Power system harmonic impedance panoramic intelligent prediction system based on industrial big data

Abstract

The invention relates to the technical field of intelligent power grid industry, and discloses a panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data. Comprising an electric power data acquisition module, an electric power data analysis module, an electric power fault pre-judgment module, an electric power fault response module, a user interaction interface module, a user feedback collection module and a prediction efficiency improvement module, the power fault pre-judgment module predicts system faults according to calculation results, the power fault response module performs targeted processing on the faults according to prediction results, and the user interaction interface module displays system operation states, fault prediction results and adjustment of system parameters to related workers by means of a visual interface. The user feedback collection module is responsible for collecting feedback information of a user in the system using process, and the prediction efficiency improvement module optimizes the whole system according to the user feedback information.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grid industry, and specifically to a panoramic intelligent prediction system for power system harmonic impedance based on industrial big data. Background Art

[0002] Under the background of the rapid development of industrial big data processing technology and the large-scale application of AC transmission projects above 750 kV, the safe and stable operation of the power system has put forward higher requirements for real-time monitoring and fault prediction. However, the existing panoramic intelligent prediction system for power system harmonic impedance based on industrial big data still faces the following technical challenges:

[0003] Insufficient adaptability to dynamic changes in the grid structure: With the expansion of transmission lines above 750 kV, large-scale grid interconnection, and the complexity of intelligent dispatching systems, dynamic adjustments such as line addition and deletion, and substation capacity expansion have led to frequent changes in the grid structure. Traditional fault prediction technologies rely on manual adjustment of monitoring points and model parameters, and it is difficult to achieve adaptive optimization through industrial big data analysis, resulting in insufficient real-time monitoring capabilities for the harmonic impedance status of high-voltage transmission networks.

[0004] Outstanding problems of communication delay and instability: The large-scale grid security guarantee system has extremely high requirements for the real-time nature of data transmission. However, the massive monitoring data involved in industrial big data processing (such as high-frequency signals of 750 kV transmission lines and equipment status data of intelligent substations) is easily affected by factors such as network congestion and signal interference during transmission, resulting in communication delays or interruptions, directly affecting the timeliness and reliability of fault prediction.

[0005] Great difficulty in system integration: The data formats and communication protocols of multi-source heterogeneous devices in the power supply system (such as high-voltage transmission line sensors, smart meters, and GIS geographic information systems) are significantly different. The integration and analysis of industrial big data need to solve the device compatibility problem. Due to the lack of a unified industrial big data processing standard in existing systems, it is difficult to efficiently integrate multi-type monitoring devices, restricting the comprehensive perception ability of the panoramic view of the grid harmonic impedance.

[0006] The dynamic changes in the power grid structure pose difficulties for fault prediction. With the advancement of the upgrading, transformation, and expansion process of the power system, the frequent addition and removal of lines and the expansion of substations occur, which makes the power grid structure constantly changing. However, the existing fault prediction technologies have obvious deficiencies in dealing with such changes. Often, manual re-adjustment of the monitoring point layout and updating of model parameters are required, which not only consumes a large amount of human and time costs but also affects the performance and accuracy of the fault prediction system due to untimely or inaccurate adjustments. It is difficult to effectively monitor the harmonic impedance state and predict faults under the new power grid structure. On the other hand, the problems of communication delay and instability seriously affect the real-time performance and reliability of the system. The fault prediction system highly depends on a high-speed and reliable communication network to transmit monitoring data and control instructions. However, in actual situations, the communication network is easily restricted by various factors such as network congestion and signal interference, resulting in data transmission delay or communication interruption. This uncertainty makes the system unable to obtain accurate monitoring data in a timely manner, thereby affecting the timely prediction and handling of power system faults and reducing the reliability and stability of power supply. In addition, the large system integration difficulty is also a key problem. There are various types of monitoring devices, control systems, and management systems in the power system, which come from different manufacturers and have different data formats, communication protocols, etc. Effectively integrating these devices and systems to achieve data sharing and interaction is a major challenge for the fault prediction system. Due to the lack of unified standards and specifications, the compatibility and collaborative working ability between different devices are poor, and it is difficult to form an efficient and accurate fault prediction system, which restricts the wide application and development of this system in the power system. Summary of the Invention

[0007] (1) Technical problems to be solved

[0008] Aiming at the deficiencies of the existing technology, the present invention provides a panoramic intelligent prediction system for harmonic impedance of power systems based on industrial big data, which has the advantages of adapting to the dynamic changes of the power grid structure, high real-time communication, and efficient system integration, and solves the problems of poor adaptability to dynamic changes of the power grid, unstable communication delay, and large system integration difficulty.

