Monitoring system for intelligent operation of power grid based on power automation device

Abstract

The invention discloses a power grid intelligent operation monitoring system based on an electric power automation device, and belongs to the technical field of power grid operation monitoring. Comprising a multi-mode sensing node module, a data acquisition preprocessing module, an edge calculation module, a power grid operation analysis module, a quantum auxiliary analysis module, a power grid fault diagnosis module, a dynamic adaptive adjustment module, a fault early warning module and a power grid operation feedback module. Potential problems in power grid operation can be found in time through the power grid operation analysis module, power grid operation parameters can be optimized and adjusted according to an analysis result, the stability and reliability of a power grid are improved, complex problems in the power grid operation analysis module are solved in an accelerated mode through the quantum auxiliary analysis module, and the power grid operation accuracy is improved. And a complex mode result is generated and fed back to the power grid operation analysis module, so that the solving speed and precision of a complex problem are remarkably improved, the power grid can make a faster and more accurate decision in a complex operation environment, and the overall operation efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid operation monitoring, and specifically refers to a monitoring system for the intelligent operation of a power grid based on an electric power automation device. Background Art

[0002] With the continuous development of power systems and the improvement of their intelligence level, real-time monitoring and precise control of power grid operation status have become increasingly important. Traditional power grid monitoring systems often have problems such as incomplete data collection and untimely processing, which makes it difficult to meet the needs of modern power grids for intelligence and efficiency.

[0003] However, there are still certain defects in the existing monitoring of intelligent operation of power grids. The existing monitoring of intelligent operation of power grids lacks an efficient optimization and adjustment mechanism, which results in the inability to dynamically adjust the operating parameters and working modes of the power grid according to real-time data, making it difficult for the power grid to maintain the best state when facing changing operating conditions, resulting in energy waste and low operating efficiency. There may be false alarms or missed alarms in fault identification, especially in complex and changeable power grid environments. Traditional fault detection methods rely on simple threshold judgments or a single data source and cannot comprehensively and accurately identify faults. When faced with emergencies or abnormal conditions, they lack the ability to respond quickly and adjust flexibly. When dealing with complex optimization problems, they rely on traditional calculation methods, which have slow solution speed and low accuracy, and it is difficult to find the optimal solution within a reasonable time. Therefore, a monitoring system for intelligent operation of power grids based on power automation devices is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a monitoring system for the intelligent operation of a power grid based on an electric power automation device, so as to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a monitoring system for the intelligent operation of a power grid based on an electric power automation device, comprising a multimodal sensing node module, a data acquisition preprocessing module, an edge computing module, a power grid operation analysis module, a quantum-assisted analysis module, a power grid fault diagnosis module, a dynamic adaptive adjustment module, a fault warning module and a power grid operation feedback module;

[0006] The multimodal sensing node module is used to collect multimodal operation data of the power grid in the power automation device in real time;

[0007] The data acquisition preprocessing module is used to receive data from the multimodal sensing node and perform preliminary data preprocessing;

[0008] The edge computing module is used to receive data transmitted by the data acquisition preprocessing module, perform preliminary data analysis, and upload the preliminary analysis results to the central server;

[0009] The power grid operation analysis module is used to obtain the preliminary analysis of the edge computing module based on the central server, and conduct a comprehensive and in-depth analysis of the power grid operation status;

[0010] The quantum-assisted analysis module is used to receive complex problems from the power grid operation analysis module for accelerated solution, generate complex pattern results and feed them back to the power grid operation analysis module;

[0011] The power grid fault diagnosis module is used to identify and accurately locate faults in the power grid based on the analysis results of the power grid operation analysis module and historical data;

[0012] The dynamic adaptive adjustment module is used to dynamically adjust the operation parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module;

[0013] The fault warning module is used to issue a warning notification when a fault is diagnosed by the power grid fault diagnosis module;

[0014] The power grid operation feedback module is used to feed back the power grid operation early warning notification result to the management personnel.

