Intelligent and safe power distribution platform management system based on Internet of Things technology

Abstract

The present invention discloses an intelligent safety power distribution platform management system based on Internet of Things technology, which relates to the technical field of Internet of Things, including: forming the operation time sequence data of edge power equipment, analyzing the operation trend of electrical parameters in the operation time sequence data, and evaluating the state index of each edge power equipment; judging whether the state index of each edge power equipment is in the safety threshold range of the corresponding equipment; predicting the risk probability of abnormal events of edge power equipment based on the operation time sequence data of edge power equipment; analyzing the impact of the risk probability of abnormal events of edge power equipment on the loss of coupled related power equipment when abnormal events occur, and quantifying the maintenance urgency of each edge power equipment; generating the safe power distribution maintenance task of edge power equipment based on the maintenance urgency of each edge power equipment. The advantages of the present invention are: improving the safety of the power distribution system and reducing the losses caused by equipment failures.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to an intelligent safety power distribution platform management system based on Internet of Things technology. Background Art

[0002] The intelligent and safe power distribution platform refers to a comprehensive management system that conducts real-time monitoring, early warning, control and intelligent operation and maintenance management of the equipment and environment in the distribution room.

[0003] The existing intelligent safe power distribution platform mainly monitors the status of electrical equipment for abnormalities. However, the status of electrical equipment is prone to fluctuations over a long period of time, resulting in false alarms on the safe power distribution platform, making it unable to achieve the expected results. Summary of the invention

[0004] In order to solve the above technical problems, an intelligent safety power distribution platform management system based on Internet of Things technology is provided. This technical solution solves the problem that the existing intelligent safety power distribution platform mainly monitors the status of electrical equipment for abnormalities, but the status of electrical equipment is prone to fluctuations over a long period of time, resulting in false alarms on the safety power distribution platform, making the safety power distribution platform unable to achieve the expected effect.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] Intelligent and safe power distribution platform management system based on Internet of Things technology, including:

[0007] Data acquisition module, status analysis module, abnormality judgment module, abnormality analysis module, urgency analysis module, task generation module;

[0008] The data acquisition module is used to collect historical operation data of all edge power devices per unit time based on the Internet of Things sensor, and to form the operation sequence data of the edge power devices;

[0009] The state analysis module is electrically connected to the data acquisition module, and is used to analyze the operating trend of electrical parameters in the operating sequence data based on the operating sequence data of the edge power consumption equipment, and evaluate the state index of each edge power consumption equipment;

[0010] The abnormality judgment module is electrically connected to the state analysis module, and is used to judge whether the state indicator of each edge electrical device is within the safety threshold range of the corresponding device. If so, it is determined that the electrical device has no abnormality; if not, it is determined that the electrical device has an abnormality;

[0011] The abnormality analysis module is electrically connected to the abnormality judgment module. The abnormality analysis module is used to analyze the electrical data fluctuation characteristics of the historical operation data based on the operation sequence data of the edge power consumption equipment if it is determined that the power consumption equipment has an abnormality, and predict the risk probability of abnormal events of the edge power consumption equipment;

[0012] The emergency analysis module is electrically connected to the abnormality analysis module, and is used to analyze the impact of the abnormal event risk probability of edge power equipment on the loss of coupled related power equipment when the abnormal event occurs, and quantify the maintenance urgency of each edge power equipment;

[0013] The task generation module is electrically connected to the urgency analysis module, and is used to generate a safe power distribution maintenance task for edge power equipment based on the maintenance urgency of each edge power equipment.

[0014] Preferably, based on the running time data of the edge power consumption equipment, analyzing the running trend of the electrical parameters in the running time data, and evaluating the status index of each edge power consumption equipment specifically include:

[0015] Determine standardized operating parameters of edge power equipment based on standardized data of edge power equipment;

[0016] Based on the operating sequence data of edge power devices, data cleaning is performed to remove noise and outliers, and normalization is performed;

[0017] Based on the pre-processed running time series data of the edge power consumption equipment, the running time series data is trend decomposed by using the autoregressive integral sliding average to obtain the running characteristic data of each edge power consumption equipment; the electrical characteristic data of the edge power consumption equipment includes: electrical periodicity, electrical seasonality, and electrical trend characteristics;

[0018] Based on the autoregressive AR architecture, an operation trend prediction model for edge power equipment is constructed;

