of security vulnerabilities, system performance and tool defects, and record all feedback information in the database of the cloud server after the summary is completed;

[0132] Prioritize the problems according to their severity, impact, and difficulty to resolve, identify the root causes of the problems, and conduct in-depth analysis using the fishbone diagram and five-question method;

[0133] The fishbone diagram is a problem analysis tool that identifies and analyzes the various potential causes of a problem. The fishbone diagram is centered on a trunk (fish spine) with "fish bones" (branches) extending outward. Each branch represents a major cause of the problem.

[0134] The five-question method is a technical tool for root cause analysis of problems. It gradually explores the essence of the problem by asking "why" in succession. Although it is called "five questions", it is not actually strictly limited to five questions. Instead, it asks questions according to the specific situation until the root cause of the problem is found.

[0135] Develop a detailed adjustment plan and gradually implement it in phased tasks. During the implementation process, continuously monitor changes in various indicators, conduct regular effectiveness evaluations, and use quantitative indicators to measure the improvement effects again to form a closed-loop management, thereby continuously iterating and optimizing the security operation and maintenance management plan.

[0136] This embodiment also provides a smart grid online security operation and maintenance management system, including: a front-end sensing and data acquisition module, which is responsible for deploying front-end sensors at key locations of transmission lines and transmitting the collected environmental data of transmission lines to edge computing devices through Internet of Things technology;

[0137] The edge computing and preliminary preprocessing module is responsible for preprocessing the collected environmental data on the edge computing device, and encrypting and transmitting the preprocessed data to the cloud server through a security authentication mechanism;

[0138] The cloud data processing and analysis module is responsible for analyzing the pre-processed data using the machine learning model on the cloud server, adjusting the model parameters through the adaptive learning mechanism to identify the fault mode, and sending the fault prediction report to the operation and maintenance scheduling unit;

[0139] The operation and maintenance task intelligent scheduling module is responsible for starting the operation and maintenance task intelligent scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand over the detailed operation and maintenance task list to the operation and maintenance personnel;

[0140] The on-site operation and maintenance execution and feedback module is responsible for the operation and maintenance personnel to perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism.

[0141] This embodiment also provides a computer device, which is suitable for the case of a smart grid online safety operation and maintenance management method, 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 smart grid online safety operation and maintenance management method proposed in the above embodiment.

[0142] 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.

[0143] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the method for realizing online safe operation and maintenance management of a smart grid as proposed in the above embodiment is implemented; 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 (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0144] In summary, the present invention realizes real-time data collection and preprocessing by combining edge computing with Internet of Things technology. The preprocessed data is efficiently analyzed by using adaptive learning mechanism and cross-validation method, and the machine learning model parameters are dynamically adjusted, which significantly improves the accuracy and recall rate of fault pattern recognition. It not only enhances the efficiency and reliability of online safety operation and maintenance management of smart grids, but also greatly reduces fault response time and maintenance costs, thereby improving the stability and security of the entire safety operation and maintenance management system.

[0145] 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 smart grid online security operation and maintenance management method, characterized in that: include, Deploy front-end sensors at key locations of power transmission lines and transmit the collected environmental data of power transmission lines to edge computing devices through IoT technology; The collected environmental data of the power transmission line is preliminarily preprocessed on the edge computing device, and the preprocessed data is encrypted and transmitted to the cloud server through a security authentication mechanism; The pre-processed data is analyzed using a machine learning model on the cloud server, and the model parameters are adjusted through an adaptive learning mechanism to identify the fault mode, while the fault prediction report is sent to the operation and maintenance scheduling unit; Start the intelligent operation and maintenance task scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand it over to the operation and maintenance personnel; The operation and maintenance personnel perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism; Adjust future online security operation and maintenance management plans based on feedback from operation and maintenance personnel.

2. The smart grid online security operation and maintenance management method according to claim 1, characterized in that: Deploy front-end sensors at key locations of the transmission line and transmit the collected environmental data of the transmission line to the edge computing device through the Internet of Things technology, including the following steps: According to the actual layout and operation characteristics of the transmission line, select key locations such as substations, roads, forests and lightning-prone areas where faults are prone to occur, and select current and voltage sensors, temperature and humidity sensors, lightning monitoring sensors and wind speed sensors according to the monitoring requirements of the specific locations where faults occur; Install sensors at selected key locations and in close contact with the transmission lines, and install front-end sensors on the towers and cables of the transmission lines; After the front-end sensor is installed, the collected environmental data of the power transmission line will be transmitted to the edge computing device through the Internet of Things technology of wired communication and wireless communication.

3. The smart grid online security operation and maintenance management method according to claim 2, characterized in that: The collected environmental data of the power transmission line is preliminarily preprocessed on the edge computing device, and the preprocessed data is encrypted and transmitted to the cloud server through a security authentication mechanism, including the following steps: The edge computing device receives the environmental data of the power transmission line through wireless and wired interfaces. After receiving the data, it removes the erroneous outliers and missing values, and uses the checksum and cyclic redundancy check methods to verify the integrity of the environmental data of the power transmission line, and extracts the average and maximum values. The expression is: y(t i )=mean(x(t i )*h); M(t i )=max(y(t i )); Among them, y(t i ) indicates t i The filtered data within the time period, mean means the mean, x(t i ) indicates t i The environmental data of the transmission line within the time period, h represents the similarity of the environmental data of the transmission line within the time period t, Indicates t i The average value within the time period, M(t i ) indicates t i The maximum value in the time period, Indicates t i The normalized average value within the time period, μ represents the average value of the collected data, and σ represents the standard deviation of the collected data. Indicates t i The normalized maximum value within the time period, μ M represents the average value of the historical maximum value, σ M represents the standard deviation of the historical maximum value, and i represents the identifier of the data point in the time series; According to the average and maximum values ​​of the environmental data of the transmission line, a symmetric encryption algorithm is selected to encrypt the environmental data of the transmission line of the front-end sensor, and identity authentication is performed through a security protocol. The pre-processed data is transmitted to the cloud server using the security protocol after identity authentication.