[0015] The edge computing module receives data transmitted by the data acquisition preprocessing module, performs preliminary data analysis, including power grid operation anomaly detection, and uploads the preliminary analysis results to the central server;

[0016] Assume that the data preprocessed by the data acquisition preprocessing module is {x1, x2, ..., x i}, let the local volatility index LVI represent the degree of fluctuation of data points in the local range, the window size is N, and the implementation formula is:

[0017]

[0018] In the formula, LVI i represents the local volatility index of the ith data point, N represents the window size, the number of data points for calculating local volatility, and x j represents the value of the jth data point, represents the average value of N data points centered on the i-th data point, Represents the absolute deviation of the jth data point from the local mean;

[0019] The local volatility index is weighted averaged, and the weight of each data point is set to w j , the implementation formula is:

[0020]

[0021] The edge computing module detects anomalies through a dynamic threshold. Let the dynamic threshold be DT and the mean of the local volatility index be, The standard deviation of the local volatility index is The change in the local volatility index in adjacent time periods is The implementation formula is:

[0022]

[0023] In the formula, DT i represents the dynamic threshold of the i-th data point, k represents the adjustment coefficient, α represents the influence coefficient of the standard deviation, and β represents the influence coefficient of the change. i >DT i , it is marked as abnormal, otherwise it is normal, and the detected abnormal results are uploaded to the central server.

[0024] Among them, the power grid operation analysis module performs a comprehensive and in-depth analysis of the power grid operation status, including fault risk assessment, power grid operation stability analysis and load prediction, based on the preliminary analysis of the edge computing module obtained by the central server;

[0025] The fault risk assessment is performed based on the results of the preliminary analysis of the edge computing module, and the implementation formula is:

[0026]

[0027] In the formula, D i represents the dynamic failure risk index of the i-th data point, M represents the window size, and w m represents the weight of the mth time point, ALVI i-m represents the local volatility index of the im-th data point, μ ALVI represents the average value of the local volatility index ALVI, σ ALVI represents the standard deviation of the local volatility index ALVI, represents the normalized local volatility index;

[0028] The grid operation stability analysis is described as follows: i , N is the average value of N data points centered on the i-th data point, is the absolute deviation between the jth data point and the local average value. Each absolute difference is normalized and the formula for grid stability analysis is:

[0029]

[0030] In the formula, LSI i represents the local stability index of the i-th data point, N represents the window size, and xj represents the value of the jth data point, It represents the maximum absolute deviation of all data points from the local mean within the N window.

[0031] Among them, the power grid operation analysis module, load forecasting predicts future power demand based on historical data and preliminary analysis results; assuming that the predicted values ​​at time t are obtained by the ARIMA model and the LSTM model respectively and Calculate the prediction error of each model at time t respectively, and the implementation formula is:

[0032]

[0033] In the formula, represents the forecast error of the ARIMA model at time t, represents the forecast error of the ARIMA model at time t, y t Indicates the actual load forecast result; the final forecast value is obtained based on the forecast results of the ARIMA model and the LSTM model The implementation formula is:

[0034]

[0035] In the formula, α represents the adaptive weight, which is dynamically adjusted according to the historical error. α is expressed as γ is represented as a temperature parameter.

[0036] The quantum-assisted analysis module receives the complex problems of the power grid operation analysis module for accelerated solution, generates complex pattern results and feeds them back to the power grid operation analysis module; let the coupling coefficient be J ij and the external magnetic field strength h i , defined according to the results of the power grid operation analysis module, assuming that the Hamiltonian is H, the problem mapping implementation formula is:

[0037]

[0038] In the formula, H represents the Hamiltonian, J ij Denotes the coupling coefficient, h i represents the external magnetic field strength, σ i and σ j Denotes the interaction between the i-th qubit and the j-th qubit, the spin variable, which is solved by quantum annealing and realized as

[0039] Among them, the dynamic adaptive adjustment module dynamically adjusts the operating parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module; collects real-time data and analysis results from the power grid operation analysis module and the power grid fault diagnosis module, and integrates the data to form a comprehensive power grid operation view, sets priority judgment, and when the power grid fault diagnosis module detects a serious fault, the fault diagnosis module recommends priority execution, and under normal conditions, the power grid operation analysis module recommends priority, and the adjusted operating parameters and working mode are fed back to the power grid operation analysis module for analysis.