[0019] Substitute the electrical characteristic data of each edge power device into the operation trend prediction model of the edge power device, take the minimization error function of the electrical parameters of the edge power device as the training target, and predict the electrical parameters of each edge power device in the future unit time as the output;

[0020] Linearly mapping the electrical parameters of each edge power device predicted within a future unit time with the standardized operating parameters of the edge power device to obtain a two-dimensional vector of the electrical parameters of each edge power device predicted within a future unit time and a two-dimensional vector of the standardized operating parameters of the edge power device;

[0021] Using the distance index formula, the spatial vector distance between the two-dimensional vector of electrical parameters of each edge power device and the two-dimensional vector of standardized operating parameters of the edge power device in the future unit time is calculated and recorded as the state index of each edge power device;

[0022] The operation trend prediction model of the edge power equipment is specifically as follows:

[0023]

[0024] In the formula, To predict the electrical parameters of the t-th unit time of the i-th edge electrical equipment, is a constant term, is the first The electrical parameters of the unit time lag order, , , are the autoregressive coefficients, is the error term;

[0025] The status indicator of each edge power-consuming device is specifically:

[0026]

[0027] In the formula, is the status indicator of the i-th edge power device, is the two-dimensional vector of electrical parameters of the ith edge electrical equipment, The two-dimensional vector of standardized operating parameters of the ith edge consumer, is the total number of edge power-consuming devices.

[0028] Preferably, if it is determined that the electrical equipment is abnormal, based on the operation sequence data of the edge electrical equipment, the electrical data fluctuation characteristics of the historical operation data are analyzed, and the abnormal event risk probability of the edge electrical equipment is predicted, which specifically includes:

[0029] Obtain big data on known abnormal events of edge power devices in the network;

[0030] Performing difference calculation based on standardized operating parameters of edge power equipment and historical operating data of abnormal edge power equipment to obtain historical deviation operating data of edge power equipment;

[0031] Based on Fourier transform, the operating sequence data of edge power equipment and the electrical periodic characteristics in the big data of known abnormal events of network edge power equipment are decomposed into the superposition state of sine wave and cosine wave, and the operating spectrum diagram of edge power equipment and the abnormal event spectrum diagram of edge power equipment are obtained;

[0032] Based on the historical deviation operation data of the edge power equipment, the abnormal operation spectrum in the operation spectrum diagram of the edge power equipment is marked to obtain the abnormal operation spectrum characteristics of the edge power equipment;

[0033] Calculate the matching degree between the abnormal operation spectrum characteristics of the edge power consumption equipment and the abnormal event spectrum diagram of the edge power consumption equipment, and determine the deviation direction of the abnormal operation event of each edge power consumption equipment;

[0034] Based on the standardized operating parameters of edge power equipment and the historical deviation operating data of edge power equipment, a set of positive and negative operating samples of edge power equipment is constructed;

[0035] Based on Logistic regression, an abnormal risk assessment model for edge power equipment is constructed;

[0036] The abnormal risk assessment model of edge power equipment is trained with the set of positive and negative operation samples of edge power equipment, the electrical characteristic parameters corresponding to the positive and negative operation samples of edge power equipment are used as input, and the abnormal event risk probability of the deviation direction of the abnormal operation of edge power equipment is used as output;

[0037] The calculation is based on the matching degree between the abnormal operation spectrum characteristics of the edge power consumption equipment and the abnormal event spectrum of the edge power consumption equipment as follows:

[0038]

[0039] In the formula, is the matching degree between the abnormal operation spectrum characteristics of the edge power equipment and the abnormal event spectrum of the edge power equipment, is the abnormal operation spectrum feature vector of edge power equipment, is the spectrum vector of abnormal events of edge power consumption equipment;

[0040] The abnormal risk assessment model of the edge electrical equipment is specifically as follows:

[0041]

[0042] In the formula, is the risk probability of abnormal events when the electrical characteristic parameters corresponding to the positive and negative samples of the marginal electrical equipment are input. is the electrical characteristic parameter corresponding to the positive and negative samples of the operation of the i-th edge electrical equipment, , , , Logistic regression coefficients.

