Intelligent power distribution cabinet operation supervision optimization control method and system, and storage medium

Abstract

The invention discloses an intelligent power distribution cabinet operation supervision optimization control method and system and a storage medium, and belongs to the technical field of intelligent power distribution cabinet operation supervision, and the method comprises the steps: obtaining the information of each intelligent power distribution cabinet, and setting a corresponding monitoring graph according to the information of each intelligent power distribution cabinet; display nodes of all the intelligent power distribution cabinets are supplemented and arranged in the monitoring graph; establishing a data transmission channel with each intelligent power distribution cabinet, obtaining monitoring data of each intelligent power distribution cabinet through the data transmission channel, and inputting the monitoring data into a corresponding display node in the monitoring graph for real-time display; performing collaborative classification on the intelligent power distribution cabinets according to the information of the intelligent power distribution cabinets in the monitoring graph; identifying monitoring data of each display node in the monitoring graph in real time, and classifying the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; establishing an exception recognition model, and analyzing the monitoring analysis data through the exception recognition model to obtain a corresponding exception recognition result; and processing according to an abnormal identification result.

Description

Technical Field

[0001] The present invention belongs to the technical field of operation supervision of intelligent power distribution cabinets, and specifically relates to an operation supervision optimization control method, system and storage medium of an intelligent power distribution cabinet. Background Art

[0002] With the increasing scarcity of energy resources and the requirements for environmental protection, improving energy efficiency and achieving energy conservation and emission reduction have become important goals. As an important part of the power system, the operation supervision and optimization control of the distribution cabinet can help improve energy utilization efficiency and reduce energy waste; especially the emergence of intelligent distribution cabinets, which can realize all-round monitoring of power quality such as voltage, current, frequency, useful power, useless power, electric energy, harmonics, etc. through intelligent distribution cabinets; greatly facilitating power management.

[0003] However, the operation supervision and optimization control of the intelligent distribution cabinet requires the integration of multiple components and systems, including sensors, monitoring equipment, intelligent control systems, etc., which increases the complexity of the system and the difficulty of maintenance, especially during the supervision process, it is necessary to supervise multiple intelligent distribution cabinets in the responsible area at the same time. When problems occur in the sensors, monitoring equipment, etc. in the intelligent distribution cabinet, the monitoring data will be inaccurate, and the corresponding staff will not be able to discover them in time, resulting in various phenomena such as abnormal alarms and unreasonable regulation. Because the monitoring data is the benchmark for intelligent monitoring, when the benchmark data is inaccurate, other supervision functions may be abnormal; however, during the application process, sensors, monitoring equipment, etc. are more easily affected by dust, specific debris, abnormal environment, etc., resulting in data inaccuracy, and the current intelligent distribution cabinet operation monitoring system is difficult to detect, which makes it easy to cause abnormal control due to data inaccuracy in some cases; therefore, in order to improve the existing operation supervision of intelligent distribution cabinets, the present invention provides an intelligent distribution cabinet operation supervision optimization control method, system and storage medium. Summary of the invention

[0004] In order to solve the problems existing in the above-mentioned scheme, the present invention provides an intelligent distribution cabinet operation supervision optimization control method, system and storage medium.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] An intelligent power distribution cabinet operation supervision optimization control method, the method comprising:

[0007] Step S1: Acquire information of each intelligent power distribution cabinet, set a corresponding monitoring diagram according to the information of each intelligent power distribution cabinet; and supplement the display node of each intelligent power distribution cabinet in the monitoring diagram; the display node is used to display the monitoring data of each intelligent power distribution cabinet in real time;

[0008] Step S2: establishing a data transmission channel with each of the intelligent power distribution cabinets, acquiring monitoring data of each of the intelligent power distribution cabinets in real time through the data transmission channel, and inputting the monitoring data into a corresponding display node in the monitoring diagram for real-time display;

[0009] Furthermore, network anomaly preprocessing is performed on the data transmission channel.

[0010] Furthermore, the method for preprocessing network anomalies is network optimization processing, and the method for network optimization processing includes:

[0011] Acquire historical data transmission records of each of the data transmission channels, and identify transmission characteristic data corresponding to the data transmission channel in real time according to the historical data transmission records; the transmission characteristic data includes a delay time period and a corresponding delay item;

[0012] Generate a transmission characteristic graph corresponding to each of the data transmission channels according to the transmission characteristic data;

[0013] Setting an evaluation time period [t1, t0], marking the evaluation time period in real time in the transmission characteristic graph; integrating each delay value curve within the evaluation time period [t1, t0] into an evaluation curve, and fitting a corresponding evaluation function G(t) according to the evaluation curve;

[0014] According to the evaluation formula Calculate the corresponding evaluation value, where: P assets is the evaluation value; the data transmission channel with the evaluation value greater than the threshold X1 is marked as the channel to be optimized, and the network transmission optimization is performed on the channel to be optimized.