[0040] Among them, the power grid fault diagnosis module identifies fault anomalies based on the results of real-time analysis by the power grid operation analysis module and key features extracted from historical data, preliminarily locates the area where the fault exists based on the results of anomaly detection, identifies the fault type by matching the extracted fault features with historical fault patterns, and accurately locates the fault by analyzing the fault propagation path through the topological structure information of the power grid.

[0041] Among them, the power grid operation feedback module receives the warning information from the fault warning module, classifies the warning information according to the warning type and severity, selects the corresponding notification template according to the warning type, fills the extracted warning information into the notification template, generates specific warning notification content and notifies the management personnel.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] 1. In order to solve the problems of optimization adjustment, inaccurate fault identification, inflexible operation adjustment, etc. in the existing power grid monitoring system, and improve rapid fault detection, efficient data analysis monitoring and optimization adjustment, the present invention obtains the preliminary analysis results uploaded by the edge computing module through the power grid operation analysis module, and conducts a comprehensive and in-depth analysis of the power grid operation status, which can timely discover potential problems and risks in the power grid operation, and can also optimize and adjust the power grid operation parameters according to the analysis results, thereby improving the stability and reliability of the power grid;

[0044] 2. The present invention accelerates the solution of complex problems in the power grid operation analysis module through the quantum-assisted analysis module, generates complex pattern results and feeds them back to the power grid operation analysis module, significantly improving the speed and accuracy of solving complex problems, enabling the power grid to make faster and more accurate decisions in a complex operating environment, thereby improving the overall operating efficiency;

[0045] 3. The present invention uses the edge computing module to perform preliminary data analysis locally, including anomaly detection and preliminary processing, which greatly reduces the burden on the central server and reduces data transmission delay. Through the local volatility index and dynamic threshold method, the edge computing module can quickly identify potential anomalies and upload them to the central server in time for further analysis, which not only improves the response speed of the system, but also reduces the pressure on network bandwidth to a certain extent;

[0046] 4. The present invention can quickly identify and accurately locate faults in the power grid through the power grid fault diagnosis module by combining the real-time analysis results and historical data of the power grid operation analysis module, extract key features from a large amount of data, perform anomaly detection and fault classification, and accurately determine the location and type of the fault through the combination of topological structure information and multiple sensors, thereby providing detailed fault information and suggestions to the maintenance team, thereby improving the efficiency of fault handling;

[0047] 5. The present invention dynamically adjusts the operating parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module through the dynamic adaptive adjustment module to cope with the ever-changing power grid operation status. By comprehensively analyzing the data from the two modules, a comprehensive power grid operation view is formed, and a priority judgment mechanism is set. The dynamic adaptive adjustment module can automatically adjust the power generation plan, load distribution, protection device settings, etc., thereby improving the flexibility and adaptability of the power grid. Through this dynamic adjustment, the power grid can maintain the best state under various operating conditions, reduce unnecessary energy waste, and improve the overall performance of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a structural schematic diagram of a monitoring system for intelligent operation of a power grid based on a power automation device of the present invention;

[0049] Figure 2 This is an operation flow chart of the edge computing module of the monitoring system for the intelligent operation of the power grid based on the power automation device of the present invention;

[0050] Figure 3 It is an operation flow chart of the power grid operation analysis module of the monitoring system for the intelligent operation of the power grid based on the power automation device of the present invention;

[0051] Figure 4 The present invention is a flowchart of the operation of the dynamic adaptive adjustment module of the monitoring system for the intelligent operation of the power grid based on the power automation device. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] Example