[0043] Preferably, analyzing the impact of the risk probability of abnormal events of edge power equipment on the loss of coupled and associated power equipment when the abnormal event occurs, and quantifying the maintenance urgency of each edge power equipment specifically includes:

[0044] Obtaining coupled associated electrical devices of edge electrical devices;

[0045] Based on the historical operation logs and historical maintenance logs of the coupled and associated electrical equipment, the remaining ideal life span of the coupled and associated electrical equipment is quantified;

[0046] According to the risk probability of abnormal events of edge power consumption equipment and the residual value of coupled power consumption equipment, the loss value of coupled power consumption equipment when the abnormal event occurs is calculated;

[0047] According to the risk level corresponding to the loss value of the coupled associated power-consuming equipment when the abnormal event occurs, the abnormal event weight of the abnormal marginal power-consuming equipment is assigned;

[0048] Based on the risk probability of abnormal events of edge power equipment and the abnormal event weight of abnormal edge power equipment, the maintenance urgency of edge power equipment is calculated.

[0049] The calculation of the loss value of the coupled associated electrical equipment when the abnormal event occurs is specifically:

[0050]

[0051] In the formula, is the loss value of the kth coupled associated power device of the ith edge power device, is the remaining ideal life span of the kth coupled electrical equipment, is the survival function of coupled electrical equipment, is the differential variable;

[0052] The maintenance urgency of the computing edge electrical equipment is specifically:

[0053]

[0054] In the formula, It is the maintenance urgency indicator of edge power equipment. is the risk probability of abnormal events of the i-th edge power equipment, is the risk probability weight of the abnormal event of the i-th edge electrical equipment.

[0055] Compared with the prior art, the present invention has the following beneficial effects:

[0056] The present invention proposes an intelligent and safe power distribution platform management solution based on the Internet of Things technology, and constructs an intelligent and safe power distribution platform management system based on the Internet of Things technology. By collecting the operating data of edge power-consuming equipment in real time, analyzing the trend of electrical parameters and evaluating the equipment status, it can identify anomalies in real time and predict the risk probability of abnormal events. Based on the impact of abnormal events on the loss of coupled and associated equipment, it can quantify the urgency of maintenance, thereby accurately generating safe power distribution maintenance tasks. The beneficial effects are: realizing intelligent management of power distribution maintenance, improving the safety of the power distribution system, and reducing losses caused by equipment failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is the framework diagram of the intelligent and safe power distribution platform management system based on the Internet of Things technology;

[0058] Figure 2 A flow chart of a method for evaluating the status indicators of each edge power device;

[0059] Figure 3 A flow chart of a method for predicting the risk probability of abnormal events of marginal electrical equipment;

[0060] Figure 4 Flowchart of a method for quantifying the maintenance urgency of each edge electrical device. DETAILED DESCRIPTION

[0061] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0062] Reference Figure 1 As shown in the figure, the intelligent and safe power distribution platform management system based on the Internet of Things technology includes:

[0063] Data acquisition module, status analysis module, abnormality judgment module, abnormality analysis module, urgency analysis module, task generation module;

[0064] The data acquisition module is used to collect historical operation data of all edge power devices per unit time based on the Internet of Things sensor, and to form the operation sequence data of the edge power devices;

[0065] The state analysis module is electrically connected to the data acquisition module, and is used to analyze the operating trend of electrical parameters in the operating sequence data based on the operating sequence data of the edge power consumption equipment, and evaluate the state index of each edge power consumption equipment;

[0066] The abnormality judgment module is electrically connected to the state analysis module, and is used to judge whether the state indicator of each edge electrical device is within the safety threshold range of the corresponding device. If so, it is determined that the electrical device has no abnormality; if not, it is determined that the electrical device has an abnormality;

[0067] The abnormality analysis module is electrically connected to the abnormality judgment module. The abnormality analysis module is used to analyze the electrical data fluctuation characteristics of the historical operation data based on the operation sequence data of the edge power consumption equipment if it is determined that the power consumption equipment has an abnormality, and predict the risk probability of abnormal events of the edge power consumption equipment;

[0068] The emergency analysis module is electrically connected to the abnormality analysis module, and is used to analyze the impact of the abnormal event risk probability of edge power equipment on the loss of coupled related power equipment when the abnormal event occurs, and quantify the maintenance urgency of each edge power equipment;

[0069] The task generation module is electrically connected to the urgency analysis module, and is used to generate a safe power distribution maintenance task for edge power equipment based on the maintenance urgency of each edge power equipment.