[0009] (2) Technical solutions

[0010] To achieve the above object, the present invention provides the following technical solutions: A panoramic intelligent prediction system for harmonic impedance of power systems based on industrial big data, including a power data acquisition module, a power data analysis module, a power fault pre-judgment module, a power fault response module, a user interaction interface module, a user feedback collection module, and a prediction efficiency improvement module;

[0011] The power data acquisition module collects power data through sensors, monitoring devices, and smart meters;

[0012] The power data analysis module calculates the network stability index Wf, the equipment compatibility index Pr, and the grid structure complexity Cy based on the collected data;

[0013] The power fault prediction module predicts system faults based on the network stability index Wf, the equipment compatibility index Pr, and the grid structure complexity Cy;

[0014] The power fault response module implements targeted processing of faults according to the prediction results;

[0015] The user interface module uses a visual interface to display the system operation status and fault prediction results to relevant staff. At the same time, according to the processing measures of the power fault response module, it supports staff to adjust system parameters;

[0016] The user feedback collection module is responsible for collecting feedback information from users during the use of the system;

[0017] The prediction efficiency improvement module optimizes the entire system according to the feedback information of the user feedback collection module and the data statistical analysis during the system operation.

[0018] Preferably, the power data collection module includes a power network data unit, a power equipment data unit, and a grid structure data unit.

[0019] Preferably, the power network data unit collects power network data through sensors and monitoring devices. The power network data unit numbers the network transmission delay time, real-time signal strength, and packet loss rate according to the characteristics of the power network data. The network transmission delay time, real-time signal strength, and packet loss rate are numbered as T, I, and D respectively.

[0020] Preferably, the power equipment data unit collects power equipment data through smart meters, sensors, and communication interfaces. The power equipment data unit numbers the identification matching degree of device j, the included angle of the data format type of device j, and the communication protocol consistency probability of device j according to the characteristics of the power equipment data. The identification matching degree of device j, the included angle of the data format type of device j, and the communication protocol consistency probability of device j are numbered as S j , θ j and H j .

[0021] Preferably, the power grid structure data unit collects power grid structure data through a geographic information system, a power monitoring system, and on-site inspections. The power grid structure data unit numbers the change value of the number of lines, the change value of the number of substations, the influence value of power grid topology change factors, and the influence value of equipment aging factors according to the characteristics of the power grid structure data. The change value of the number of lines, the change value of the number of substations, the influence value of power grid topology change factors, and the influence value of equipment aging factors are numbered as ΔL, Δm, G, and V, respectively.

[0022] Preferably, the power data analysis module includes a power network stability analysis unit, a power equipment compatibility analysis unit, and a power grid structure analysis unit. The power network stability analysis unit calculates the network stability index Wf according to the power network data. The power equipment compatibility analysis unit calculates the equipment compatibility index Pr according to the power network data. The power grid structure analysis unit calculates the complexity Cy of the power grid structure according to the power grid structure data.

[0023] Preferably, the power network stability analysis unit calculates the network stability index Wf according to the power network data, and its calculation formula is:

[0024]

[0025] In the formula, Wf represents the network stability index, T is the network transmission delay time, I represents the real-time signal strength, I max represents the maximum signal strength, D represents the packet loss rate, and a, b, and c respectively represent the weight coefficients of the network transmission delay time, the real-time signal strength, and the packet loss rate.

[0026] Preferably, the power equipment compatibility analysis unit calculates the equipment compatibility index Pr according to the power network data, and its calculation formula is:

[0027]

[0028] In the formula, Pr represents the equipment compatibility index, p j represents the weight factor of device j, S j represents the identification matching degree of device j, θ j represents the included angle of the data format type of device j, H j represents the communication protocol consistency probability of device j, and n represents the total number of devices.

