Distributed power grid node health monitoring and prediction method

Abstract

The present invention relates to the field of power grid monitoring technology, and specifically discloses a distributed power grid node health monitoring and prediction method, the method comprising: obtaining distributed power grid nodes, marking them as each power grid node, and obtaining health monitoring data of each power grid node; processing the equipment status data to obtain the equipment status abnormality evaluation index of each power grid node, and comprehensively analyzing to obtain the data accuracy evaluation value of each power grid node; screening to obtain each normal monitoring power grid node according to the data accuracy evaluation value of each power grid node; and providing evaluation feedback according to the health status evaluation value of each normal monitoring power grid node. By providing a distributed power grid node health monitoring and prediction method, the present invention can timely discover and handle health problems of power grid nodes, help prevent power outages or safety accidents caused by equipment failures, can more reasonably allocate power resources, improve the operating efficiency of the power grid, and help provide better power output and stability.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid monitoring, and in particular to a distributed power grid node health monitoring and prediction method. Background Art

[0002] At present, distributed power grid node health monitoring and prediction is a very important part of the field of power grid data processing technology. With the advancement of technology and the growth of demand, providing more refined distributed power grid node health monitoring and prediction methods has become the norm. Efficient and accurate distributed power grid node health monitoring and prediction methods are of great significance to improving the operation and maintenance efficiency and stability of the power grid.

[0003] For example, the invention patent with the announcement number CN112034306B is a method for robust detection of power failure in a joint distribution network based on distributed nodes. The method is carried out in the following steps: 1) In the power-on state, multiple distributed nodes collect current sensing signals in the same distribution network line and send them to the joint power failure detection unit. The joint power failure detection unit processes the received current sensing signals and estimates the time delay and phase parameters of the current sensing signals of each node; 2) When power failure detection is required, multiple distributed nodes collect current sensing signals in the distribution network line and send them to the joint power failure detection unit. The joint power failure detection performs joint power failure robust detection to determine the power failure location.

[0004] For example, the invention patent with announcement number CN117031214B is a method, system, medium and equipment for intelligent monitoring of power grid faults. The switch nodes are encoded according to the relative position relationship between the distributed power sources and the switch nodes and the main power source of the distribution network, and the correlation function and fitness function are constructed according to the current direction of the main power source of the distribution network and the distributed power source flowing through the switch nodes. The new encoding method is obtained based on the topological structure analysis after the distributed power source is connected, and the iterative update method of the number of pigeon groups in the pigeon group optimization algorithm is improved in exponential form, so that the local search is more accurate and the fault location is more accurate.

[0005] However, in the process of implementing the technical solution of the invention in the embodiments of the present application, the present application discovered that the above-mentioned technology has at least the following technical problems: the current distributed power grid node health monitoring and prediction methods focus more on fault location, but since the data involved in the power grid nodes are complex and changeable, the monitored power grid node data may be inaccurate, thereby affecting the judgment of the health status of the power grid. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a distributed power grid node health monitoring and prediction method, which can effectively solve the problems involved in the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: The present invention provides a distributed power grid node health monitoring and prediction method, including: obtaining distributed power grid nodes, marking them as each power grid node, and obtaining health monitoring data of each power grid node, wherein the health monitoring data includes power grid status data, data acquisition environment data and equipment status data.

[0008] The equipment status data is processed to obtain the equipment status anomaly assessment index of each power grid node. According to the equipment status anomaly assessment index of each power grid node and the data collection environment data, a comprehensive analysis is performed to obtain the data accuracy assessment value of each power grid node.

[0009] According to the data accuracy evaluation value of each power grid node, each normal monitoring power grid node is screened and feedback is provided.

[0010] According to the abnormal equipment status assessment index and grid status data of each normal monitoring grid node, a comprehensive analysis is performed to obtain the health status assessment value of each normal monitoring grid node, and evaluation feedback is performed on each normal monitoring grid node based on the health status assessment value of each normal monitoring grid node.

[0011] As a further method, the device status data is processed to obtain the device status anomaly assessment index of each power grid node. The specific processing process is: the device status data includes the mechanical stress, output power and insulation resistance of each device.

[0012] The reference standard mechanical stress, allowable deviation mechanical stress, reference standard output power, allowable deviation output power and critical insulation resistance are extracted from the distributed power grid database, and the equipment status abnormality assessment index of each power grid node is obtained through comprehensive analysis.

[0013] As a further method, the data accuracy evaluation value of each power grid node is obtained by comprehensive analysis based on the equipment status abnormality evaluation index and data acquisition environment data of each power grid node. The specific analysis process is: the data acquisition environment data includes working environment data and data acquisition parameters.

[0014] The environmental interference value of each power grid node is obtained based on the working environment data processing.

[0015] The data acquisition parameters include sampling rate and sensor response time.

[0016] The critical sampling rate and critical sensor response time are extracted from the distributed power grid database, and the data accuracy evaluation value of each power grid node is obtained through comprehensive analysis based on the equipment status abnormality evaluation index and environmental interference value of each power grid node. The data accuracy evaluation value of each power grid node is used to quantify the data accuracy of each power grid node.

[0017] As a further method, the environmental interference value of each power grid node is obtained according to the working environment data processing. The specific processing process is: the working environment data includes the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree of each environmental monitoring point.

[0018] The reference standard temperature, allowable deviation temperature, reference standard wind speed, allowable deviation wind speed, critical electromagnetic interference value, critical communication noise intensity and critical dust degree are extracted from the distributed power grid database, and the environmental interference value of each power grid node is obtained by comprehensive analysis. The data accuracy assessment threshold correction value is obtained according to the matching of the environmental interference value of each power grid node.

[0019] As a further method, the data accuracy assessment threshold correction value is obtained by matching the environmental interference value of each power grid node. The specific matching process is: matching the environmental interference value of each power grid node with the data accuracy assessment threshold correction value corresponding to each environmental interference value interval preset in the distributed power grid database to obtain the data accuracy assessment threshold correction value of each power grid node.