[0054] See also Figure 1-Figure 4 As shown, the present invention provides a technical solution: including a multimodal perception node module, a data acquisition preprocessing module, an edge computing module, a power grid operation analysis module, a quantum-assisted analysis module, a power grid fault diagnosis module, a dynamic adaptive adjustment module, a fault warning module and a power grid operation feedback module;

[0055] The multimodal sensing node module is used to collect multimodal operation data of the power grid in the power automation device in real time;

[0056] The data acquisition preprocessing module is used to receive data from the multimodal sensing node and perform preliminary data preprocessing;

[0057] The edge computing module is used to receive data transmitted by the data acquisition preprocessing module, perform preliminary data analysis, and upload the preliminary analysis results to the central server;

[0058] The power grid operation analysis module is used to obtain the preliminary analysis of the edge computing module based on the central server, and conduct a comprehensive and in-depth analysis of the power grid operation status;

[0059] The quantum-assisted analysis module is used to receive complex problems from the power grid operation analysis module for accelerated solution, generate complex pattern results and feed them back to the power grid operation analysis module;

[0060] The power grid fault diagnosis module is used to identify and accurately locate faults in the power grid based on the analysis results of the power grid operation analysis module and historical data;

[0061] The dynamic adaptive adjustment module is used to dynamically adjust the operation parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module;

[0062] The fault warning module is used to issue a warning notification when a fault is diagnosed by the power grid fault diagnosis module;

[0063] The power grid operation feedback module is used to feed back the power grid operation early warning notification result to the management personnel.

[0064] The edge computing module receives data transmitted by the data acquisition preprocessing module, performs preliminary data analysis, including power grid operation anomaly detection, and uploads the preliminary analysis results to the central server;

[0065] Assume that the data preprocessed by the data acquisition preprocessing module is {x1, x2, ..., x i}, let the local volatility index LVI represent the degree of fluctuation of data points in the local range, the window size is N, and the implementation formula is:

[0066]

[0067] In the formula, LVI i represents the local volatility index of the ith data point, N represents the window size, the number of data points for calculating local volatility, and x j represents the value of the jth data point, represents the average value of N data points centered on the i-th data point, Represents the absolute deviation of the jth data point from the local mean;

[0068] The local volatility index is weighted averaged, and the weight of each data point is set to w j , the implementation formula is:

[0069]

[0070] The edge computing module detects anomalies through a dynamic threshold. Let the dynamic threshold be DT and the mean of the local volatility index be, The standard deviation of the local volatility index is σ ALVIi The change in the local volatility index in adjacent time periods is The implementation formula is:

[0071]

[0072] In the formula, DT i represents the dynamic threshold of the i-th data point, k represents the adjustment coefficient, α represents the influence coefficient of the standard deviation, and β represents the influence coefficient of the change. i >DT i , it is marked as abnormal, otherwise it is normal, and the detected abnormal results are uploaded to the central server.

[0073] Among them, the power grid operation analysis module performs a comprehensive and in-depth analysis of the power grid operation status, including fault risk assessment, power grid operation stability analysis and load prediction, based on the preliminary analysis of the edge computing module obtained by the central server;

[0074] The fault risk assessment is performed based on the results of the preliminary analysis of the edge computing module, and the implementation formula is:

[0075]

[0076] In the formula, D i represents the dynamic failure risk index of the i-th data point, M represents the window size, and w m represents the weight of the mth time point, ALVI i-m represents the local volatility index of the im-th data point, μ ALVI represents the average value of the local volatility index ALVI, σ ALVI represents the standard deviation of the local volatility index ALVI, represents the normalized local volatility index;

[0077] The power grid operation stability analysis is as follows: i , N is the average value of N data points centered on the i-th data point, is the absolute deviation between the jth data point and the local average value. Each absolute difference is normalized and the formula for grid stability analysis is:

[0078]

[0079] In the formula, LSI i represents the local stability index of the i-th data point, N represents the window size, and x j represents the value of the jth data point, It represents the maximum absolute deviation of all data points from the local mean within the N window.