[0015] Furthermore, the method for setting the transmission characteristic map includes:

[0016] Generate a transmission characteristic axis corresponding to each of the data transmission channels according to the transmission characteristic data;

[0017] Mark the delayed items in the delay time period as i, i=1, 2, ..., n, and n is the number of delayed items;

[0018] According to the formula Calculate the instantaneous delay value of each delay item in the delay time period, where: T value is the instantaneous delay value; Δt is the time period starting from the start of the delay time period; t min and t max are the minimum time period and the maximum time period respectively; lg(*) is the logarithmic function with base 10; exp(*) is the exponential function with the natural constant e as the base; λ is the correction factor, and its value range is 0<λ≤1;

[0019] The instantaneous delay value of each delay item is marked as Tivalue ; then the comprehensive delay value of the delay time period Where: Tl value is the comprehensive delay value; i = 1, 2, ..., n, n is the number of delay items;

[0020] Establish a corresponding coordinate graph according to the transmission characteristic axis; input each comprehensive delay value corresponding to the delay time period in the coordinate graph, and connect them to form a delay value curve corresponding to the delay time period; mark the current coordinate graph as a transmission characteristic graph.

[0021] Step S3: According to the information of each intelligent power distribution cabinet in the monitoring diagram, collaboratively classify each intelligent power distribution cabinet, and mark each intelligent power distribution cabinet with a corresponding collaborative classification label;

[0022] Furthermore, the method of performing collaborative classification includes:

[0023] A preset feature matching table is used to count feature ranges and corresponding feature numbers corresponding to different intelligent power distribution cabinet information, application environment information and object power consumption information;

[0024] Matching is performed according to the feature matching table and the data corresponding to the intelligent power distribution cabinet to obtain the intelligent power distribution cabinet features corresponding to each of the intelligent power distribution cabinets;

[0025] The intelligent distribution cabinets with the same characteristics are classified into one category, which is marked as collaborative classification.

[0026] Furthermore, the method for preprocessing network anomalies is monitoring data simulation; the method for monitoring data simulation includes:

[0027] Identify the collaborative distribution cabinets with the same collaborative classification label; identify the collaborative distribution cabinets with abnormal data transmission channels, mark them as simulated collaborative distribution cabinets, and mark the collaborative distribution cabinets corresponding to the data transmission channels without abnormal data transmission as reference collaborative distribution cabinets; mark the monitoring data before the transmission abnormality of the simulated collaborative distribution cabinet as target monitoring data;

[0028] Obtain the historical monitoring data of each of the collaborative distribution cabinets, and establish a data simulation model corresponding to the collaborative classification based on the historical monitoring data, wherein the input of the data simulation model is the target monitoring data of the simulated collaborative distribution cabinet, the monitoring data of each reference collaborative distribution cabinet at the same time as the target monitoring data, and the monitoring data of each reference collaborative distribution cabinet at a subsequent time; the output of the data simulation model is the simulated monitoring data of the simulated collaborative distribution cabinet at a subsequent time, that is, the data at a time corresponding to the monitoring data of each reference collaborative distribution cabinet at a subsequent time;

[0029] Analyze through the data simulation model to obtain corresponding simulated monitoring data, and display the simulated monitoring data at the corresponding display node in the monitoring diagram;

[0030] When receiving monitoring data that has not been received due to delay, the corresponding analog monitoring data is replaced.

[0031] Furthermore, the method for preprocessing network anomalies is a combined application of network optimization processing and monitoring data simulation.

[0032] Step S4: real-time identification of monitoring data of each display node in the monitoring graph, and grouping the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; establishing an abnormality identification model, and analyzing the monitoring analysis data through the abnormality identification model to obtain corresponding abnormality identification results, wherein the abnormality identification results include normal identification and abnormal identification;

[0033] Furthermore, the expression of the abnormality recognition model in step S4 is:

[0034]

[0035] In the formula: x is the input data, the input data is the monitoring data; the output data is the abnormal monitoring value f(x).