[0020] As a further method, the normal monitoring grid nodes are screened according to the data accuracy evaluation value of each grid node and feedback is provided. The specific screening process is: extracting the data accuracy evaluation threshold from the distributed grid database, adding the data accuracy evaluation threshold to the data accuracy evaluation threshold correction value of each grid node to obtain the updated data accuracy evaluation threshold of each grid node, and comparing the data accuracy evaluation value of each grid node with the updated data accuracy evaluation threshold of each grid node respectively; if the data accuracy evaluation value of a grid node is greater than or equal to the updated data accuracy evaluation threshold of the grid node, the grid node is marked as a normal monitoring grid node; if the data accuracy evaluation value of a grid node is less than the updated data accuracy evaluation threshold of the grid node, feedback correction is provided.

[0021] As a further method, the health status assessment value of each normal monitored power grid node is obtained by comprehensive analysis based on the equipment status abnormality assessment index and power grid status data of each normal monitored power grid node. The specific analysis process is: the power grid status data includes the power grid frequency and power grid load at each time node within the monitoring period.

[0022] The reference standard grid frequency and the allowable deviation grid frequency are extracted from the distributed power grid database, and the health status assessment value of each normal monitoring grid node is obtained by comprehensive analysis based on the equipment status abnormality assessment index of each normal monitoring grid node.

[0023] As a further method, the evaluation feedback is performed on each normal monitoring power grid node according to the health status evaluation value of each normal monitoring power grid node. The specific evaluation process is: extracting the health status evaluation threshold from the distributed power grid database, comparing the health status evaluation value of each normal monitoring power grid node with the health status evaluation threshold, if the health status evaluation value of a normal monitoring power grid node is greater than or equal to the health status evaluation threshold, then the normal monitoring power grid node is evaluated as healthy, if the health status evaluation value of a normal monitoring power grid node is less than the health status evaluation threshold, then the normal monitoring power grid node is evaluated as unhealthy and feedback correction is performed.

[0024] As a further method, the feedback correction is performed, and the specific process is: subtracting the health status assessment threshold from the health status assessment value of each unhealthy and normal monitoring power grid node to obtain the health status assessment difference of each unhealthy and normal monitoring power grid node, extracting the first health status assessment difference threshold and the second health status assessment difference threshold from the distributed power grid database, and comparing the health status assessment difference of each unhealthy and normal monitoring power grid node with the health status assessment difference threshold; if the health status assessment difference of an unhealthy and normal monitoring power grid node is greater than or equal to the first health status assessment difference threshold, immediately notify the relevant staff to conduct an on-site inspection of the unhealthy and normal monitoring power grid node; if the health status assessment difference of an unhealthy and normal monitoring power grid node is less than the first health status assessment difference threshold and greater than the second health status assessment difference threshold, then increase the maintenance frequency of the node equipment; if the health status assessment difference of an unhealthy and normal monitoring power grid node is less than the second health status assessment difference threshold, then increase the monitoring frequency of the node.

[0025] As a further method, the health status evaluation value of each normal monitoring grid node is specifically expressed as:

[0026]

[0027] Among them, Hs c represents the health status assessment value of the cth normally monitored power grid node, Ma c represents the abnormal evaluation index of the equipment status of the cth normally monitored power grid node, w cb represents the grid frequency of the cth normally monitored grid node at the bth time node, w 0 represents the reference standard grid frequency, Δw represents the allowable deviation grid frequency, h cb represents the grid load of the cth normally monitored grid node at the bth time node, θ 1 Indicates the health status assessment impact factor corresponding to the set equipment status abnormality assessment index, θ 2 Indicates the health status assessment impact factor corresponding to the set grid frequency, θ 3represents the health status assessment influencing factor corresponding to the set power grid load, c represents the number of each normal monitoring power grid node, c = 1, 2, 3, ..., q, q represents the total number of normal monitoring power grid nodes, b represents the number of each time node, b = 1, 2, 3, ..., r, r represents the total number of time nodes.

[0028] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0029] (1) The present invention provides a distributed power grid node health monitoring and prediction method, which can timely discover and deal with health problems of power grid nodes, help prevent power outages or safety accidents caused by equipment failures, allocate power resources more reasonably, avoid resource waste and excessive consumption, improve the operating efficiency of the power grid, and help provide better power output and stability.

[0030] (2) By evaluating the data accuracy assessment value of each power grid node, the present invention can timely discover data anomalies and quickly take corresponding countermeasures, thereby improving the safety and stability of power grid operation, helping to understand the actual load conditions and energy consumption of power grid nodes, thereby providing a basis for the rational allocation of power grid resources and further improving the efficiency and quality of power grid operation and maintenance management.

[0031] (3) By evaluating the environmental interference value of each power grid node, the present invention can predict the type and time of possible failure of power grid equipment, so as to take preventive measures in advance. It can also provide accurate fault location information for power grid operation and maintenance personnel, helping them to quickly find the fault point and repair it, shorten the power outage time and recovery time, and further formulate a more scientific and reasonable operation and maintenance strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The present invention is further described using the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0033] Figure 1 It is a schematic diagram of the method flow of the present invention.

[0034] Figure 2 It is a schematic diagram of the functional relationship between the health status evaluation value of each normal monitoring power grid node and the equipment status abnormal evaluation index of each normal monitoring power grid node of the present invention. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0036] Reference Figure 1 As shown, the present invention provides a distributed power grid node health monitoring and prediction method, including: obtaining distributed power grid nodes, marking them as each power grid node, obtaining health monitoring data of each power grid node, and the health monitoring data includes power grid status data, data acquisition environment data and equipment status data.

[0037] The equipment status data is processed to obtain the equipment status anomaly assessment index of each power grid node. According to the equipment status anomaly assessment index of each power grid node and the data collection environment data, a comprehensive analysis is performed to obtain the data accuracy assessment value of each power grid node.

[0038] According to the data accuracy evaluation value of each power grid node, each normal monitoring power grid node is screened and feedback is provided.

[0039] According to the abnormal equipment status assessment index and grid status data of each normal monitoring grid node, a comprehensive analysis is performed to obtain the health status assessment value of each normal monitoring grid node, and evaluation feedback is performed on each normal monitoring grid node based on the health status assessment value of each normal monitoring grid node.

[0040] Specifically, the device status data is processed to obtain the device status abnormality assessment index of each power grid node. The specific processing process is: the device status data includes the mechanical stress, output power and insulation resistance of each device.

[0041] The reference standard mechanical stress, allowable deviation mechanical stress, reference standard output power, allowable deviation output power and critical insulation resistance are extracted from the distributed power grid database, and the equipment status abnormality assessment index of each power grid node is obtained through comprehensive analysis. The equipment status feedback is performed according to the equipment status abnormality assessment index of each power grid node.