[0080] Among them, the power grid operation analysis module, load forecasting predicts future power demand based on historical data and preliminary analysis results; assuming that the predicted values ​​at time t are obtained by the ARIMA model and the LSTM model respectively and Calculate the prediction error of each model at time t respectively, and the implementation formula is:

[0081]

[0082] In the formula, represents the forecast error of the ARIMA model at time t, represents the forecast error of the ARIMA model at time t, y t Indicates the actual load forecast result; the final forecast value is obtained based on the forecast results of the ARIMA model and the LSTM model The implementation formula is:

[0083]

[0084] In the formula, α represents the adaptive weight, which is dynamically adjusted according to the historical error. α is expressed as γ is represented as a temperature parameter.

[0085] The quantum-assisted analysis module receives the complex problems of the power grid operation analysis module for accelerated solution, generates complex pattern results and feeds them back to the power grid operation analysis module; let the coupling coefficient be J ij and the external magnetic field strength h i , defined according to the results of the power grid operation analysis module, assuming that the Hamiltonian is H, the problem mapping implementation formula is:

[0086]

[0087] In the formula, H represents the Hamiltonian, J ij Denotes the coupling coefficient, h i represents the external magnetic field strength, σ i and σ j Denotes the interaction between the i-th qubit and the j-th qubit, the spin variable, which is solved by quantum annealing and realized as

[0088] Among them, the dynamic adaptive adjustment module dynamically adjusts the operating parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module; collects real-time data and analysis results from the power grid operation analysis module and the power grid fault diagnosis module, and integrates the data to form a comprehensive power grid operation view, sets priority judgment, and when the power grid fault diagnosis module detects a serious fault, the fault diagnosis module recommends priority execution, and under normal conditions, the power grid operation analysis module recommends priority, and the adjusted operating parameters and working mode are fed back to the power grid operation analysis module for analysis.

[0089] Among them, the power grid fault diagnosis module identifies fault anomalies based on the results of real-time analysis by the power grid operation analysis module and key features extracted from historical data, preliminarily locates the area where the fault exists based on the results of anomaly detection, identifies the fault type by matching the extracted fault features with historical fault patterns, and accurately locates the fault by analyzing the fault propagation path through the topological structure information of the power grid.

[0090] Among them, the power grid operation feedback module receives the warning information from the fault warning module, classifies the warning information according to the warning type and severity, selects the corresponding notification template according to the warning type, fills the extracted warning information into the notification template, generates specific warning notification content and notifies the management personnel.

[0091] In this example, specifically: the edge computing module receives the data transmitted by the data acquisition preprocessing module, performs preliminary data analysis, including power grid operation anomaly detection, and uploads the preliminary analysis results to the central server; suppose the data preprocessed by the data acquisition preprocessing module is {x1, x2, ..., x i}, let the local volatility index LVI represent the degree of fluctuation of data points in the local range, the window size is N, and the implementation formula is:

[0092]

[0093] In the formula, LVI i represents the local volatility index of the ith data point, N represents the window size, the number of data points for calculating local volatility, and x j represents the value of the jth data point, represents the average value of N data points centered on the i-th data point, Represents the absolute deviation of the jth data point from the local mean;

[0094] The local volatility index is weighted averaged, and the weight of each data point is set to w j , the implementation formula is:

[0095]

[0096] The edge computing module detects anomalies through a dynamic threshold. Let the dynamic threshold be DT and the mean of the local volatility index be, The standard deviation of the local volatility index is The change in the local volatility index in adjacent time periods is The implementation formula is:

[0097]

[0098] In the formula, DT i represents the dynamic threshold of the i-th data point, k represents the adjustment coefficient, α represents the influence coefficient of the standard deviation, and β represents the influence coefficient of the change. i >DT i , it is marked as abnormal, otherwise it is normal, and the detected abnormal results are uploaded to the central server.