[0036] Step S5: Processing is performed according to the abnormal identification result. When the abnormal identification result is normal identification, no corresponding operation is performed; when the abnormal identification result is abnormal identification, the corresponding intelligent distribution cabinet is identified and a corresponding alarm mark is made in the monitoring diagram;

[0037] Step S6: Real-time identification of the monitoring data of each display node in the monitoring diagram, when the preset time is reached, data meter reading is recorded, and the meter reading data is sent to the corresponding staff.

[0038] An intelligent power distribution cabinet operation supervision and optimization control system, comprising a transmission module, a monitoring module and an analysis module;

[0039] The transmission module is used to establish a data transmission channel with each intelligent power distribution cabinet, obtain the monitoring data of each intelligent power distribution cabinet in real time through the data transmission channel, and send the monitoring data to the monitoring module; and perform network abnormality preprocessing on the data transmission channel;

[0040] The monitoring module is used to monitor each intelligent power distribution cabinet, set a corresponding monitoring diagram according to the information of each intelligent power distribution cabinet, and input the received monitoring data into the corresponding display node in the monitoring diagram for real-time display;

[0041] The analysis module is used to analyze according to the monitoring diagram, collaboratively classify each intelligent power distribution cabinet according to the information of each intelligent power distribution cabinet in the monitoring diagram, and mark each intelligent power distribution cabinet with a corresponding collaborative classification label;

[0042] Identify the monitoring data of each display node in the monitoring map in real time, and classify the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; establish an anomaly recognition model, analyze the monitoring analysis data through the anomaly recognition model, and obtain the corresponding anomaly recognition results, which include normal recognition and abnormal recognition;

[0043] Processing is performed according to the abnormal identification result. When the abnormal identification result is normal identification, no corresponding operation is performed; when the abnormal identification result is abnormal identification, the corresponding intelligent distribution cabinet is identified and a corresponding alarm mark is made in the monitoring diagram.

[0044] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet are implemented.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] By pre-processing the data transmission channel for network anomalies, real-time monitoring and analysis of the intelligent distribution cabinet is guaranteed to avoid the lack of monitoring data of one or some intelligent distribution cabinets due to data transmission problems, and thus the inability to conduct supervision and analysis; from the direction of network optimization processing, the smooth flow of data transmission channels is guaranteed, and from the direction of monitoring data simulation, the continuous and uninterrupted monitoring data is guaranteed, thereby realizing intelligent optimization of the existing intelligent distribution cabinet supervision system.

[0047] Through collaborative classification, all intelligent distribution cabinets with the same or similar changes are classified into one category, and the historical monitoring data within the collaborative classification is used to establish an anomaly recognition model. Subsequently, based on the monitoring data of each collaborative distribution cabinet in the collaborative classification, a joint analysis is performed to identify abnormal data that is different from other monitoring data. Because the difference in monitoring data of each collaborative distribution cabinet under ideal conditions is very small, even in actual application, the gap between each monitoring data will not be very large, making it easier to identify abnormal data; this helps to improve the accuracy of anomaly recognition.

[0048] Remote meter reading can also be realized, and the working status of each intelligent distribution cabinet can be obtained in real time through the monitoring diagram. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 This is a principle block diagram of the present invention. DETAILED DESCRIPTION

[0051] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, a method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet comprises:

[0053] Step S1: Obtain information of each intelligent distribution cabinet that needs to be supervised, such as type, model, location, data of each monitoring device, etc.; the information can be collected according to the preset intelligent distribution cabinet information collection template; set the corresponding monitoring map according to the obtained information of each intelligent distribution cabinet; supplement the display node of each intelligent distribution cabinet in the monitoring map, the display node is used to display the monitoring data of each intelligent distribution cabinet in real time, and the display is set according to the monitoring items corresponding to each intelligent distribution cabinet.

[0054] According to the location of each intelligent power distribution cabinet, the corresponding location is marked in the map, and the preset model representing each intelligent power distribution cabinet is marked at the corresponding location to represent the corresponding intelligent power distribution cabinet; then the current map is regarded as a monitoring map.

[0055] Step S2: Connect with each intelligent power distribution cabinet and establish a corresponding data transmission channel. Data can be transmitted by wire or wirelessly. The monitoring data of each intelligent power distribution cabinet, such as the monitoring data of current, voltage, power and other monitoring equipment, is obtained in real time through the data transmission channel; the obtained monitoring data is input into each display node in the monitoring diagram for real-time display;

[0056] Among them, data cleaning, format conversion and other processing of monitoring data shall be handled in accordance with existing processing measures.