[0042] In a specific embodiment, mechanical stress refers to the sum of the stresses to which the device is subjected during operation, which can be measured by installing stress gauges at key locations of the device; output power refers to the electrical energy output by the device during operation, which can be calculated by multiplying the output current and the output voltage, wherein the output current and the output voltage are measured by an ammeter and a voltmeter, respectively; insulation resistance refers to the ability of the insulating material in the device to block the current, which can be measured using a megohmmeter.

[0043] Furthermore, the specific numerical expression of the abnormal equipment status evaluation index of each power grid node is:

[0044]

[0045] Among them, Ma i represents the abnormal evaluation index of the equipment status of the i-th grid node, Y ij represents the mechanical stress of the jth device at the i-th grid node, Y 0 represents the reference standard mechanical stress, ΔY represents the allowable deviation mechanical stress, p ij represents the output power of the jth device at the i-th grid node, p 0 represents the reference standard output power, Δp represents the allowable deviation output power, Z ij represents the insulation resistance of the jth device at the i-th grid node, Z 0 represents the critical insulation resistance, ω 1 Indicates the equipment status abnormality assessment impact factor corresponding to the set mechanical stress, ω 2 Indicates the equipment status abnormality assessment impact factor corresponding to the set output power, ω 3 It represents the equipment status abnormality assessment impact factor corresponding to the set insulation resistance, i represents the number of each grid node, i=1,2,3,...,m, m represents the total number of grid nodes, j represents the number of each device, j=1,2,3,...,n, n represents the total number of devices.

[0046] The algorithm of this embodiment combines the mechanical stress, output power and insulation resistance of each device, and comprehensively analyzes to obtain the abnormal equipment status evaluation index of each grid node. When the output power of the device increases, it may be accompanied by an increase in mechanical stress. For example, in a distributed power generation system, as the output power increases, the mechanical stress on the rotor, stator and other components of the generator will also increase accordingly; changes in output power may affect the insulation resistance of the device. For example, under long-term high-load operation, the device may cause aging of the insulation material due to overheating, thereby reducing the insulation resistance; mechanical stress usually does not directly affect the insulation resistance of the device, but may indirectly affect the insulation resistance by affecting the physical structure and material properties of the device. For example, excessive mechanical stress may cause the insulation material to rupture or deform, thereby reducing the insulation resistance. Comprehensive analysis can obtain a more comprehensive abnormal equipment status evaluation index.

[0047] Table 1 Example of equipment status abnormality evaluation index data for each power grid node

[0048]

[0049] As shown in Table 1, the equipment state abnormality evaluation index of each grid node is jointly determined by mechanical stress, output power and insulation resistance. In a specific embodiment, the reference standard mechanical stress is 10MPa, the allowable deviation mechanical stress is 3MPa, the reference standard output power is 100kW, the allowable deviation output power is 10kW, the critical insulation resistance is 5MΩ, the set mechanical stress corresponding to the equipment state abnormality evaluation impact factor is 0.3, the set output power corresponding to the equipment state abnormality evaluation impact factor is 0.4, and the set insulation resistance corresponding to the equipment state abnormality evaluation impact factor is 0.3. This formula takes into account three key factors, namely the mechanical stress, output power and insulation resistance of each device at each grid node, which can ensure that the device will not fail or be damaged when bearing the expected physical load, help prevent grid accidents caused by equipment failure, and can timely discover problems such as insulation aging, moisture or damage, thereby avoiding electrical failures and electric shock accidents. It can also ensure the balance of supply and demand of the grid, avoid grid fluctuations or collapse caused by excess or insufficient power, further reduce energy waste and improve the overall efficiency of the grid. By standardizing the mechanical stress, output power and insulation resistance of each device at each grid node, we ensure that they are compared at the same level, which improves the fairness and comparability of the evaluation. 0 、p 0 and Z 0 The setting can avoid grid safety problems caused by unreasonable mechanical stress, unstable output power and too low insulation resistance. By weighting the influence of mechanical stress, output power and insulation resistance of each device at each grid node, it reflects their relative importance in the evaluation index. The weights of different factors can be adjusted according to different needs, making the model highly adaptable. It is not difficult to see that the larger the signal amplitude, the larger the signal-to-noise ratio or the smaller the signal frequency deviation, the larger the abnormal equipment status evaluation index. By evaluating the abnormal equipment status evaluation index of each grid node, it is possible to timely discover the existing faults or potential faults of the equipment, so as to take necessary maintenance or replacement measures to avoid the expansion of faults or power outages in the grid. It can provide a scientific basis for the maintenance plan and replacement strategy of the equipment, ensure that the equipment maintains the best operating state during its life cycle, and help to timely discover and deal with risk factors that may cause grid accidents, thereby reducing the incidence of grid accidents. It can also provide key information for emergency response, help quickly locate the fault point and take corresponding emergency measures to ensure the safe operation of the grid and further improve the efficiency of grid management.

[0050] In a specific embodiment, the value range of the equipment state abnormality assessment influencing factor corresponding to mechanical stress, output power and insulation resistance is between 0 and 1, which represents the numerical value of the influence degree of mechanical stress, output power and insulation resistance on the equipment state abnormality assessment index. Each equipment state abnormality assessment influencing factor can be obtained from the distributed power grid database. By adjusting the value of the influencing factor, the influence degree of different factors on the final equipment state abnormality assessment index can be flexibly adjusted. The corresponding relationship can be a pre-set mapping relationship. For example, mechanical stress, output power and insulation resistance form a mapping set with the weight factors corresponding to the mechanical stress, output power and insulation resistance preset in the distributed power grid database, and the real-time mechanical stress, output power and insulation resistance are brought into the mapping set to obtain the weight factors corresponding to the mechanical stress, output power and insulation resistance. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0051] Furthermore, equipment status feedback is performed based on the equipment status abnormality assessment index of each power grid node. The specific process is: extract the equipment status abnormality assessment threshold from the distributed power grid database, compare the equipment status abnormality assessment index of each power grid node with the equipment status abnormality assessment threshold; if the equipment status abnormality assessment index of a certain power grid node is greater than or equal to the equipment status abnormality assessment threshold, the equipment of the power grid node is evaluated as unqualified and the relevant staff is notified; if the equipment status abnormality assessment index of a certain power grid node is less than the equipment status abnormality assessment threshold, the equipment of the power grid node is evaluated as qualified.