[0070] This solution builds an intelligent and safe power distribution platform management system based on the Internet of Things technology. It collects the operating data of edge power equipment in real time, analyzes the trend of electrical parameters and evaluates the status of equipment, identifies anomalies in real time and predicts the risk probability of abnormal events. It also quantifies the urgency of maintenance based on the impact of abnormal events on the loss of coupled related equipment, thereby accurately generating safe power distribution maintenance tasks. The beneficial effects are: realizing intelligent management of power distribution maintenance, improving the safety of the power distribution system, and reducing losses caused by equipment failures.

[0071] Reference Figure 2 As shown, based on the operating time series data of edge power consumption equipment, the operating trend of electrical parameters in the operating time series data is analyzed, and the status indicators of each edge power consumption equipment are evaluated, including:

[0072] Determine standardized operating parameters of edge power equipment based on standardized data of edge power equipment;

[0073] Based on the operating sequence data of edge power devices, data cleaning is performed to remove noise and outliers, and normalization is performed;

[0074] Based on the pre-processed running time series data of the edge power consumption equipment, the running time series data is trend decomposed by using the autoregressive integral sliding average to obtain the running characteristic data of each edge power consumption equipment; the electrical characteristic data of the edge power consumption equipment includes: electrical periodicity, electrical seasonality, and electrical trend characteristics;

[0075] Based on the autoregressive AR architecture, an operation trend prediction model for edge power equipment is constructed;

[0076] Substitute the electrical characteristic data of each edge power device into the operation trend prediction model of the edge power device, take the minimization error function of the electrical parameters of the edge power device as the training target, and predict the electrical parameters of each edge power device in the future unit time as the output;

[0077] Linearly mapping the electrical parameters of each edge power device predicted within a future unit time with the standardized operating parameters of the edge power device to obtain a two-dimensional vector of the electrical parameters of each edge power device predicted within a future unit time and a two-dimensional vector of the standardized operating parameters of the edge power device;

[0078] Using the distance index formula, the spatial vector distance between the two-dimensional vector of electrical parameters of each edge power device and the two-dimensional vector of standardized operating parameters of the edge power device in the future unit time is calculated and recorded as the state index of each edge power device;

[0079] The operation trend prediction model of the edge power equipment is specifically as follows:

[0080]

[0081] In the formula, To predict the electrical parameters of the t-th unit time of the i-th edge electrical equipment, is a constant term, is the first The electrical parameters of the unit time lag order, , ,

[0082] are the autoregressive coefficients, is the error term;

[0083] The status indicator of each edge power-consuming device is specifically:

[0084]

[0085] In the formula, is the status indicator of the i-th edge power device, is the two-dimensional vector of electrical parameters of the ith edge electrical equipment, The two-dimensional vector of standardized operating parameters of the ith edge consumer, is the total number of edge power-consuming devices.

[0086] It can be understood that the farther the distance between the two-dimensional vector of the electrical parameters of the edge power device and the two-dimensional vector of the standardized operation parameters of the edge power device is, the worse the current state of the edge device is, and the closer the distance between the two-dimensional vector of the electrical parameters of the edge power device and the two-dimensional vector of the standardized operation parameters of the edge power device is, the better the current state of the edge device is.

[0087] This solution is based on the operating sequence data of edge power equipment. Through data cleaning, normalization and trend decomposition, the electrical characteristic data is obtained, and then the operating trend prediction model is constructed to predict future electrical parameters, and linear mapping is performed with standardized operating parameters, and the spatial vector distance is calculated to evaluate the equipment status. The beneficial effect is that the real-time operating status of edge power equipment can be accurately evaluated.

[0088] Reference Figure 3 As shown in the figure, if it is determined that the electrical equipment is abnormal, based on the operating sequence data of the edge electrical equipment, the electrical data fluctuation characteristics of the historical operating data are analyzed, and the abnormal event risk probability of the edge electrical equipment is predicted, which specifically includes:

[0089] Obtain big data on known abnormal events of edge power devices in the network;

[0090] Performing difference calculation based on standardized operating parameters of edge power equipment and historical operating data of abnormal edge power equipment to obtain historical deviation operating data of edge power equipment;

[0091] Based on Fourier transform, the operating sequence data of edge power equipment and the electrical periodic characteristics in the big data of known abnormal events of network edge power equipment are decomposed into the superposition state of sine wave and cosine wave, and the operating spectrum diagram of edge power equipment and the abnormal event spectrum diagram of edge power equipment are obtained;