[0057] In one embodiment, because many current data transmission channels need to rely on network connections, including local area networks or the Internet, if the network connection is unstable or interrupted, it may affect the effect of supervision and control, resulting in poor data transmission and affecting the monitoring and adjustment of the intelligent distribution cabinet supervision system; therefore, it is necessary to perform network abnormality preprocessing on the data transmission channel; in this embodiment, network abnormality preprocessing includes two methods, namely:

[0058] 1. Network optimization processing, that is, based on the past data transmission situation, evaluate whether the data transmission channel can meet the data transmission requirements. For data transmission channels that cannot meet the data transmission requirements, network optimization is carried out by changing the transmission method and upgrading network equipment.

[0059] 2. Monitoring data simulation: When the monitoring data cannot be received in time due to network problems, the monitoring data simulation is performed based on the current data to estimate the monitoring data that has not been monitored and display it for supervision. That is, it is used for predictive supervision and corresponding corrections are made when the corresponding monitoring data is received later.

[0060] The specific method is as follows:

[0061] Network optimization processing:

[0062] Obtain historical data transmission records of each data transmission channel, identify time periods with transmission delays and monitoring items corresponding to the corresponding delayed transmission data according to the historical data transmission records; integrate each delayed time period and the corresponding monitoring item into transmission characteristic data; that is, the transmission characteristic data corresponding to a data transmission channel includes each delayed time period and monitoring item combination corresponding to the data transmission channel; generate a transmission characteristic axis corresponding to each data transmission channel according to the transmission characteristic data, that is, mark each delayed time period on the time axis, and mark the monitoring item corresponding to each delayed time period;

[0063] To facilitate differentiation, the monitored items in the transmission characteristic axis are labeled as delay items;

[0064] The delayed items in the delay time period are marked as i, i=1, 2, ..., n, and n is the number of delayed items; the delayed items in different delay time periods may be different;

[0065] Calculate the instantaneous delay value of each delay item within the delay time period.

[0066] In one embodiment, the calculation is performed based on the actual delay situation, specifically based on the actual delay situation and the correction factor of each delay item. The impact corresponding to the transmission delay of different delay items is different. The greater the impact, the greater the correction factor. The correction factor corresponding to each delay item can be preset; specifically, the instantaneous delay value of each delay item is determined based on the existing technology.

[0067] In one implementation, according to the formula Calculate the instantaneous delay value of each delay item within the delay time period, where: T value is the instantaneous delay value; Δt is the time period starting from the starting point of the delay time period, that is, the corresponding moment corresponds to the time period from the starting point; t min and t max They are respectively the minimum time period and the maximum time period in the statistical delay time period database, referred to as the minimum time period and the maximum time period for short; lg(*) is a logarithmic function with base 10; exp(*) is an exponential function with the natural constant e as base; λ is a correction factor with a value range of 0<λ≤1, which is set according to the corresponding delay item. The impact of different delay items on the transmission delay is different. The greater the impact, the greater the correction factor. The correction factor corresponding to each delay item can be preset.

[0068] The instantaneous delay value of each delay item is expressed as Ti value ; then the instantaneous delay value of the delay time period Tl value is the instantaneous delay value of the delay time period, marked as the comprehensive delay value;

[0069] Add a coordinate axis corresponding to the comprehensive delay value to the transmission characteristic axis, which can be used as the y-axis, and time as the x-axis to form a transmission characteristic diagram; input each comprehensive delay value corresponding to the delay time period in the transmission characteristic diagram, and connect them to form a delay value curve corresponding to the delay time period;

[0070] Set the evaluation time period. The evaluation time period takes the current time as the starting point and moves forward for a period of time as the evaluation benchmark. The delay situation in this time period is used as the evaluation standard for the data transmission channel. For example, you can choose a time span of 1 day, 3 days, 1 week, etc. as the evaluation benchmark; delays outside the evaluation time period are not considered; mark the evaluation time period as [t1, t0], and mark the position corresponding to the evaluation time period in the transmission feature graph in real time, that is, mark t1 and t0;

[0071] The delay value curves within the evaluation time period [t1, t0] are integrated into an evaluation curve, which is a curve formed by combining the delay value curves within the evaluation time period [t1, t0] and a line segment with a comprehensive delay value of 0; using existing fitting technology, a function of the evaluation curve is fitted, marked as an evaluation function G(t); such as using Matlab for fitting.