[0099] In this example, specifically: the power grid operation analysis module obtains the preliminary analysis of the edge computing module based on the central server, and conducts a comprehensive and in-depth analysis of the power grid operation status, including fault risk assessment, power grid operation stability analysis and load prediction;

[0100] The fault risk assessment is performed based on the results of the preliminary analysis of the edge computing module, and the implementation formula is:

[0101]

[0102] In the formula, D i represents the dynamic failure risk index of the i-th data point, M represents the window size, and w m represents the weight of the mth time point, ALVI i-m represents the local volatility index of the im-th data point, μ ALVI represents the average value of the local volatility index ALVI, σ ALVI represents the standard deviation of the local volatility index ALVI, represents the normalized local volatility index;

[0103] The power grid operation stability analysis is as follows: N is the average value of N data points centered on the i-th data point, is the absolute deviation between the jth data point and the local average value. Each absolute difference is normalized and the formula for grid stability analysis is:

[0104]

[0105] In the formula, LSI i represents the local stability index of the i-th data point, N represents the window size, and x j represents the value of the jth data point, It represents the maximum absolute deviation of all data points from the local mean within the N window.

[0106] In this example, specifically: the power grid operation analysis module, load forecasting predicts future power demand based on historical data and preliminary analysis results; assuming that the predicted values ​​at time t are obtained by the ARIMA model and the LSTM model respectively and Calculate the prediction error of each model at time t respectively, and the implementation formula is:

[0107]

[0108] In the formula, represents the forecast error of the ARIMA model at time t, represents the forecast error of the ARIMA model at time t, y t Indicates the actual load forecast result; the final forecast value is obtained based on the forecast results of the ARIMA model and the LSTM model The implementation formula is:

[0109]

[0110] In the formula, α represents the adaptive weight, which is dynamically adjusted according to the historical error. α is expressed as γ is represented as a temperature parameter.

[0111] The quantum-assisted analysis module receives the complex problems of the power grid operation analysis module for accelerated solution, generates complex pattern results and feeds them back to the power grid operation analysis module; let the coupling coefficient be J ij and the external magnetic field strength h i , defined according to the results of the power grid operation analysis module, assuming that the Hamiltonian is H, the problem mapping implementation formula is:

[0112]

[0113] In the formula, H represents the Hamiltonian, J ij Denotes the coupling coefficient, h i represents the external magnetic field strength, σ i and σ j Denotes the interaction between the i-th qubit and the j-th qubit, the spin variable, which is solved by quantum annealing and realized as

[0114] Working principle: The multimodal sensing node module collects multimodal data in power grid operation in real time through different types of sensors. The data acquisition preprocessing module receives data from the multimodal sensing node module and performs preliminary data cleaning, format conversion and normalization. The edge computing module performs preliminary data analysis and anomaly detection based on the preprocessed data, calculates the local volatility index to measure the degree of fluctuation of data points in the local range, detects anomalies in the data through the dynamic threshold method, and uploads these anomalies and preliminary analysis results to the central server.