[0052] Specifically, according to the equipment status abnormality evaluation index of each power grid node and the data acquisition environment data, a comprehensive analysis is performed to obtain the data accuracy evaluation value of each power grid node. The specific analysis process is: the data acquisition environment data includes working environment data and data acquisition parameters.

[0053] The environmental interference value of each power grid node is obtained based on the working environment data processing.

[0054] The data acquisition parameters include sampling rate and sensor response time.

[0055] The critical sampling rate and critical sensor response time are extracted from the distributed power grid database, and the data accuracy evaluation value of each power grid node is obtained through comprehensive analysis based on the equipment status abnormality evaluation index and environmental interference value of each power grid node. The data accuracy evaluation value of each power grid node is used to quantify the data accuracy of each power grid node.

[0056] Furthermore, the environmental interference value of each power grid node is obtained according to the working environment data processing, and the specific processing process is: the working environment data includes the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree of each environmental monitoring point.

[0057] The reference standard temperature, allowable deviation temperature, reference standard wind speed, allowable deviation wind speed, critical electromagnetic interference value, critical communication noise intensity and critical dust degree are extracted from the distributed power grid database, and the environmental interference value of each power grid node is obtained by comprehensive analysis. The data accuracy assessment threshold correction value is obtained according to the matching of the environmental interference value of each power grid node.

[0058] In a specific embodiment, temperature is an important factor affecting the performance of power grid equipment. By monitoring the temperature of each node, overheating can be discovered in time to prevent equipment from being damaged due to overheating, thereby ensuring the stable operation of the power grid. The temperature can be obtained through a temperature sensor; changes in wind speed can affect the heat dissipation effect of power grid equipment. By monitoring the wind speed, the heat dissipation design can be optimized and the operating efficiency of the equipment can be improved. The wind speed can be monitored by a wind speed sensor; the electromagnetic interference value can be directly obtained through an electromagnetic interference sensor, and the communication noise intensity can be obtained through a noise meter. By real-time monitoring and analysis of changes in electromagnetic interference values ​​and communication noise intensity, potential interference problems can be discovered and dealt with in time; dust accumulation can affect the heat dissipation and insulation performance of power grid equipment. By monitoring the dust level, an effective cleaning and maintenance plan can be formulated to keep the equipment in good operating condition. The dust level can be obtained through a dust sensor.

[0059] Specifically, the environmental interference value of each power grid node is expressed as follows:

[0060]

[0061] Among them, En i represents the environmental interference value of the ith power grid node, e represents the natural constant, T ix represents the temperature of the xth environmental monitoring point of the ith grid node, T 0 Indicates the reference standard temperature, ΔT indicates the allowable deviation temperature, F ix represents the wind speed at the xth environmental monitoring point of the ith grid node, F 0 represents the reference standard wind speed, ΔF represents the allowable deviation wind speed, d ix represents the dust level of the xth environmental monitoring point of the ith grid node, d 0 Indicates critical dust level, C ix represents the electromagnetic interference value of the xth environmental monitoring point of the ith grid node, C 0 Indicates the critical electromagnetic interference value, N ix represents the communication noise intensity of the xth environmental monitoring point of the ith grid node, N 0 represents the critical communication noise intensity, ρ 1 Indicates the environmental interference factor corresponding to the set temperature, ρ 2 Indicates the environmental interference factor corresponding to the set wind speed, ρ 3Indicates the environmental interference factor corresponding to the set dust level, ρ 4 Indicates the environmental interference impact factor corresponding to the set electromagnetic interference value, ρ 5 It represents the environmental interference impact factor corresponding to the set communication noise intensity, i represents the number of each grid node, i=1,2,3,...,m, m represents the total number of grid nodes, x represents the number of each environmental monitoring point, x=1,2,3,...,y, y represents the total number of environmental monitoring points.

[0062] The algorithm of this embodiment combines the temperature, wind speed, electromagnetic interference value, communication noise intensity and dustiness of each environmental monitoring point, and comprehensively analyzes to obtain the environmental interference value of each power grid node. Changes in wind speed will affect the distribution of ambient temperature. When the wind speed is high, air flow will accelerate heat loss, thereby reducing the ambient temperature; at the same time, dust deposition may affect the heat dissipation performance of the equipment, causing the temperature to rise, and the higher the temperature, the faster the deposition and solidification of dust may be; changes in wind speed may affect the diffusion and deposition of dust. When the wind is strong, the dust may be blown away; and when the wind is weak, the dust may be more easily deposited. The size of the electromagnetic interference value directly affects the strength of the communication noise intensity. When the electromagnetic interference value is larger, the interference signal received in the communication system will also be correspondingly enhanced, thereby increasing the communication noise intensity. Comprehensive analysis can obtain a more comprehensive environmental interference value.

[0063] It should be explained that in this embodiment, five key factors, namely, the temperature, wind speed, electromagnetic interference value, communication noise intensity and dustiness of each environmental monitoring point, are considered, and abnormal conditions of power grid equipment can be discovered in time, so as to take preventive measures to prevent equipment failure from causing power grid accidents, which is helpful to improve the safety and reliability of the power grid, and optimize the resource allocation of the power grid, such as adding heat dissipation equipment in areas with higher temperatures, strengthening the fixation and protection of equipment in areas with higher wind speeds, etc., thereby reducing the operating cost of the power grid, improving economic benefits, and further providing a scientific basis for power grid management and environmental monitoring. By standardizing the temperature, wind speed, electromagnetic interference value, communication noise intensity and dustiness of each environmental monitoring point, it is ensured that they are compared at the same magnitude, which improves the fairness and comparability of the evaluation. By weighting the influence of the temperature, wind speed, electromagnetic interference value, communication noise intensity and dustiness of each environmental monitoring point, it reflects their relative importance in the evaluation index, and the weights of different factors can be adjusted according to different needs, so that the formula has good adaptability. It is not difficult to see that the greater the temperature deviation or wind speed deviation or electromagnetic interference value or communication noise intensity or dustiness, the greater the environmental interference value. By evaluating the environmental interference value of each power grid node, the power grid equipment can be reasonably configured and optimized to improve the equipment's anti-interference ability and operational stability. It can also predict the type and time of possible failures in power grid equipment, so that preventive measures can be taken in advance to avoid or reduce the occurrence of accidents. It can also provide accurate fault location information for power grid operation and maintenance personnel, helping them to quickly find the fault point and repair it, shorten the power outage time and recovery time, and further formulate more scientific and reasonable operation and maintenance strategies.