4. The smart grid online security operation and maintenance management method according to claim 3, characterized in that: The pre-processed data is analyzed using a machine learning model on the cloud server, and the model parameters are adjusted through an adaptive learning mechanism to identify the fault mode. At the same time, the fault prediction report is sent to the operation and maintenance scheduling unit, including the following steps: Import the pre-processed data on the edge computing device and store it in the database of the cloud server; By using the Pandas library to read the preprocessed data files stored in the cloud server database, two machine learning models, random forest and support vector machine, are selected, and the cross-validation method in the machine learning model is used to analyze the preprocessed data, and the accuracy and recall are calculated. The expression is: Among them, Acc j represents the accuracy, x i represents the feature vector of the i-th sample, y i represents the label of the i-th sample, (x i ,y i ) represents a sample consisting of a feature vector and a corresponding label, Represents the test data set used in the jth round of cross validation, j represents the index variable identifying the round in the cross validation, Rec j represents the recall rate, Indicates whether the predicted label is equal to the actual label. Indicates that both the predicted label and the actual label are equal to one; [y i =1] indicates the number of samples whose label of the i-th sample is equal to one; According to the accuracy and recall of the preprocessed data, an adaptive learning mechanism is used to evaluate the performance of the machine learning model, so as to adjust the machine learning model parameters to identify the failure mode. The expression is: Among them, θ j+1 represents the model parameters updated after adaptive learning after the j+1th round, θ j represents the model parameters of the jth round, η represents the learning rate, and Perf j represents the performance metric of the model in the jth iteration, and c represents the adjustment of Perf j The constant factor of represents the training data set used in the jth round of cross validation, represents the gradient of the loss term L, represents the model parameters θ obtained from the training dataset used in the jth round of cross-validation; A fault prediction report is generated based on the results of identifying the fault mode, and the fault prediction report is sent to the operation and maintenance scheduling unit using a message queue.

5. The smart grid online security operation and maintenance management method according to claim 4, characterized in that: Start the operation and maintenance task intelligent scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand over the detailed operation and maintenance task list to the operation and maintenance personnel, including the following steps: Use the intelligent scheduling system for operation and maintenance tasks to extract key information such as fault type, fault location, and timestamp from the fault prediction report, and analyze the impact scope and severity based on different fault types; Based on the scope and severity of the impact, a task template database is created to automatically generate a detailed operation and maintenance task list, and the detailed operation and maintenance task list is delivered to the operation and maintenance personnel in the form of an email.

6. The smart grid online security operation and maintenance management method according to claim 5, characterized in that: The operation and maintenance personnel perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism, including the following steps: The operation and maintenance personnel receive the operation and maintenance task list via email and formulate a detailed action plan based on the steps in the task list; Arrive at the specific location of the fault as directed in the action plan, perform maintenance tasks, and use handheld terminal devices to record the progress of maintenance work; The information on the progress of maintenance work is uploaded to the cloud server through a secure authentication mechanism involving identity verification, encrypted transmission, and hash verification.

7. The smart grid online security operation and maintenance management method according to claim 6, characterized in that: Adjust the future online security operation and maintenance management plan based on the feedback from the operation and maintenance personnel, including the following steps: Collect the opinions and experiences of operation and maintenance personnel through questionnaires, summarize the feedback information according to the categories of security vulnerabilities, system performance and tool defects, and record all feedback information in the database of the cloud server after the summary is completed; Prioritize the problems according to their severity, impact, and difficulty to resolve, identify the root causes of the problems, and conduct in-depth analysis using the fishbone diagram and five-question method; Develop a detailed adjustment plan and gradually implement it in phased tasks. During the implementation process, continuously monitor changes in various indicators, conduct regular effectiveness evaluations, and use quantitative indicators to measure the improvement effects again to form a closed-loop management, thereby continuously iterating and optimizing the security operation and maintenance management plan.

8. A smart grid online security operation and maintenance management system, based on the smart grid online security operation and maintenance management method and system according to any one of claims 1 to 7, characterized in that: include, The front-end sensing and data acquisition module is responsible for deploying front-end sensors at key locations of the power transmission line and transmitting the collected environmental data of the power transmission line to the edge computing device through the Internet of Things technology; The edge computing and preliminary preprocessing module is responsible for preprocessing the collected environmental data on the edge computing device, and encrypting and transmitting the preprocessed data to the cloud server through a security authentication mechanism; The cloud data processing and analysis module is responsible for analyzing the pre-processed data using the machine learning model on the cloud server, adjusting the model parameters through the adaptive learning mechanism to identify the fault mode, and sending the fault prediction report to the operation and maintenance scheduling unit; The operation and maintenance task intelligent scheduling module is responsible for starting the operation and maintenance task intelligent scheduling system to analyze the information in the fault prediction report, automatically generate a detailed operation and maintenance task list, and hand over the detailed operation and maintenance task list to the operation and maintenance personnel; The on-site operation and maintenance execution and feedback module is responsible for the operation and maintenance personnel to perform maintenance tasks according to the instructions on the operation and maintenance task list, use smart terminal devices to record the progress of maintenance work in real time, and upload the information on the progress of maintenance work to the cloud server through a security authentication mechanism.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the smart grid online security operation and maintenance management method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the smart grid online security operation and maintenance management method described in any one of claims 1 to 7 are implemented.

Images