[0115] The grid operation analysis module receives the preliminary analysis results from the edge computing module and conducts a comprehensive and in-depth analysis of the grid operation status. The analysis content includes fault risk assessment, grid operation stability analysis and load forecasting. The fault risk assessment calculates the dynamic fault risk index based on the local volatility index; the grid operation stability analysis calculates the local stability index by normalized absolute deviation; the load forecast combines the prediction results of the ARIMA model and the LSTM model, and obtains the final prediction value through adaptive weights; the quantum analysis auxiliary analysis module receives the complex problems of the grid operation analysis module, and uses quantum computing technology to accelerate the solution. By mapping the problem to the Hamiltonian of the quantum system, the quantum annealing algorithm is used to solve the complex pattern results and feedback them to the grid operation analysis module. The grid fault diagnosis module extracts key features for fault identification based on the results of the grid operation analysis module and historical data, and identifies faults by matching historical fault patterns. The fault type is identified. At the same time, the topological structure information of the power grid is used to analyze the fault propagation path and accurately locate the fault. The dynamic adaptive adjustment module dynamically adjusts the operating parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module, collects real-time data and analysis results, and forms a comprehensive power grid operation view. According to priority judgment, when a serious fault is detected, the suggestions of the fault diagnosis module are executed first; under normal conditions, the suggestions of the power grid operation analysis module are executed first, and the adjusted parameters and modes are fed back to the power grid operation analysis module for analysis. The fault warning module triggers a warning notification when a fault is detected based on the diagnosis results of the power grid fault diagnosis module. The power grid operation feedback module receives the warning information of the fault warning module, classifies the warning information according to the warning type and severity, selects the corresponding notification template, fills the warning information into the template, generates specific warning notification content, and notifies the management personnel.

[0116] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0117] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A monitoring system for intelligent operation of power grid based on power automation devices, characterized by: It includes multimodal sensing node module, data acquisition preprocessing module, edge computing module, power grid operation analysis module, quantum-assisted analysis module, power grid fault diagnosis module, dynamic adaptive adjustment module, fault warning module and power grid operation feedback module; The multimodal sensing node module is used to collect multimodal operation data of the power grid in the power automation device in real time; The data acquisition preprocessing module is used to receive data from the multimodal sensing node and perform preliminary data preprocessing; The edge computing module is used to receive data transmitted by the data acquisition preprocessing module, perform preliminary data analysis, and upload the preliminary analysis results to the central server; The power grid operation analysis module is used to obtain the preliminary analysis of the edge computing module based on the central server, and conduct a comprehensive and in-depth analysis of the power grid operation status; The quantum-assisted analysis module is used to receive complex problems from the power grid operation analysis module for accelerated solution, generate complex pattern results and feed them back to the power grid operation analysis module; The power grid fault diagnosis module is used to identify and accurately locate faults in the power grid based on the analysis results of the power grid operation analysis module and historical data; The dynamic adaptive adjustment module is used to dynamically adjust the operation parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module; The fault warning module is used to issue a warning notification when a fault is diagnosed by the power grid fault diagnosis module; The power grid operation feedback module is used to feed back the power grid operation early warning notification result to the management personnel.

2. The monitoring system for intelligent operation of power grid based on power automation device according to claim 1 is characterized in that: The edge computing module receives the data transmitted by the data acquisition preprocessing module, performs preliminary data analysis, including power grid operation anomaly detection, and uploads the preliminary analysis results to the central server; Assume that the data preprocessed by the data acquisition preprocessing module is {x1, x2, ..., x i }, let the local volatility index LVI represent the degree of fluctuation of data points in the local range, the window size is N, and the implementation formula is: In the formula, LVI i represents the local volatility index of the ith data point, N represents the window size, the number of data points for calculating local volatility, and x j represents the value of the jth data point, represents the average value of N data points centered on the i-th data point, Represents the absolute deviation of the jth data point from the local mean; The local volatility index is weighted averaged, and the weight of each data point is set to w j , the implementation formula is:

3. The monitoring system for intelligent operation of power grid based on power automation device according to claim 2 is characterized in that: The edge computing module detects anomalies through a dynamic threshold. Let the dynamic threshold be DT and the mean of the local volatility index be, The standard deviation of the local volatility index is The change in the local volatility index in adjacent time periods is The implementation formula is: In the formula, DT i represents the dynamic threshold of the i-th data point, k represents the adjustment coefficient, α represents the influence coefficient of the standard deviation, and β represents the influence coefficient of the change. i >DT i , it is marked as abnormal, otherwise it is normal, and the detected abnormal results are uploaded to the central server.