[0064] In a specific embodiment, the value range of the environmental interference influence factor corresponding to the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree is between 0 and 1, which represents the numerical value of the influence degree of the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree on the environmental interference value. Each environmental interference influence factor can be obtained from the distributed power grid database. By adjusting the value of the influence factor, the influence degree of different factors on the final environmental interference value can be flexibly adjusted. The corresponding relationship can be a pre-set mapping relationship. For example, the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree form a mapping set with the weight factors corresponding to the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree preset in the distributed power grid database. The real-time temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree are brought into the mapping set to obtain the weight factors corresponding to the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust degree. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0065] Specifically, the data accuracy assessment threshold correction value is obtained according to the environmental interference value matching of each power grid node. The specific matching process is: matching the environmental interference value of each power grid node with the data accuracy assessment threshold correction value corresponding to each environmental interference value interval preset in the distributed power grid database to obtain the data accuracy assessment threshold correction value of each power grid node.

[0066] It should be understood that, through the relationship between the environmental interference values ​​in the historical data and the data accuracy assessment threshold correction values, a mapping set of environmental interference values ​​and corresponding data accuracy assessment threshold correction values ​​is constructed, and the real-time environmental interference values ​​are input to obtain the corresponding data accuracy assessment threshold correction values ​​from the mapping set.

[0067] In a specific embodiment, the sampling rate refers to the number of times data is collected per unit time, which determines the degree of precision with which the system can capture signal changes. A reasonable sampling rate can capture the key features of the signal and provide sufficient data support for equipment status assessment, which can be obtained through the configuration interface of the power grid monitoring system. The sensor response time refers to the time required for the sensor to output a stable signal from receiving a stimulus signal. A fast response time can ensure that the system responds to changes in equipment status in a timely manner, improve the real-time performance of the system, and can be measured by an oscilloscope.

[0068] Specifically, the data accuracy evaluation value of each power grid node is expressed as follows:

[0069]

[0070] Among them, Da i represents the data accuracy evaluation value of the i-th power grid node, Ma i represents the abnormal evaluation index of the equipment status of the ith power grid node, En i represents the environmental interference value of the ith grid node, s i represents the sampling rate of the ith grid node, s 0 represents the critical sampling rate, Δs represents the allowable deviation sampling rate, and t i represents the sensor response time of the ith grid node, t 0 represents the critical sensor response time, β 1 Indicates the data accuracy assessment impact factor corresponding to the set device status abnormality assessment index, β 2 Indicates the data accuracy assessment impact factor corresponding to the set environmental interference value, β 3 Indicates the data accuracy assessment impact factor corresponding to the set sampling rate, β 4 It represents the data accuracy assessment influencing factor corresponding to the set sensor response time, i represents the number of each power grid node, i=1,2,3,...,m, and m represents the total number of power grid nodes.

[0071] The algorithm of this embodiment combines the device state abnormality assessment index, environmental interference value, sampling rate and sensor response time, and comprehensively analyzes to obtain the data accuracy assessment value of each power grid node. The higher the sampling rate, the more signal details can be captured, making the device state abnormality assessment index more accurate; the response time of the sensor determines the system's response speed to changes in the device state. The shorter the response time, the faster the abnormal changes in the device state can be detected; the environmental interference value may affect the selection of the sampling rate. In an environment with greater interference, the sampling rate may need to be increased to capture more signal details, thereby offsetting the impact of interference on data acquisition; there is a certain balance between the sampling rate and the sensor response time. A higher sampling rate may require a faster sensor response time to match the speed of data acquisition. Comprehensive analysis can obtain a more comprehensive data accuracy assessment value.

[0072] It should be explained that this embodiment takes into account four key factors, namely, the equipment status abnormality assessment index, environmental interference value, sampling rate, and sensor response time. It can reasonably configure system resources, such as adjusting the sampling rate, optimizing the sensor layout, etc., to improve the overall performance of the system, and can also reduce system energy consumption and improve energy utilization efficiency. It helps to simplify the operation and maintenance process, reduce manual intervention, improve operation and maintenance efficiency, and avoid downtime losses and maintenance costs caused by failures. It helps operation and maintenance personnel to promptly discover and deal with safety hazards and improve operation and maintenance safety. By standardizing the sampling rate and sensor response time to ensure that they are compared at the same level, the fairness and comparability of the evaluation are improved, and at the same time, s 0 and t 0 The setting can avoid the problem of inaccurate data caused by too low sampling rate and too long sensor response time. By weighting the influence of the equipment status abnormality evaluation index, environmental interference value, sampling rate and sensor response time, it reflects their relative importance in the evaluation index. The weights of different factors can be adjusted according to different needs, making the formula very adaptable. It is not difficult to see that when the equipment status abnormality evaluation index is smaller or the environmental interference value is smaller or the sampling rate is larger or the sensor response time is smaller, the data accuracy evaluation value is larger. By evaluating the data accuracy evaluation value of each power grid node, the accuracy of the power grid monitoring system can be improved, so that the monitoring system can more accurately reflect the actual operation status of the power grid, timely discover data anomalies, and quickly take corresponding countermeasures to improve the safety and stability of power grid operation, which helps to understand the actual load and energy consumption of power grid nodes, thereby providing a basis for the rational allocation of power grid resources, and can discover problems and deficiencies in the power grid structure, and take corresponding optimization measures to further improve the efficiency and quality of power grid operation and maintenance management.