[0092] Based on the historical deviation operation data of the edge power equipment, the abnormal operation spectrum in the operation spectrum diagram of the edge power equipment is marked to obtain the abnormal operation spectrum characteristics of the edge power equipment;

[0093] Calculate the matching degree between the abnormal operation spectrum characteristics of the edge power consumption equipment and the abnormal event spectrum diagram of the edge power consumption equipment, and determine the deviation direction of the abnormal operation event of each edge power consumption equipment;

[0094] Based on the standardized operating parameters of edge power equipment and the historical deviation operating data of edge power equipment, a set of positive and negative operating samples of edge power equipment is constructed;

[0095] Based on Logistic regression, an abnormal risk assessment model for edge power equipment is constructed;

[0096] The abnormal risk assessment model of edge power equipment is trained with the set of positive and negative operation samples of edge power equipment, the electrical characteristic parameters corresponding to the positive and negative operation samples of edge power equipment are used as input, and the abnormal event risk probability of the deviation direction of the abnormal operation of edge power equipment is used as output;

[0097] The calculation is based on the matching degree between the abnormal operation spectrum characteristics of the edge power consumption equipment and the abnormal event spectrum of the edge power consumption equipment as follows:

[0098]

[0099] In the formula, is the matching degree between the abnormal operation spectrum characteristics of the edge power equipment and the abnormal event spectrum of the edge power equipment, is the abnormal operation spectrum feature vector of edge power equipment, is the spectrum vector of abnormal events of edge power consumption equipment;

[0100] The abnormal risk assessment model of the edge electrical equipment is specifically as follows:

[0101]

[0102] In the formula, is the risk probability of abnormal events when the electrical characteristic parameters corresponding to the positive and negative samples of the marginal electrical equipment are input. is the electrical characteristic parameter corresponding to the positive and negative samples of the operation of the i-th edge electrical equipment, , , , Logistic regression coefficients.

[0103] This solution obtains the big data of known abnormal events of edge power equipment in the network, combines the standardized operating parameters of the equipment with the historical operating data, uses Fourier transform to analyze the periodic characteristics of the electrical data, and marks the abnormal operating spectrum. The deviation direction of the abnormal event is determined by calculating the degree of match between the abnormal operating spectrum characteristics and the known abnormal event spectrum diagram. Based on this, a set of positive and negative operation samples is constructed, and the abnormal risk assessment model is trained using Logistic regression. The model takes electrical characteristic parameters as input and outputs the deviation direction of the abnormal operation of edge power equipment and its risk probability. The beneficial effect is that it can accurately predict the risk of abnormal events of edge power equipment, provide a directional basis for abnormal events of equipment, and reduce the time for abnormal troubleshooting.

[0104] Reference Figure 4 As shown in the figure, the impact of the abnormal event risk probability of edge power equipment on the loss of coupled related power equipment when the abnormal event occurs is analyzed, and the maintenance urgency of each edge power equipment is quantified, including:

[0105] Obtaining coupled associated electrical devices of edge electrical devices;

[0106] Based on the historical operation logs and historical maintenance logs of the coupled and associated electrical equipment, the remaining ideal life span of the coupled and associated electrical equipment is quantified;

[0107] According to the risk probability of abnormal events of edge power consumption equipment and the residual value of coupled power consumption equipment, the loss value of coupled power consumption equipment when the abnormal event occurs is calculated;

[0108] According to the risk level corresponding to the loss value of the coupled associated power-consuming equipment when the abnormal event occurs, the abnormal event weight of the abnormal marginal power-consuming equipment is assigned;

[0109] Based on the risk probability of abnormal events of edge power equipment and the abnormal event weight of abnormal edge power equipment, the maintenance urgency of edge power equipment is calculated;

[0110] The calculation of the loss value of the coupled associated electrical equipment when the abnormal event occurs is specifically:

[0111]

[0112] In the formula, is the loss value of the kth coupled associated power device of the ith edge power device, is the remaining ideal life span of the kth coupled electrical equipment, is the survival function of coupled electrical equipment, is the differential variable;

[0113] The maintenance urgency of the computing edge electrical equipment is specifically:

[0114]

[0115] In the formula, It is the maintenance urgency indicator of edge power equipment. is the risk probability of abnormal events of the i-th edge power equipment, is the risk probability weight of the abnormal event of the i-th edge electrical equipment.

