Intelligent power monitoring and management method and system for electrical cabinets

Abstract

The present invention relates to the field of power monitoring technology, and more particularly to a method and system for intelligent power monitoring and management of electrical cabinets. The method comprises: obtaining status data points at each moment during the operation of the electrical cabinet, the status data points including temperature data and residual current data; detecting the status data points using an isolation forest algorithm to obtain anomaly scores, and correcting the anomaly scores to obtain optimal anomaly scores for use in monitoring the operating status of the electrical cabinet. By correcting the initial anomaly scores, the present invention improves the accuracy of the isolation forest monitoring results.

Description

Technical Field

[0001] The present invention relates to the technical field of power monitoring, and in particular to an intelligent power monitoring and management method and system for an electrical cabinet. Background Art

[0002] An electrical cabinet is a cabinet used to store and protect electrical equipment. Typically constructed of metal or non-metallic materials, it houses various electrical components such as switches, relays, contactors, circuit breakers, transformers, and control modules. Its primary function is to centrally manage, protect, and control electrical equipment. Monitoring and managing electrical cabinets can promptly identify and flag potential issues within the cabinet. Timely anomaly detection enables rapid response to issues before they occur, minimizing potential damage to equipment.

[0003] The Chinese patent application document with publication number CN119010364A discloses a weak current control monitoring system and method based on the Internet of Things. The method collects monitoring data through monitoring nodes deployed on weak current equipment, and generates a tracking certificate for the monitoring data of the same weak current equipment at the same time. The cloud analysis platform verifies the legitimacy of the received data through the tracking certificate to ensure that the data is not lost during the transmission process, thereby ensuring the authenticity and integrity of the monitoring data during the transmission process. After that, the system uses the intelligent monitoring model of weak current equipment to build an isolation forest, randomly selects temperature, current, and voltage features for segmentation, and continuously divides the data points until each data point is isolated, automatically outputs abnormal points, and then the system identifies potential faults of the equipment, intelligently controls and adjusts the working status of the weak current equipment, and ensures the normal operation of the weak current equipment.

[0004] When conducting power monitoring and management on electrical cabinets, the isolation forest algorithm can be used to monitor the parameters of the electrical cabinets to understand the operating status of the electrical cabinets. In the traditional isolation forest algorithm, each isolated tree has the same weight, but in fact, different isolated trees have different detection effects on abnormal data. Therefore, the accuracy of the anomaly score obtained by the traditional isolation forest algorithm is low, and it is impossible to achieve effective monitoring and management of the electrical cabinets. Summary of the Invention

[0005] In order to solve the problem that the weight of each isolated tree in the traditional isolation forest algorithm is the same, resulting in low accuracy of monitoring results, the present invention provides an intelligent power monitoring and management method and system for electrical cabinets.

[0006] In a first aspect, the present invention provides an intelligent power monitoring and management method for an electrical cabinet, which adopts the following technical solutions:

[0007] Obtain status data points at each moment during the operation of the electrical cabinet, including temperature data and residual current data; use the isolation forest algorithm to detect the status data points to obtain anomaly scores, and then correct the anomaly scores to obtain the optimal anomaly score for monitoring the operating status of the electrical cabinet;

[0008] Among them, the method for correcting the anomaly score to obtain the best anomaly score is:

[0009] Calculate the electrical environment anomaly index at each moment. The electrical environment anomaly index represents the correlation between temperature data and residual current data. Calculate the anomaly index of each leaf node in the isolation tree. The anomaly index of a leaf node is positively correlated with the mean of the electrical environment anomaly index at the corresponding moment in the leaf node. Obtain the isolated anomaly factor of the isolation tree by weighted summation of the anomaly indices of leaf nodes at each layer. Normalize the isolated anomaly factor and use the normalized isolated anomaly factor to weighted sum the initial anomaly score to obtain the optimal anomaly score.

[0010] The abnormality degree of leaf nodes in the isolation tree is analyzed based on the electrical environment anomaly index, and an isolated anomaly factor is constructed to evaluate the isolation effect of the isolation tree on abnormal data. Based on the isolated anomaly factor, the calculation method of the anomaly score in the isolation forest is improved, so that the isolation tree with a good isolation effect on abnormal data has a larger isolated anomaly factor, and the final calculated anomaly score can more accurately reflect the abnormal state of the electrical cabinet, thereby improving the accuracy of the isolation forest monitoring results.