[0073] In a specific embodiment, the value range of the data accuracy assessment influencing factor corresponding to the device state abnormality assessment index, environmental interference value, sampling rate and sensor response time is between 0 and 1, which represents the numerical value of the degree of influence of the device state abnormality assessment index, environmental interference value, sampling rate and sensor response time on the data accuracy assessment value. Each data accuracy assessment influencing factor can be obtained from the distributed power grid database. By adjusting the value of the influencing factor, the degree of influence of different factors on the final data accuracy assessment value can be flexibly adjusted. The corresponding relationship can be a pre-set mapping relationship. For example, the device state abnormality assessment index, environmental interference value, sampling rate and sensor response time and the weight factors corresponding to the device state abnormality assessment index, environmental interference value, sampling rate and sensor response time preset in the distributed power grid database form a mapping set, and the real-time device state abnormality assessment index, environmental interference value, sampling rate and sensor response time are brought into the mapping set to obtain the weight factors corresponding to the device state abnormality assessment index, environmental interference value, sampling rate and sensor response time. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0074] Furthermore, each normal monitoring grid node is screened and feedback is performed based on the data accuracy evaluation value of each grid node. The specific screening process is: extracting the data accuracy evaluation threshold from the distributed power grid database, adding the data accuracy evaluation threshold to the data accuracy evaluation threshold correction value of each grid node to obtain the updated data accuracy evaluation threshold of each grid node, and comparing the data accuracy evaluation value of each grid node with the updated data accuracy evaluation threshold of each grid node respectively; if the data accuracy evaluation value of a grid node is greater than or equal to the updated data accuracy evaluation threshold of the grid node, the grid node is marked as a normal monitoring grid node; if the data accuracy evaluation value of a grid node is less than the updated data accuracy evaluation threshold of the grid node, feedback correction is performed.

[0075] In a specific embodiment, the grid frequency refers to the number of times the AC voltage changes in a unit time. The monitoring of the grid frequency helps to understand the balance of active power in the grid and promptly discover problems of insufficient or excessive power, thereby adjusting the generator output or load distribution to maintain a stable grid frequency. It can be monitored in real time through a grid monitoring tool; the grid load refers to the power consumed by the electrical equipment connected to the power system. The monitoring of the grid load helps to understand the power demand of each node, avoid overload or low load operation through reasonable load distribution and scheduling, and improve the operating efficiency of the grid. It can be measured by a grid meter.

[0076] Specifically, based on the equipment status abnormality assessment index and grid status data of each normal monitored grid node, a comprehensive analysis is performed to obtain the health status assessment value of each normal monitored grid node. The specific analysis process is: the grid status data includes the grid frequency and grid load at each time node within the monitoring period.

[0077] The reference standard grid frequency and the allowable deviation grid frequency are extracted from the distributed power grid database, and the health status assessment value of each normal monitoring grid node is obtained by comprehensive analysis based on the equipment status abnormality assessment index of each normal monitoring grid node.

[0078] Furthermore, the health status evaluation value of each normal monitoring grid node is expressed as follows:

[0079]

[0080] Among them, Hs c represents the health status assessment value of the cth normally monitored power grid node, Ma' c represents the abnormal evaluation index of the equipment status of the cth normally monitored power grid node, w cb represents the grid frequency of the cth normally monitored grid node at the bth time node, w 0 represents the reference standard grid frequency, Δw represents the allowable deviation grid frequency, h cb represents the grid load of the cth normally monitored grid node at the bth time node, θ 1 Indicates the health status assessment impact factor corresponding to the set equipment status abnormality assessment index, θ 2 Indicates the health status assessment impact factor corresponding to the set grid frequency, θ 3 represents the health status assessment influencing factor corresponding to the set power grid load, c represents the number of each normal monitoring power grid node, c = 1, 2, 3, ..., q, q represents the total number of normal monitoring power grid nodes, b represents the number of each time node, b = 1, 2, 3, ..., r, r represents the total number of time nodes.

[0081] like Figure 2 As shown, in a specific embodiment, θ 1 =0.4,θ 2 =0.3,θ 3 =0.4, b=r=1, w cb =48Hz, w 0 =50Hz, Δw=3Hz. When h cb = 1 degree, the functional relationship between the health status evaluation value of each normal monitoring grid node and the abnormal equipment status evaluation index of each normal monitoring grid node is shown in curve a; when h cb=3 degrees, the functional relationship between the health status evaluation value of each normal monitoring grid node and the abnormal equipment status evaluation index of each normal monitoring grid node is shown in curve b; when h cb When =5 degrees, the functional relationship between the health status evaluation value of each normal monitoring grid node and the equipment status abnormal evaluation index of each normal monitoring grid node is shown as curve c.

[0082] The algorithm of this embodiment combines the equipment status abnormality evaluation index, the grid frequency and the grid load, and comprehensively analyzes to obtain the health status evaluation value of each normal monitoring grid node. When the equipment fails or is abnormal, its evaluation index will change, and this change may have an impact on the grid frequency. For example, when a large generator or transformer in the grid fails, it may cause the active power output of the grid to be insufficient or excessive, thereby causing fluctuations in the grid frequency; changes in the grid load will also affect the equipment status abnormality evaluation index. When the load increases, the operating pressure and load of the grid equipment will also increase accordingly, which may increase the probability of equipment failure, thereby increasing the equipment status abnormality evaluation index; there is also a close relationship between the grid frequency and the grid load. When the grid load increases, if the active power output of the generator cannot keep up in time, it will cause the grid frequency to drop. Conversely, when the grid load decreases, if the active power output of the generator is not reduced in time, it will cause the grid frequency to rise. Comprehensive analysis can obtain a more comprehensive health status evaluation value.

[0083] It should be explained that three key factors, namely, the equipment state abnormality evaluation index, the grid frequency and the grid load, are considered in this embodiment, which is helpful to optimize the output and load distribution of the generator, reduce unnecessary energy waste and loss, and can intelligently dispatch the grid, optimize energy configuration, improve energy utilization efficiency, reduce the peak-to-valley difference of the grid, and increase the load rate of the grid, which is helpful to formulate a more scientific and reasonable grid dispatch and operation strategy. It can also quickly understand the operation status of the grid, formulate effective emergency response measures, and quickly restore the normal operation of the grid, which helps to enhance the resilience of the grid so that it can better maintain stability, reliability and safety in the face of emergencies. By standardizing the grid frequency and grid load, ensuring that they are compared at the same magnitude, the fairness and comparability of the evaluation are improved. By weighting the impact of the equipment state abnormality evaluation index, grid frequency and grid load, it reflects their relative importance in the evaluation index. The weights of different factors can be adjusted according to different needs, so that the formula has good adaptability. It is not difficult to see that the smaller the equipment state abnormality evaluation index or the grid frequency deviation or the grid load deviation, the greater the health status evaluation value. By evaluating the health status assessment value of each normally monitored power grid node, health problems of the power grid node can be discovered and handled in a timely manner, which helps prevent power outages or safety accidents caused by equipment failures, allocates power resources more reasonably, avoids resource waste and excessive consumption, improves the operating efficiency of the power grid, helps provide better power output and stability, thereby improving the quality of power supply, meeting users' needs for power stability and reliability, and formulating more scientific and reasonable power grid dispatching and operation strategies, further improving the response speed and emergency capabilities of the power grid.