[0116] Through refined quantitative analysis, this solution can more accurately evaluate the impact of abnormal events in edge power equipment on coupled and associated power equipment, thereby improving the targeted equipment maintenance, effectively preventing damage to coupled equipment caused by abnormalities in edge equipment, and ensuring the stable operation of the power system.

[0117] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. Intelligent and safe power distribution platform management system based on Internet of Things technology, characterized by: include: Data acquisition module, status analysis module, abnormality judgment module, abnormality analysis module, urgency analysis module, task generation module; The data acquisition module is used to collect historical operation data of all edge power devices per unit time based on the Internet of Things sensor, and to form the operation sequence data of the edge power devices; The state analysis module is electrically connected to the data acquisition module, and is used to analyze the operating trend of electrical parameters in the operating sequence data based on the operating sequence data of the edge power consumption equipment, and evaluate the state index of each edge power consumption equipment; The abnormality judgment module is electrically connected to the state analysis module, and is used to judge whether the state indicator of each edge electrical device is within the safety threshold range of the corresponding device. If so, it is judged that the electrical device has no abnormality; if not, it is judged that the electrical device has an abnormality; The abnormality analysis module is electrically connected to the abnormality judgment module. The abnormality analysis module is used to analyze the electrical data fluctuation characteristics of the historical operation data based on the operation sequence data of the edge power consumption equipment if it is determined that the power consumption equipment has an abnormality, and predict the risk probability of abnormal events of the edge power consumption equipment; The emergency analysis module is electrically connected to the abnormality analysis module, and is used to analyze the impact of the abnormal event risk probability of edge power equipment on the loss of coupled related power equipment when the abnormal event occurs, and quantify the maintenance urgency of each edge power equipment; The task generation module is electrically connected to the urgency analysis module, and is used to generate a safe power distribution maintenance task for edge power equipment based on the maintenance urgency of each edge power equipment; If it is determined that the electrical equipment is abnormal, based on the operation sequence data of the edge electrical equipment, the electrical data fluctuation characteristics of the historical operation data are analyzed, and the abnormal event risk probability of the edge electrical equipment is predicted, which specifically includes: Obtain big data on known abnormal events of edge power devices in the network; Perform difference calculation on the standardized operating parameters of the basic edge power equipment and the historical operating data of the abnormal edge power equipment to obtain the historical deviation operating data of the edge power equipment; Based on Fourier transform, the operating sequence data of edge power equipment and the electrical periodic characteristics in the big data of known abnormal events of network edge power equipment are decomposed into the superposition state of sine wave and cosine wave, and the operating spectrum diagram of edge power equipment and the abnormal event spectrum diagram of edge power equipment are obtained; Based on the historical deviation operation data of the edge power equipment, the abnormal operation spectrum in the operation spectrum diagram of the edge power equipment is marked to obtain the abnormal operation spectrum characteristics of the edge power equipment; Calculate the matching degree between the abnormal operation spectrum characteristics of the edge power consumption equipment and the abnormal event spectrum diagram of the edge power consumption equipment, and determine the deviation direction of the abnormal operation event of each edge power consumption equipment; Based on the standardized operating parameters of edge power equipment and the historical deviation operating data of edge power equipment, a set of positive and negative operating samples of edge power equipment is constructed; Based on Logistic regression, an abnormal risk assessment model for edge power equipment is constructed; The abnormal risk assessment model of edge power equipment is trained with a set of positive and negative operation samples of edge power equipment, with the electrical characteristic parameters corresponding to the positive and negative operation samples of edge power equipment as input, and the risk probability of abnormal events in the deviation direction of the abnormal operation of edge power equipment as output.