[0011] Preferably, the method also includes: using multiple state data points to construct a neighbor operating state sequence at the corresponding moment, the neighbor operating state sequence includes a neighbor temperature data sequence and a neighbor residual current data sequence, inputting the neighbor operating state sequence into the Wilcoxon signed rank test algorithm, assuming that the test condition is that the neighbor operating state sequence has an upward trend, and obtaining the p value that the neighbor operating state sequence has an upward trend.

[0012] The p-value reflects the reliability of the upward trend of the neighboring residual current data series and the neighboring temperature data series.

[0013] Preferably, the method further comprises: performing first-order difference processing on the neighboring operating state sequence to obtain a difference sequence, and calculating the local rising intensity index of the neighboring operating state sequence at each moment, wherein the expression is:

[0014]

[0015] Where, Represents the local rising intensity index of the neighboring operating state sequence at time t, It represents the p-value of the neighboring running state sequence at time t after the Wilcoxon signed rank test, and They represent the number of positive and negative elements in the differential sequence corresponding to the neighboring running state sequence at time t, It represents the ath positive value in the differential sequence corresponding to the neighboring running state sequence at time t, Indicates the bth negative value in the difference sequence corresponding to the neighboring operating state sequence at time t.

[0016] The local rising intensity index can reflect the changing trend of the neighboring operating state sequence and provide a theoretical basis for analyzing the electrical environment anomaly index.

[0017] Preferably, the method also includes: obtaining the maximum points of the neighboring temperature data sequence and the neighboring residual current data sequence, and constructing the neighboring residual current maximum sequence and the neighboring temperature maximum sequence, and inputting the neighboring residual current maximum sequence and the neighboring temperature maximum sequence into the DTW algorithm to obtain two maximum sequences.

[0018] Preferably, the expression of the electrical environment abnormality index is:

[0019]

[0020] Where, Indicates the electrical environment abnormality index of the state data point at time t, and They represent the local rising intensity index of the neighboring residual current series and the neighboring temperature series at time t, It represents the length of the maximum value sequence after aligning the nearest neighbor residual current maximum value sequence and the nearest neighbor temperature maximum value sequence at time t using the DTW algorithm. It represents the Manhattan distance of the c-th maximum point in the two sequences after alignment.

[0021] The electrical environment anomaly index can reflect the difference between the neighboring residual current series and the neighboring temperature series, and further reflect the degree of abnormality of the electrical environment.

[0022] Preferably, the abnormal index expression of the leaf node is:

[0023]

[0024] Where, represents the abnormality index of the leaf node in the hth layer of the isolation tree, Represents the number of state data points in the leaf nodes in the hth layer of the isolation tree, Represents the electrical environment anomaly index of the mth state data point in the hth layer in the isolation tree, Indicates the maximum value of the electrical environment anomaly index of all status data points in the isolation tree.

[0025] The anomaly index of the leaf node is obtained by calculating the state data points, which improves the accuracy of the calculation results and provides a theoretical basis for calculating the isolated anomaly factor.

[0026] Preferably, the isolated anomaly factor expression of the isolated tree is:

[0027]

[0028] Where, represents the isolated anomaly factor of the ith isolated tree in the isolation forest, represents the maximum depth of the ith isolated tree, h represents the h-th leaf node in the isolated tree, Represents the electrical environment anomaly index of the h-th leaf node of the i-th isolated tree.

[0029] Preferably, the expression of the best anomaly score is:

[0030]

[0031] Where, represents the best abnormal score of the electrical cabinet operating status at time v, N represents the number of isolated trees set in the isolation forest algorithm, represents the isolated anomaly factor of the ith isolated tree in the isolation forest algorithm, It represents the maximum value of the isolated anomaly factor of all isolated trees in the isolation forest algorithm. Represents the initial anomaly score of the electrical cabinet operating status data at time v in the i-th isolated tree.

[0032] The optimal anomaly score is obtained by correcting the initial anomaly score. Compared with the fixed weight of the traditional isolation tree, the accuracy of the anomaly score is improved and the operating status of the electrical cabinet can be accurately reflected.