[0029] Preferably, the power grid structure analysis unit calculates the complexity Cy of the power grid structure according to the power grid structure data, and its calculation formula is:

[0030] Cy = ΔL * β1 + Δm * β2 + G * β3 + V * β4

[0031] In the formula, Cy represents the complexity of the power grid structure, ΔL represents the change value of the number of lines, Δm represents the change value of the number of substations, G represents the influence value of the power grid topology change factor, V represents the influence value of the equipment aging factor, and β1, β2, β3, and β4 respectively represent the weight coefficients of the influence of lines, substations, power grid topology change factors, and equipment aging factors.

[0032] Preferably, the power data analysis module substitutes historical data into the power network data unit, the power equipment data unit, and the power grid structure data unit, and through the superposition calculation of historical data, obtains the fault prediction standard thresholds of the network stability index, the equipment compatibility index, and the complexity of the power grid structure. The power fault prediction module predicts system faults. When the network stability index Wf is lower than the set threshold, it is predicted that a fault is caused by network problems. When the equipment compatibility index Pr is too low, the fault risk in equipment integration is predicted. When the complexity of the power grid structure Cy is higher than the threshold, it is judged that there are fault hazards caused by changes in the power grid structure.

[0033] Compared with the prior art, the present invention provides a panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data, having the following beneficial effects:

[0034] 1. By calculating the network stability index Wf, the present invention is used to judge the real-time operation status and stability performance of the power network. When the network stability index Wf is lower than the set threshold, it is predicted that a fault is caused by network problems. When it is predicted that there are network problems, the module takes measures to optimize the network and add spare communication links, actively adjusts the network topology structure to reduce transmission delay, enhance signal strength, and reduce the packet loss rate, thereby effectively improving the stability and reliability of the network, and finally solving the problem of abnormal operation of the power system caused by network instability, achieving the beneficial effects of ensuring the continuity of power supply, improving the operation efficiency of the power system, enhancing the ability to cope with network faults, and ensuring the safe and stable operation of the power system.

[0035] 2. By calculating the equipment compatibility index Pr, the present invention is used to evaluate the collaborative working ability and integration effect among various devices in the power system. When the equipment compatibility index Pr is too low, the fault risk in equipment integration is predicted. When it is predicted that there is an equipment integration fault, the module uses the visual interface of the user interaction interface module to prompt technicians to perform equipment compatibility debugging, and specifically adjusts equipment parameters, updates communication programs, or replaces incompatible components, thereby ensuring that devices can smoothly exchange information and work together, and finally solving the problem of unstable or even paralyzed system operation caused by equipment incompatibility, achieving the beneficial effects of improving the overall operation efficiency of the power system, reducing faults and maintenance costs caused by equipment compatibility problems, and ensuring the reliability of power supply, providing a solid foundation for the stable operation of the power system.

[0036] 3. The present invention calculates the grid structure complexity Cy to evaluate the rationality and stability of the grid structure. When the grid structure complexity Cy is higher than the threshold, it judges the potential fault hazards caused by the grid structure change. When it is predicted that the fault risk is caused by the grid structure change, the module will re-evaluate the layout of the monitoring points of the system and update the model parameters in a timely manner, so as to optimize the monitoring system, ensure that it can more accurately monitor the key parts and potential risk points, make the monitoring data more representative, and finally solve the problem of insufficient fault monitoring caused by the complex grid structure, achieving the beneficial effects of improving the operation safety and reliability of the grid, reducing the fault occurrence rate, and enhancing the grid operation and maintenance efficiency, providing a strong guarantee for the stable supply of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a system flowchart of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0039] Please refer to Figure 1 , a panoramic intelligent prediction system for harmonic impedance of power system based on industrial big data, including a power data acquisition module, a power data analysis module, a power fault pre-judgment module, a power fault response module, a user interaction interface module, a user feedback collection module, and a prediction efficiency improvement module;

[0040] The power data acquisition module collects power data through sensors, monitoring devices, and smart meters. It collects power usage data of the user side through smart meters, and through the cooperation of sensors and monitoring devices, it obtains data of all links of the power system in an all-round way, including network status, equipment operation, and grid structure information;

[0041] The power data analysis module calculates the network stability index Wf, the equipment compatibility index Pr, and the grid structure complexity Cy according to the collected data. It obtains the network stability index Wf by processing the network transmission delay time, real-time signal strength, and packet loss rate; it jointly analyzes and calculates the equipment compatibility index Pr for data of different device identifiers, data format types, and communication protocol types; it calculates the grid structure complexity Cy according to data related to line addition and subtraction and substation expansion;