[0084] In a specific embodiment, the value range of the health status assessment influencing factor corresponding to the equipment state abnormality assessment index, power grid frequency and power grid load is between 0 and 1, which represents the numerical value of the influence degree of the equipment state abnormality assessment index, power grid frequency and power grid load on the health status assessment value. Each data accuracy assessment influencing factor can be obtained from the distributed power grid database. By adjusting the value of the influencing factor, the influence degree of different factors on the final health status assessment value can be flexibly adjusted. The corresponding relationship can be a pre-set mapping relationship. For example, the equipment state abnormality assessment index, power grid frequency and power grid load and the weight factors corresponding to the equipment state abnormality assessment index, power grid frequency and power grid load preset in the distributed power grid database form a mapping set, and the real-time equipment state abnormality assessment index, power grid frequency and power grid load are brought into the mapping set to obtain the weight factors corresponding to the equipment state abnormality assessment index, power grid frequency and power grid load. The mapping relationship can be a one-to-one correspondence or a many-to-one relationship.

[0085] Specifically, evaluation and feedback are performed on each normal monitoring grid node according to the health status evaluation value of each normal monitoring grid node. The specific evaluation process is: extract the health status evaluation threshold from the distributed power grid database, compare the health status evaluation value of each normal monitoring grid node with the health status evaluation threshold, if the health status evaluation value of a normal monitoring grid node is greater than or equal to the health status evaluation threshold, then the normal monitoring grid node is evaluated as healthy, if the health status evaluation value of a normal monitoring grid node is less than the health status evaluation threshold, then the normal monitoring grid node is evaluated as unhealthy and feedback correction is performed, and at the same time, the number of unhealthy grid nodes is counted and feedback is performed.

[0086] Furthermore, feedback correction is performed, and the specific process is: subtract the health status assessment threshold from the health status assessment value of each unhealthy normal monitoring power grid node to obtain the health status assessment difference of each unhealthy normal monitoring power grid node, extract the health status assessment difference first threshold and the health status assessment difference second threshold from the distributed power grid database, compare the health status assessment difference of each unhealthy normal monitoring power grid node with the health status assessment difference threshold, if the health status assessment difference of an unhealthy normal monitoring power grid node is greater than or equal to the health status assessment difference first threshold, immediately notify the relevant staff to conduct on-site inspection of the unhealthy normal monitoring power grid node, if the health status assessment difference of an unhealthy normal monitoring power grid node is greater than or equal to the health status assessment difference first threshold, then immediately notify the relevant staff to conduct on-site inspection of the unhealthy normal monitoring power grid node If the difference is less than the first threshold of the health status assessment difference and greater than the second threshold of the health status assessment difference, the maintenance frequency of the node equipment is increased, that is, the health status assessment difference of the unhealthy and normal monitoring power grid node is input into the distributed power grid database to match the corresponding equipment maintenance frequency, and the equipment of the unhealthy and normal monitoring power grid node is maintained according to the equipment maintenance frequency. If the health status assessment difference of an unhealthy and normal monitoring power grid node is less than the second threshold of the health status assessment difference, the monitoring frequency of the node is increased, that is, the health status assessment difference of the unhealthy and normal monitoring power grid node is input into the distributed power grid database to match the corresponding monitoring frequency, and the unhealthy and normal monitoring power grid node is monitored according to the monitoring frequency.

[0087] Specifically, the number of unhealthy grid nodes is counted and feedback is provided. The specific process is: extracting the unhealthy grid node threshold from the distributed power grid database, comparing the number of unhealthy grid nodes with the unhealthy grid node threshold; if the number of unhealthy grid nodes is greater than or equal to the unhealthy grid node threshold, the unhealthy nodes are isolated from the power grid as soon as possible to prevent their faults from further spreading and affecting the stability of the entire power grid; if the number of unhealthy grid nodes is less than the unhealthy grid node threshold, the relevant staff are notified.

[0088] The distributed power grid database is used to store distributed power grid related data, including: reference standard mechanical stress, allowable deviation mechanical stress, reference standard output power, allowable deviation output power, critical insulation resistance, critical sampling rate, critical sensor response time, reference standard temperature, allowable deviation temperature, reference standard wind speed, allowable deviation wind speed, critical vibration frequency, critical dust degree, data accuracy assessment threshold correction value, data accuracy assessment threshold, health status assessment influencing factor corresponding to the set equipment status abnormality assessment index, health status assessment influencing factor corresponding to the set power grid frequency, health status assessment influencing factor corresponding to the set power grid load, health status assessment threshold and health status assessment difference threshold and other indicators.

[0089] The above contents are merely examples and explanations of the structure of the present invention. The technicians in this technical field may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A distributed power grid node health monitoring and prediction method, characterized in that: include: Obtain distributed power grid nodes, mark them as each power grid node, and obtain health monitoring data of each power grid node, wherein the health monitoring data includes power grid status data, data collection environment data, and device status data; The device status data is processed to obtain the device status anomaly assessment index of each power grid node. According to the device status anomaly assessment index of each power grid node and the data collection environment data, a comprehensive analysis is performed to obtain the data accuracy assessment value of each power grid node. According to the data accuracy evaluation value of each power grid node, each normal monitoring power grid node is screened and feedback is provided; According to the abnormal equipment status assessment index and grid status data of each normal monitoring grid node, a comprehensive analysis is performed to obtain the health status assessment value of each normal monitoring grid node, and evaluation feedback is performed on each normal monitoring grid node based on the health status assessment value of each normal monitoring grid node.