[0033] Preferably, the method further comprises the step of filtering and denoising the state data points.

[0034] In a second aspect, the present invention provides an intelligent power monitoring and management system for electrical cabinets, which adopts the following technical solutions:

[0035] An intelligent power monitoring and management system for an electrical cabinet comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent power monitoring and management method for an electrical cabinet is implemented.

[0036] The above-mentioned intelligent power monitoring and management method for an electrical cabinet is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a system based on the memory and the processor for easy use.

[0037] The present invention has the following technical effects:

[0038] By analyzing the rising trend strength of the residual current data and temperature data of the circuit during the operation of the electrical cabinet, a local rising intensity index is constructed to evaluate the abnormal impact of the residual current and temperature in the circuit on the operating status of the electrical cabinet respectively; since the magnitude of the residual current in the circuit will cause corresponding changes in temperature, the difference between the local rising intensity index of the residual current and temperature and the similarity between the peak changes of the residual current and temperature in the local time are analyzed to construct an electrical environment anomaly index to evaluate the effectiveness of the electrical cabinet cooling system; based on the electrical environment anomaly index, the anomaly degree of the leaf nodes in the isolated tree is analyzed, and an isolated anomaly factor is constructed to evaluate the isolation effect of the isolated tree on abnormal data; based on the isolated anomaly factor, the calculation method of the anomaly score in the isolated forest is improved, so that the isolated tree with a good isolation effect on abnormal data has a larger isolated anomaly factor, so that the finally calculated anomaly score can more accurately reflect the abnormal state of the electrical cabinet, and different measures are taken according to different anomaly degrees to realize intelligent monitoring and management of the electrical cabinet power. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 The present invention is a flow chart of an intelligent power monitoring and management method for an electrical cabinet. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0041] The embodiment of the present invention discloses an intelligent power monitoring and management method for an electrical cabinet, referring to Figure 1 , including the following steps, as follows:

[0042] S1: Obtain the status data points at each moment during the operation of the electrical cabinet.

[0043] The status data points include temperature data and residual current data. During the electrical operation process, the temperature data of one point on the surface of the electrical cabinet and the residual current data of the electrical cabinet cable are collected by temperature sensors and current transformers respectively. The collection interval is set to 1 second. The collected temperature data and residual current data are denoised using a mean filter denoising algorithm, and the denoised data are normalized using a standard deviation normalization method. The mean filter denoising algorithm and the standard deviation normalization method are well-known technologies and will not be described in detail here. The residual current data is leakage current. In the normal operating circuit of the electrical cabinet, the current vector sum between the phase line and the neutral line is 0. If the current vector sum is not 0, it indicates that there is leakage in the circuit, generating residual current. In other embodiments, the status data points can also be power data and temperature data.

[0044] S2: Calculate the local rising intensity index of the neighboring running state sequence at each moment.

[0045] The state data points at the n moments before time t are used to construct the neighboring operating state sequence of the corresponding moment. The neighboring operating state sequence includes the neighboring temperature data sequence and the neighboring residual current data sequence. For example, the temperature data at the 30 moments before time t are used to construct the neighboring temperature data sequence, and the residual current data at the 30 moments before time t are used to construct the neighboring residual current data sequence.

[0046] The neighboring operating state sequence is input into the Wilcoxon signed-rank test algorithm. Assuming the test condition is that the neighboring operating state sequence has an upward trend, a p-value is obtained to indicate that the neighboring operating state sequence has an upward trend. It can be understood that a p-value is obtained by inputting the neighboring temperature data sequence into the Wilcoxon signed-rank test algorithm, and a p-value is obtained by inputting the neighboring residual current data sequence into the Wilcoxon signed-rank test algorithm.

[0047] Perform first-order difference processing on the neighboring operating state sequence to obtain the difference sequence, and calculate the local rising intensity index of the neighboring operating state sequence at each moment, where the expression is:

[0048]

[0049] Where, Represents the local rising intensity index of the neighboring operating state sequence at time t, It represents the p-value of the neighboring running state sequence at time t after the Wilcoxon signed rank test, and They represent the number of positive and negative elements in the differential sequence corresponding to the neighboring running state sequence at time t, It represents the ath positive value in the differential sequence corresponding to the neighboring running state sequence at time t, It represents the bth negative value in the difference sequence corresponding to the neighboring running state sequence at time t. The 1 in the denominator represents the hyperparameter to avoid the phenomenon of the denominator being 0.