2. According to claim 1, the intelligent and safe power distribution platform management system based on Internet of Things technology is characterized in that: Based on the operation time series data of edge power consumption equipment, the operation trend of electrical parameters in the operation time series data is analyzed, and the status indicators of each edge power consumption equipment are evaluated, including: Determine standardized operating parameters of edge power equipment based on standardized data of edge power equipment; Based on the operating sequence data of edge power devices, data cleaning is performed to remove noise and outliers, and normalization is performed; Based on the pre-processed running time series data of the edge power consumption equipment, the running time series data is trend decomposed by using the autoregressive integrated sliding average to obtain the running characteristic data of each edge power consumption equipment; the electrical characteristic data of the edge power consumption equipment includes: electrical periodicity, electrical seasonality, and electrical trend characteristics; Based on the autoregressive AR architecture, an operation trend prediction model for edge power equipment is constructed; Substitute the electrical characteristic data of each edge power device into the operation trend prediction model of the edge power device, take the minimization error function of the electrical parameters of the edge power device as the training target, and predict the electrical parameters of each edge power device in the future unit time as the output; Linearly mapping the electrical parameters of each edge power device predicted within a future unit time with the standardized operating parameters of the edge power device to obtain a two-dimensional vector of the electrical parameters of each edge power device predicted within a future unit time and a two-dimensional vector of the standardized operating parameters of the edge power device; Using the distance index formula, the spatial vector distance between the two-dimensional vector of electrical parameters of each edge power consumer in the future unit time and the two-dimensional vector of standardized operating parameters of the edge power consumer is calculated and recorded as the state index of each edge power consumer.

3. The intelligent and safe power distribution platform management system based on Internet of Things technology according to claim 2 is characterized in that: The operation trend prediction model of the edge power equipment is specifically as follows: In the formula, To predict the electrical parameters of the t-th unit time of the i-th edge electrical equipment, is a constant term, is the first The electrical parameters of the unit time lag order, , , are the autoregression coefficients, is the error term; The status indicator of each edge power-consuming device is specifically: In the formula, is the status indicator of the i-th edge power device, is the two-dimensional vector of electrical parameters of the ith edge electrical equipment, The two-dimensional vector of standardized operating parameters of the ith edge consumer, is the total number of edge power-consuming devices.

4. The intelligent and safe power distribution platform management system based on Internet of Things technology according to claim 3 is characterized in that: The calculation is based on the matching degree between the abnormal operation spectrum characteristics of the edge power consumption equipment and the abnormal event spectrum of the edge power consumption equipment as follows: In the formula, is the matching degree between the abnormal operation spectrum characteristics of the edge power equipment and the abnormal event spectrum of the edge power equipment, is the abnormal operation spectrum feature vector of edge power equipment, is the spectrum vector of abnormal events of edge power consumption equipment; The abnormal risk assessment model of the edge electrical equipment is specifically as follows: In the formula, is the risk probability of abnormal events when the electrical characteristic parameters corresponding to the positive and negative samples of the marginal electrical equipment are input. is the electrical characteristic parameter corresponding to the positive and negative samples of the operation of the i-th edge electrical equipment, , , Logistic regression coefficients.

5. The intelligent and safe power distribution platform management system based on Internet of Things technology according to claim 4 is characterized in that: Analyze the impact of abnormal event risk probability of edge power equipment on the loss of coupled and associated power equipment when abnormal events occur, and quantify the maintenance urgency of each edge power equipment, including: Obtaining coupled associated electrical devices of edge electrical devices; Based on the historical operation logs and historical maintenance logs of the coupled and associated electrical equipment, the remaining ideal life span of the coupled and associated electrical equipment is quantified; According to the risk probability of abnormal events of edge power consumption equipment and the residual value of coupled power consumption equipment, the loss value of coupled power consumption equipment when the abnormal event occurs is calculated; According to the risk level corresponding to the loss value of the coupled associated power-consuming equipment when the abnormal event occurs, the abnormal event weight of the abnormal marginal power-consuming equipment is assigned; Based on the risk probability of abnormal events of edge power equipment and the abnormal event weight of abnormal edge power equipment, the maintenance urgency of edge power equipment is calculated.

6. The intelligent and safe power distribution platform management system based on Internet of Things technology according to claim 5 is characterized in that: The specific calculation of the loss reduction value of the coupled associated electrical equipment when an abnormal event occurs is: In the formula, is the loss value of the kth coupled associated power device of the ith edge power device, is the remaining ideal life span of the kth coupled electrical equipment, is the survival function of coupled electrical equipment, is the differential variable; The maintenance urgency of the computing edge electrical equipment is specifically: In the formula, It is the maintenance urgency indicator of edge power equipment. is the risk probability of abnormal events of the i-th edge power equipment, is the risk probability weight of the abnormal event of the i-th edge electrical equipment.

Images