[0042] The power fault pre-judgment module predicts system faults according to the network stability index Wf, the equipment compatibility index Pr, and the grid structure complexity Cy;

[0043] According to the prediction results, the power failure response module implements targeted processing for the faults;

[0044] The user interaction interface module uses a visual interface to display the system operation status and fault prediction results to relevant staff. At the same time, according to the processing measures of the power failure response module, it supports the staff to adjust the system parameters, such as adjusting the monitoring frequency and modifying the device communication parameters;

[0045] The user feedback collection module is responsible for collecting the feedback information of users during the use of the system, including the evaluation of the accuracy of fault prediction and the feedback on operation convenience. The staff can set the feedback entrance through the interface. After the user submits the feedback, the system automatically records and classifies it;

[0046] The prediction efficiency improvement module optimizes the entire system according to the feedback information of the user feedback collection module and the data statistical analysis during the system operation. For example, according to the inaccurate fault prediction feedback by the user, it adjusts the data analysis algorithm parameters; for the operation convenience problem, it optimizes the design of the user interaction interface module, etc., so as to continuously improve the efficiency of the system fault prediction.

[0047] The power data acquisition module includes a power network data unit, a power equipment data unit, and a power grid structure data unit.

[0048] The power network data unit collects power network data through sensors and monitoring devices. The power network data unit numbers the network transmission delay time, real-time signal strength, and packet loss rate according to the characteristics of the power network data. The network transmission delay time, real-time signal strength, and packet loss rate are numbered as T, I, and D respectively.

[0049] The power equipment data unit collects power equipment data through smart meters, sensors, and communication interfaces. The power equipment data unit numbers the identification matching degree of device j, the included angle of the data format type of device j, and the communication protocol consistency probability of device j according to the characteristics of the power equipment data. The identification matching degree of device j, the included angle of the data format type of device j, and the communication protocol consistency probability of device j are numbered as S j , θ j and H j , where j represents different device aliases.

[0050] The power grid structure data unit collects power grid structure data through a geographic information system (GIS), a power monitoring system, and on-site inspections. The power grid structure data unit numbers the change value of the number of lines, the change value of the number of substations, the influence value of power grid topology change factors, and the influence value of equipment aging factors according to the characteristics of the power grid structure data. The change value of the number of lines, the change value of the number of substations, the influence value of power grid topology change factors, and the influence value of equipment aging factors are numbered as ΔL, Δm, G, and V respectively.

[0051] The power data analysis module includes a power network stability analysis unit, a power equipment compatibility analysis unit, and a power grid structure analysis unit. The power network stability analysis unit calculates the network stability index Wf according to the power network data. The power equipment compatibility analysis unit calculates the equipment compatibility index Pr according to the power network data. The power grid structure analysis unit calculates the complexity Cy of the power grid structure according to the power grid structure data.

[0052] The power network stability analysis unit calculates the network stability index Wf according to the power network data, and its calculation formula is:

[0053]

[0054] In the formula, Wf represents the network stability index, T is the network transmission delay time, I represents the real-time signal strength, I max represents the maximum signal strength, D represents the packet loss rate, and a, b, and c respectively represent the weight coefficients of the network transmission delay time, the real-time signal strength, and the packet loss rate.

[0055] The advantages are as follows: By calculating the network stability index Wf, it is used to judge the real-time operation status and stability performance of the power network. When the network stability index Wf is lower than the set threshold, it is predicted that a fault is caused by network problems. When it is predicted that it is a network problem, the module takes measures to optimize the network and add backup communication links, actively adjusts the network topology structure to reduce the transmission delay, enhance the signal strength, and reduce the packet loss rate, thereby effectively improving the stability and reliability of the network, and finally solving the problem of abnormal operation of the power system caused by network instability, achieving the beneficial effects of ensuring the continuity of power supply, improving the operation efficiency of the power system, and enhancing the ability to cope with network failures, and ensuring the safe and stable operation of the power system.