[0050] It can be understood that the differential sequence includes a temperature data differential sequence and a residual current data differential sequence, and a neighboring temperature data sequence corresponds to a local rising intensity index, and a neighboring residual current data sequence corresponds to a local rising intensity index.

[0051] During the operation of the electrical cabinet, the magnitude of the residual current indicates the severity of the leakage. Generally, all electrical systems have residual current. The trace residual current caused by non-electrical faults has almost no harm to the electrical system and can be considered a normal phenomenon. However, as the residual current increases, the temperature of the line will rise. When the temperature reaches a certain level, it may cause the cable to burn, thereby causing electrical accidents.

[0052] Based on the above analysis, by constructing the local rising intensity index to reflect the trend intensity of the residual current data and temperature data, in the neighboring residual current sequence at time t, if the residual current in the electrical cabinet has an upward trend, that is, When the rise is greater than the fall, When it is larger, it indicates that the electrical cabinet is in an abnormal electrical working state, so the calculated local rising intensity index is larger.

[0053] S3: Calculate the electrical environment anomaly index at each moment, where the electrical environment anomaly index represents the correlation between the temperature data and the residual current data.

[0054] When residual current flows in an electrical cabinet, Joule's law indicates that a certain amount of heating occurs in the circuit. The greater the residual current, the greater the heat generated, which in turn causes a temperature rise. Therefore, when the residual current is high, the corresponding temperature is higher. If the temperature in the electrical cabinet is not controlled, a flashover may occur within a short period of time, causing significant damage to the electrical cabinet and surrounding facilities. Therefore, an electrical environment anomaly index is constructed based on the local rise intensity index to reflect the degree of environmental anomalies during electrical cabinet operation.

[0055] The maximum points of the neighboring temperature data sequence and the neighboring residual current data sequence are obtained, and the neighboring residual current maximum sequence and the neighboring temperature maximum sequence are constructed. The neighboring residual current maximum sequence and the neighboring temperature maximum sequence are input into the DTW algorithm to obtain two maximum sequences.

[0056] The expression of the electrical environment abnormality index is:

[0057]

[0058] Where, Indicates the electrical environment abnormality index of the state data point at time t, and They represent the local rising intensity index of the neighboring residual current series and the neighboring temperature series at time t, Indicates the length of the maximum value sequence after aligning the neighboring residual current maximum value sequence and the neighboring temperature maximum value sequence at time t using the DTW algorithm (Dynamic Time Warping). It represents the Manhattan distance of the cth maximum point in the two sequences after alignment. The Manhattan distance can also be understood as the absolute value of the difference between the two maximum points.

[0059] If the difference in the local rising intensity index between the neighboring residual current sequence and the neighboring temperature sequence at time t is smaller, that is, The smaller it is, the smaller the trend strength of the residual current data and the temperature data. At the same time, if the neighboring residual current maximum value sequence is aligned with the neighboring temperature maximum value sequence, the smaller the Manhattan distance between the two maximum points at the same position is, that is, The smaller the value, the greater the change in residual current can cause a corresponding change in temperature. That is, the cooling system of the electrical cabinet is poor and the temperature cannot be well controlled. The operating environment of the electrical cabinet is poor and related power accidents are prone to occur. Therefore, the larger the calculated electrical environment abnormality index is.

[0060] S4: Calculate the anomaly index of each leaf node in the isolation tree. The anomaly index of the leaf node is positively correlated with the mean value of the electrical environment anomaly index at the corresponding moment in the leaf node.

[0061] Construct an isolation forest model, where the number of isolated trees is 100 and the depth of the isolation tree is 10.

[0062] The abnormal index expression of the leaf node is:

[0063]

[0064] Where, represents the abnormality index of the leaf node in the hth layer of the isolation tree, Represents the number of state data points in the leaf nodes in the hth layer of the isolation tree, Represents the electrical environment anomaly index of the mth state data point in the hth layer in the isolation tree, Indicates the maximum value of the electrical environment anomaly index of all state data points in the isolated tree, It reflects the relative abnormal operation degree of the electrical cabinet at the mth moment in the isolated tree.