4. The monitoring system for intelligent operation of power grid based on power automation device according to claim 1 is characterized in that: The power grid operation analysis module performs a comprehensive and in-depth analysis of the power grid operation status, including fault risk assessment, power grid operation stability analysis, and load prediction, based on the preliminary analysis of the edge computing module obtained by the central server; The fault risk assessment is performed based on the results of the preliminary analysis of the edge computing module, and the implementation formula is: In the formula, D i represents the dynamic failure risk index of the i-th data point, M represents the window size, and w m represents the weight of the mth time point, ALVI i-m represents the local volatility index of the im-th data point, μ ALVI represents the average value of the local volatility index ALVI, σ ALVI represents the standard deviation of the local volatility index ALVI, represents the normalized local volatility index; The power grid operation stability analysis is as follows: N is the average value of N data points centered on the i-th data point, is the absolute deviation between the jth data point and the local average value. Each absolute difference is normalized and the formula for grid stability analysis is: In the formula, LSI i represents the local stability index of the i-th data point, N represents the window size, and x j represents the value of the jth data point, It represents the maximum absolute deviation of all data points from the local mean within the N window.

5. The monitoring system for intelligent operation of power grid based on power automation device according to claim 4 is characterized in that: The grid operation analysis module, load forecasting predicts future power demand based on historical data and preliminary analysis results; assuming that the predicted values ​​at time t are obtained by the ARIMA model and the LSTM model respectively and Calculate the prediction error of each model at time t respectively, and the implementation formula is: In the formula, represents the forecast error of the ARIMA model at time t, represents the forecast error of the ARIMA model at time t, y t Indicates the actual load forecast result; the final forecast value is obtained based on the forecast results of the ARIMA model and the LSTM model The implementation formula is: In the formula, α represents the adaptive weight, which is dynamically adjusted according to the historical error. α is expressed as γ is represented as a temperature parameter.

6. The monitoring system for intelligent operation of power grid based on power automation device according to claim 1 is characterized in that: The quantum-assisted analysis module receives the complex problems of the power grid operation analysis module for accelerated solution, generates complex pattern results and feeds them back to the power grid operation analysis module; assuming the coupling coefficient is J ij and the external magnetic field strength h i , defined according to the results of the power grid operation analysis module, assuming that the Hamiltonian is H, the problem mapping implementation formula is: In the formula, H represents the Hamiltonian, J ij Denotes the coupling coefficient, h i represents the external magnetic field strength, σ i and σ j Denotes the interaction between the i-th qubit and the j-th qubit, the spin variable, which is solved by quantum annealing and realized as 7. The monitoring system for intelligent operation of power grid based on power automation device according to claim 1 is characterized in that: The dynamic adaptive adjustment module dynamically adjusts the operation parameters and working mode of the power grid according to the results of the power grid operation analysis module and the power grid fault diagnosis module; collects real-time data and analysis results from the power grid operation analysis module and the power grid fault diagnosis module, and fuses the data to form a comprehensive power grid operation view, sets priority judgment, and when the power grid fault diagnosis module detects a serious fault, the fault diagnosis module recommends priority execution, and under normal conditions, the power grid operation analysis module recommends priority, and the adjusted operation parameters and working mode are fed back to the power grid operation analysis module for analysis.

8. The monitoring system for intelligent operation of power grid based on power automation device according to claim 1, characterized in that: The power grid fault diagnosis module identifies fault anomalies based on the results of the real-time analysis of the power grid operation analysis module and the key features extracted from the historical data, preliminarily locates the area where the fault exists based on the results of the anomaly detection, identifies the fault type by matching the extracted fault features with the historical fault patterns, and accurately locates the fault by analyzing the fault propagation path through the topological structure information of the power grid.

9. The monitoring system for intelligent operation of power grid based on power automation device according to claim 1, characterized in that: The power grid operation feedback module receives the warning information from the fault warning module, classifies the warning information according to the warning type and severity, selects the corresponding notification template according to the warning type, fills the extracted warning information into the notification template, generates specific warning notification content and notifies the management personnel.

Images