[0056] The power equipment compatibility analysis unit calculates the equipment compatibility index Pr according to the power network data, and its calculation formula is:

[0057]

[0058] In the formula, Pr represents the equipment compatibility index, p j represents the weight factor of equipment j, S jrepresents the identification matching degree of device j, which is used to measure the matching degree between the actual identification of the device and the expected or standard identification of the system, θ j The data format type angle of device j reflects the difference between the data format of the data transmitted by the device and the data format expected by the system. j represents the communication protocol consistency probability of device j, which is the consistency degree of the device following the predetermined communication protocol during the communication process, that is, the degree of fit between the device communication behavior and the standard communication protocol, and n represents the total number of devices.

[0059] The advantages are: by calculating the equipment compatibility index Pr, it is used to evaluate the collaborative working ability and integration effect between various devices in the power system. When the equipment compatibility index Pr is too low, the failure risk of equipment integration is predicted. When equipment integration failure is predicted, the module prompts technicians to perform equipment compatibility debugging through the visual interface of the user interaction interface module, and adjust equipment parameters, update communication programs or replace incompatible components in a targeted manner, thereby ensuring that the devices can smoothly exchange information and work together, and ultimately solve the problem of unstable or even paralyzed system operation caused by equipment incompatibility, thereby achieving the beneficial effects of improving the overall operation efficiency of the power system, reducing failures and maintenance costs caused by equipment compatibility issues, and ensuring the reliability of power supply, providing a solid foundation for the stable operation of the power system.

[0060] The grid structure analysis unit calculates the grid structure complexity Cy according to the grid structure data, and the calculation formula is:

[0061] Cy=ΔL*β1+Δm*β2+G*β3+V*β4

[0062] In the formula, Cy represents the complexity of the grid structure, ΔL represents the change in the number of lines (the number of new or reduced lines), Δm represents the change in the number of substations (the number of new or expanded substations), G represents the impact of the grid topology change factor, V represents the impact of the equipment aging factor, β1, β2, β3, and β4 represent the weight coefficients of the influence of lines, substations, grid topology change factors, and equipment aging factors, respectively, and are used to adjust the importance of each factor in the calculation.

[0063] The advantages are as follows: By calculating the grid structure complexity Cy, it is used to evaluate the rationality and stability of the grid structure. When the grid structure complexity Cy is higher than the threshold, the potential fault hazards caused by the change of the grid structure are judged. When it is predicted that the fault risk is caused by the change of the grid structure, the module will re-evaluate the layout of the monitoring points of the system and update the model parameters in a timely manner, so as to optimize the monitoring system, ensure that it can more accurately monitor the key parts and potential risk points, make the monitoring data more representative, and finally solve the problem of inadequate fault monitoring caused by the complex grid structure, achieving the beneficial effects of improving the operation safety and reliability of the grid, reducing the fault occurrence rate, and enhancing the grid operation and maintenance efficiency, and providing a strong guarantee for the stable supply of the power system.

[0064] The power fault prediction module predicts system faults based on the network stability index Wf, the device compatibility index Pr, and the grid structure complexity Cy. When the network stability index Wf is lower than the set threshold, it is predicted that a fault is caused by network problems. When the device compatibility index Pr is too low, the fault risk in device integration is predicted. When the grid structure complexity Cy is higher than the threshold, the potential fault hazards caused by the change of the grid structure are judged.

[0065] The power fault response module takes targeted measures to handle faults according to the prediction results. When it is predicted that there are network problems, the module takes measures to optimize the network and add backup communication links. When a device integration fault is predicted, the module arranges technicians to conduct device compatibility debugging or upgrade. When it is predicted that the fault risk is caused by the change of the grid structure, the module will re-evaluate the layout of the monitoring points of the system and update the model parameters in a timely manner.