[0065] S5: The weighted sum of the anomaly indexes of the leaf nodes at each layer is used to obtain the isolated anomaly factor of the isolated tree.

[0066] The expression of the isolated outlier factor of the isolated tree is:

[0067]

[0068] Where, represents the isolated anomaly factor of the ith isolated tree in the isolation forest, represents the maximum depth of the ith isolated tree, h represents the h-th leaf node in the isolated tree, Represents the electrical environment anomaly index of the h-th leaf node of the i-th isolated tree.

[0069] In the isolation forest algorithm, if the isolation tree is better at identifying abnormal data, the data with greater abnormality will be identified earlier. That is, when h is smaller, the abnormality of the h-layer leaf node should be greater. Therefore, the electrical environment anomaly index of the leaf node with a smaller depth of the isolation tree is given a greater weight.

[0070] Therefore, if h is small, the abnormality of the leaf node is large, indicating that the isolation tree has a better effect on isolating abnormal data. When the isolation tree is used to identify abnormal data, a larger weight should be given, so the calculated isolation anomaly factor is larger.

[0071] S6: Use the isolation forest algorithm to detect the state data points to obtain anomaly scores, and correct the anomaly scores to obtain the optimal anomaly scores for monitoring the operating status of the electrical cabinet.

[0072] The isolated anomaly factor is normalized, and the normalized isolated anomaly factor is used to weight the initial anomaly score to obtain the optimal anomaly score.

[0073] The expression for the best anomaly score is:

[0074]

[0075] Where, represents the best abnormal score of the electrical cabinet operating status at time v, N represents the number of isolated trees set in the isolation forest algorithm, represents the isolated anomaly factor of the ith isolated tree in the isolation forest algorithm, It represents the maximum value of the isolated anomaly factor of all isolated trees in the isolation forest algorithm. Used to normalize isolated abnormal factors, Represents the initial anomaly score of the electrical cabinet operating status data at time v in the i-th isolated tree.

[0076] If the abnormality degree of the electrical cabinet at time v is higher, it is easier to be isolated in the isolation tree, the corresponding abnormality score is larger, and therefore the calculated optimal abnormality score is higher.

[0077] If the abnormality score of the electrical cabinet operating status at time v obtained after the improved isolation forest algorithm is greater than or equal to the first-level abnormality threshold, it indicates that the electrical cabinet operating status is seriously abnormal at this time, and a first-level warning should be issued in time to prompt relevant staff to deal with it immediately to avoid serious electrical accidents; if the abnormality score obtained is less than the first-level abnormality threshold and greater than or equal to the second-level abnormality threshold, it indicates that the electrical cabinet operating status is relatively abnormal at this time, and a second-level warning should be issued to prompt relevant staff to deal with it in time; if the abnormality score obtained is less than or equal to the second-level abnormality threshold, it indicates that the electrical cabinet operating status is slightly abnormal or normal. In this way, intelligent monitoring and management of the power of the electrical cabinet is achieved. Among them, the first-level abnormality threshold and the second-level abnormality threshold are selected according to the actual situation. For example, the first-level abnormality threshold is 0.8 and the second-level abnormality threshold is 0.5.

[0078] An embodiment of the present invention further discloses an intelligent power monitoring and management system for an electrical cabinet, comprising a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an intelligent power monitoring and management method for an electrical cabinet according to the present invention is implemented.