2. The distributed power grid node health monitoring and prediction method according to claim 1 is characterized in that: The device status data is processed to obtain the device status abnormality evaluation index of each power grid node, and the specific processing process is as follows: The device status data includes mechanical stress, output power and insulation resistance of each device; The reference standard mechanical stress, allowable deviation mechanical stress, reference standard output power, allowable deviation output power and critical insulation resistance are extracted from the distributed power grid database, and the equipment status abnormality assessment index of each power grid node is obtained through comprehensive analysis.

3. The distributed power grid node health monitoring and prediction method according to claim 1, characterized in that: According to the equipment status abnormality evaluation index of each power grid node and the data collection environment data, a comprehensive analysis is performed to obtain the data accuracy evaluation value of each power grid node. The specific analysis process is as follows: The data collection environment data includes working environment data and data collection parameters; Obtain the environmental interference value of each power grid node according to the working environment data processing; The data acquisition parameters include sampling rate and sensor response time; The critical sampling rate and critical sensor response time are extracted from the distributed power grid database, and the data accuracy evaluation value of each power grid node is obtained through comprehensive analysis based on the equipment status abnormality evaluation index and environmental interference value of each power grid node. The data accuracy evaluation value of each power grid node is used to quantify the data accuracy of each power grid node.

4. The distributed power grid node health monitoring and prediction method according to claim 3 is characterized by: The environmental interference value of each power grid node is obtained by processing the working environment data. The specific processing process is as follows: The working environment data includes the temperature, wind speed, electromagnetic interference value, communication noise intensity and dust level of each environmental monitoring point; The reference standard temperature, allowable deviation temperature, reference standard wind speed, allowable deviation wind speed, critical electromagnetic interference value, critical communication noise intensity and critical dust degree are extracted from the distributed power grid database, and the environmental interference value of each power grid node is obtained by comprehensive analysis. The data accuracy assessment threshold correction value is obtained according to the matching of the environmental interference value of each power grid node.

5. The distributed power grid node health monitoring and prediction method according to claim 4, characterized in that: The data accuracy assessment threshold correction value is obtained by matching the environmental interference value of each power grid node. The specific matching process is: The environmental interference value of each power grid node is matched with the data accuracy assessment threshold correction value corresponding to each environmental interference value interval preset in the distributed power grid database to obtain the data accuracy assessment threshold correction value of each power grid node.

6. The distributed power grid node health monitoring and prediction method according to claim 5, characterized in that: The normal monitoring grid nodes are screened and fed back according to the data accuracy evaluation value of each grid node. The specific screening process is as follows: A data accuracy assessment threshold is extracted from the distributed power grid database, and the data accuracy assessment threshold is added to the data accuracy assessment threshold correction value of each power grid node to obtain the updated data accuracy assessment threshold of each power grid node. The data accuracy assessment value of each power grid node is compared with the updated data accuracy assessment threshold of each power grid node respectively. If the data accuracy assessment value of a power grid node is greater than or equal to the updated data accuracy assessment threshold of the power grid node, the power grid node is marked as a normal monitoring power grid node. If the data accuracy assessment value of a power grid node is less than the updated data accuracy assessment threshold of the power grid node, feedback correction is performed.

7. The distributed power grid node health monitoring and prediction method according to claim 2, characterized in that: According to the abnormal equipment status evaluation index and grid status data of each normally monitored grid node, a comprehensive analysis is performed to obtain the health status evaluation value of each normally monitored grid node. The specific analysis process is as follows: The grid status data includes grid frequency and grid load at each time point in the monitoring period; The reference standard grid frequency and the allowable deviation grid frequency are extracted from the distributed power grid database, and the health status assessment value of each normal monitoring grid node is obtained by comprehensive analysis based on the equipment status abnormality assessment index of each normal monitoring grid node.

8. The distributed power grid node health monitoring and prediction method according to claim 7, characterized in that: The evaluation feedback is performed on each normal monitoring grid node according to the health status evaluation value of each normal monitoring grid node. The specific evaluation process is as follows: The health status assessment threshold is extracted from the distributed power grid database, and the health status assessment value of each normal monitoring power grid node is compared with the health status assessment threshold. If the health status assessment value of a normal monitoring power grid node is greater than or equal to the health status assessment threshold, the normal monitoring power grid node is assessed as healthy. If the health status assessment value of a normal monitoring power grid node is less than the health status assessment threshold, the normal monitoring power grid node is assessed as unhealthy and feedback correction is performed.

9. The distributed power grid node health monitoring and prediction method according to claim 8, characterized in that: The feedback correction is specifically performed as follows: The health status assessment threshold is subtracted from the health status assessment value of each unhealthy and normal monitoring power grid node to obtain the health status assessment difference of each unhealthy and normal monitoring power grid node, the health status assessment difference first threshold and the health status assessment difference second threshold are extracted from the distributed power grid database, and the health status assessment difference of each unhealthy and normal monitoring power grid node is compared with the health status assessment difference threshold. If the health status assessment difference of an unhealthy and normal monitoring power grid node is greater than or equal to the first health status assessment difference threshold, the relevant staff is immediately notified to conduct an on-site inspection of the unhealthy and normal monitoring power grid node. If the health status assessment difference of an unhealthy and normal monitoring power grid node is less than the first health status assessment difference threshold and greater than the second health status assessment difference threshold, the maintenance frequency of the node equipment is increased. If the health status assessment difference of an unhealthy and normal monitoring power grid node is less than the second health status assessment difference threshold, the monitoring frequency of the node is increased.

10. The distributed power grid node health monitoring and prediction method according to claim 7, characterized in that: The specific numerical expression of the health status evaluation value of each normal monitoring grid node is: Among them, Hs c represents the health status assessment value of the cth normally monitored power grid node, Ma' c represents the abnormal equipment status evaluation index of the cth normally monitored power grid node, w cb represents the grid frequency of the cth normal monitoring grid node at the bth time node, w0 represents the reference standard grid frequency, Δw represents the allowable deviation grid frequency, h cb represents the grid load of the bth time node of the cth normal monitoring grid node, θ1 represents the health status assessment impact factor corresponding to the set equipment status abnormal assessment index, θ2 represents the health status assessment impact factor corresponding to the set grid frequency, θ3 represents the health status assessment impact factor corresponding to the set grid load, c represents the number of each normal monitoring grid node, c = 1, 2, 3, ..., q, q represents the total number of normal monitoring grid nodes, b represents the number of each time node, b = 1, 2, 3, ..., r, r represents the total number of time nodes.

Images