[0066] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data, characterized in that, It includes a power data acquisition module, a power data analysis module, a power fault prediction module, a power fault response module, a user interaction interface module, a user feedback collection module, and a prediction efficiency improvement module; The power data acquisition module collects power data through sensors, monitoring devices, and smart meters; The power data analysis module calculates the network stability index Wf, the device compatibility index Pr, and the grid structure complexity y based on the collected data; The power fault prediction module predicts system faults based on the network stability index Wf, the device compatibility index Pr, and the grid structure complexity Cy; The power fault response module implements targeted processing of faults according to the prediction results; The user interaction interface module uses a visual interface to display the system operation status and fault prediction results to relevant staff. At the same time, according to the processing measures of the power fault response module, it supports staff to adjust system parameters; The user feedback collection module is responsible for collecting feedback information from users during the use of the system; The prediction efficiency improvement module optimizes the entire system based on the feedback information of the user feedback collection module and the data statistical analysis during the system operation; 2. The panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data according to claim 1, wherein: The power data acquisition module includes a power network data unit, a power equipment data unit, and a grid structure data unit; 3. The panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data according to claim 2, wherein: The power network data unit collects power network data through sensors and monitoring devices. The power network data unit numbers the network transmission delay time, real-time signal strength, and packet loss rate according to the characteristics of the power network data. The network transmission delay time, real-time signal strength, and packet loss rate are numbered as T, I, and D respectively; 4. The panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data according to claim 2, wherein: The power equipment data unit collects power equipment data through smart meters, sensors, and communication interfaces. The power equipment data unit numbers the identification matching degree of device j, the included angle of the data format type of device j, and the communication protocol consistency probability of device j according to the characteristics of the power equipment data. The identification matching degree of device j, the included angle of the data format type of device j, and the communication protocol consistency probability of device j are numbered as S j , θ j , and H j .

5. The panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data according to claim 2, characterized in that: The grid structure data unit collects grid structure data through a geographic information system, a power monitoring system, and on-site inspections. The grid structure data unit numbers the change value of the number of lines, the change value of the number of substations, the influence value of grid topology change factors, and the influence value of equipment aging factors according to the characteristics of the grid structure data. The change value of the number of lines, the change value of the number of substations, the influence value of grid topology change factors, and the influence value of equipment aging factors are numbered as ΔL, Δm, G, and V respectively; 6. The panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data according to claim 1, characterized in that: The power data analysis module includes a power network stability analysis unit, a power equipment compatibility analysis unit, and a grid structure analysis unit. The power network stability analysis unit calculates the network stability index Wf based on the power network data. The power equipment compatibility analysis unit calculates the device compatibility index Pr based on the power network data. The grid structure analysis unit calculates the grid structure complexity Cy based on the grid structure data; 7. An intelligent panoramic prediction system for harmonic impedance of a power system based on industrial big data according to claim 6, characterized in that: The power network stability analysis unit calculates the network stability index Wf based on the power network data, and its calculation formula is: In the formula, Wf represents the network stability index, T is the network transmission delay time, I represents the real-time signal strength, and I max represents the maximum signal strength, D represents the packet loss rate, and a, b, and c respectively represent the weight coefficients of the network transmission delay time, real-time signal strength, and packet loss rate.

8. An intelligent panoramic prediction system for harmonic impedance of a power system based on industrial big data according to claim 6, characterized in that: The power equipment compatibility analysis unit calculates the device compatibility index Pr based on the power network data, and its calculation formula is: In the formula, Pr represents the device compatibility index, p j represents the weight factor of device j, S j represents the identification matching degree of device j, θ j represents the included angle of the data format type of device j, H j represents the communication protocol consistency probability of device j, and n represents the total number of devices.

9. The panoramic intelligent prediction system for harmonic impedance of a power system based on industrial big data according to claim 6, wherein: The grid structure analysis unit calculates the grid structure complexity Cy based on the grid structure data, and its calculation formula is: Cy = ΔL * β1 + Δm * β2 + G * β3 + V * β4 In the formula, Cy represents the complexity of the power grid structure, ΔL represents the change value of the number of lines, Δm represents the change value of the number of substations, G represents the influence value of the power grid topology change factor, V represents the influence value of the equipment aging factor, and β1, β2, β3, and β4 respectively represent the weight coefficients of the influences of lines, substations, power grid topology change factors, and equipment aging factors.

10. An intelligent panoramic prediction system for harmonic impedance of a power system based on industrial big data according to claim 1, characterized in that: The power data analysis module substitutes historical data into the power network data unit, the power equipment data unit, and the power grid structure data unit, and through the superposition calculation of historical data, obtains the fault prediction standard thresholds of the network stability index, the equipment compatibility index, and the complexity of the power grid structure. The power fault prediction module predicts system faults. When the network stability index Wf is lower than the set threshold, it is predicted that the fault is caused by network problems. When the equipment compatibility index Pr is too low, the fault risk in equipment integration is predicted. When the complexity of the power grid structure Cy is higher than the threshold, it is judged that there are potential faults caused by the change of the power grid structure.

Images