[0079] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0080] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent power monitoring and management method for an electrical cabinet, characterized in that: Including steps: Obtain status data points at each moment during the operation of the electrical cabinet, including temperature data and residual current data; use the isolation forest algorithm to detect the status data points to obtain anomaly scores, and then correct the anomaly scores to obtain the optimal anomaly score for monitoring the operating status of the electrical cabinet; Among them, the method for correcting the anomaly score to obtain the best anomaly score is: Calculate the electrical environment anomaly index at each moment. The electrical environment anomaly index represents the correlation between temperature data and residual current data. Calculate the anomaly index of each leaf node in the isolation tree. The anomaly index of a leaf node is positively correlated with the mean of the electrical environment anomaly index at the corresponding moment within the leaf node. Obtain the isolated anomaly factor of the isolation tree by weighted summation of the anomaly indices of each leaf node. Normalize the isolated anomaly factor and use the normalized isolated anomaly factor to weight the initial anomaly score to obtain the optimal anomaly score. The expression of the electrical environment abnormality index is: ; Where, Indicates the electrical environment abnormality index of the state data point at time t, and They represent the local rising intensity index of the neighboring residual current series and the neighboring temperature series at time t, It represents the length of the maximum value sequence after aligning the nearest neighbor residual current maximum value sequence and the nearest neighbor temperature maximum value sequence at time t using the DTW algorithm. It represents the Manhattan distance of the c-th maximum point in the two sequences after alignment.

2. The method for intelligent power monitoring and management of an electrical cabinet according to claim 1, characterized in that: The method also includes: using multiple state data points to construct a neighbor operating state sequence at the corresponding moment, the neighbor operating state sequence includes a neighbor temperature data sequence and a neighbor residual current data sequence, inputting the neighbor operating state sequence into a Wilcoxon signed rank test algorithm, assuming that the test condition is that the neighbor operating state sequence has an upward trend, and obtaining a p value that the neighbor operating state sequence has an upward trend.

3. The method for intelligent power monitoring and management of an electrical cabinet according to claim 2, characterized in that: The method further includes: performing first-order difference processing on the neighboring operating state sequence to obtain a difference sequence, and calculating the local rising intensity index of the neighboring operating state sequence at each moment, wherein the expression is: Where, Represents the local rising intensity index of the neighboring operating state sequence at time t, It represents the p-value of the neighboring running state sequence at time t after the Wilcoxon signed rank test, and They represent the number of positive and negative elements in the differential sequence corresponding to the neighboring running state sequence at time t, It represents the ath positive value in the differential sequence corresponding to the neighboring running state sequence at time t, Indicates the bth negative value in the difference sequence corresponding to the neighboring operating state sequence at time t.

4. The method for intelligent power monitoring and management of an electrical cabinet according to claim 3, characterized in that: The method also includes: obtaining the maximum points of the neighboring temperature data sequence and the neighboring residual current data sequence, and constructing the neighboring residual current maximum sequence and the neighboring temperature maximum sequence, and inputting the neighboring residual current maximum sequence and the neighboring temperature maximum sequence into the DTW algorithm to obtain two maximum sequences.

5. The method for intelligent power monitoring and management of an electrical cabinet according to claim 1, characterized in that: The abnormal index expression of the leaf node is: Where, represents the abnormality index of the leaf node in the hth layer of the isolation tree, Represents the number of state data points in the leaf nodes in the hth layer of the isolation tree, Represents the electrical environment anomaly index of the mth state data point in the hth layer in the isolation tree, Indicates the maximum value of the electrical environment anomaly index of all status data points in the isolation tree.

6. The method for intelligent power monitoring and management of an electrical cabinet according to claim 1, characterized in that: The expression of the isolated outlier factor of the isolated tree is: Where, represents the isolated anomaly factor of the ith isolated tree in the isolation forest, represents the maximum depth of the ith isolated tree, h represents the h-th leaf node in the isolated tree, Represents the electrical environment anomaly index of the h-th leaf node of the i-th isolated tree.

7. The method for intelligent power monitoring and management of an electrical cabinet according to claim 6, characterized in that: The expression for the best anomaly score is: Where, represents the best abnormal score of the electrical cabinet operating status at time v, N represents the number of isolated trees set in the isolation forest algorithm, represents the isolated anomaly factor of the ith isolated tree in the isolation forest algorithm, It represents the maximum value of the isolated anomaly factor of all isolated trees in the isolation forest algorithm. Represents the initial anomaly score of the electrical cabinet operating status data at time v in the i-th isolated tree.

8. The method for intelligent power monitoring and management of an electrical cabinet according to claim 1, characterized in that: The method also includes the step of filtering and denoising the state data points.

9. An intelligent power monitoring and management system for electrical cabinets, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent power monitoring and management method for an electrical cabinet according to any one of claims 1 to 8 is implemented.

Images