[0072] According to the evaluation formula Calculate the corresponding evaluation value, where: P assets is the evaluation value; the data transmission channel with the evaluation value greater than the threshold X1 is marked as the channel to be optimized, and the network transmission optimization is performed on the channel to be optimized.

[0073] Monitoring data simulation:

[0074] Identify each intelligent distribution cabinet with the same collaborative classification label and mark it as a collaborative distribution cabinet; obtain the historical monitoring data of each collaborative distribution cabinet, and establish a data simulation model corresponding to the collaborative classification based on the historical monitoring data obtained. The data simulation model is used to simulate the monitoring data of the next period of time based on the current monitoring data, that is, when the data is received with a delay, it can simulate the monitoring data of this period of time, which is equivalent to a prediction model to predict the corresponding monitoring data; it is a self-learning model that can perform real-time simulation and correction learning based on real-time monitoring data; it is established using existing prediction model technology; the input data of the data simulation model is not the monitoring data of a single collaborative distribution cabinet, but is analyzed based on the monitoring data of other collaborative distribution cabinets.

[0075] Exemplarily, when the monitoring data transmission of an intelligent distribution cabinet is delayed, the monitoring data of all corresponding collaborative distribution cabinets at the same time are identified; referring to the real-time monitoring data changes of other collaborative distribution cabinets, the next monitoring data is predicted based on the monitoring data of the intelligent distribution cabinet with transmission delay; and the simulation accuracy is improved through collaborative correction of other collaborative distribution cabinets.

[0076] In other embodiments, the network optimization process and the monitoring data simulation may be applied separately or in combination.

[0077] By pre-processing the data transmission channel for network anomalies, real-time monitoring and analysis of the intelligent distribution cabinet is guaranteed to avoid the lack of monitoring data of one or some intelligent distribution cabinets due to data transmission problems, and thus the inability to conduct supervision and analysis; from the direction of network optimization processing, the smooth flow of data transmission channels is guaranteed, and from the direction of monitoring data simulation, the continuous and uninterrupted monitoring data is guaranteed, thereby realizing intelligent optimization of the existing intelligent distribution cabinet supervision system.

[0078] Step S3: According to the information of each intelligent power distribution cabinet in the monitoring diagram, collaborative classification of each intelligent power distribution cabinet is performed, and a corresponding collaborative classification label is marked for each intelligent power distribution cabinet;

[0079] According to the information of each smart distribution cabinet, the smart distribution cabinet characteristics of each smart distribution cabinet are analyzed, and the smart distribution cabinets with the same characteristics are classified into one category, that is, collaborative classification. The characteristics of the smart distribution cabinet are set from three directions: equipment, environment, and use; use refers to the electricity usage habits of the object, such as treating the same or similar electricity usage habits as the same feature; specifically, the simulation is carried out under the same conditions, and the ones with the same impact are classified into one category to form characteristic standards in the three directions of equipment, environment, and use, that is, to obtain the actual response range of the smart distribution cabinet, that is, the range of simulation conditions that the smart distribution cabinet may have in the actual application process, and gradually change the simulation conditions to identify the changes in monitoring data of the smart distribution cabinet under different equipment conditions, different working environments, and different electricity usage conditions. It is simulated using a single variable control method, such as environment and inconvenience in use. Simulate, and then keep the equipment and environment unchanged, and so on, simulate the changes in the monitoring data with the changes in simulation conditions in a single direction, and then count the changes in the monitoring data with the changes in simulation conditions in various situations, and classify the equipment situations in which the changes in monitoring data are within the allowable range, that is, classify the equipment situations with basically the same impact on monitoring, to form various situation classifications for the equipment direction, each situation classification corresponds to an equipment feature range, marked with the corresponding equipment feature number; and so on, to form the environmental feature range and the usage feature range; after integration, the equipment feature matching table, the environmental feature matching table and the usage feature matching table are formed and merged into the feature matching table.

[0080] According to the intelligent distribution cabinet information, application environment information and object power consumption information, the corresponding device feature number, environment feature number and usage feature number are matched from the feature matching table and integrated into the intelligent distribution cabinet feature.

[0081] It is also possible to directly set up feature matching tables in the three directions of equipment, environment and use based on manual experience; or other existing methods can be used to set the features of the intelligent distribution cabinet; such as using existing neural network technology to establish a corresponding feature analysis model based on a CNN network or a DNN network, and manually establish a corresponding training set for training. The training set includes input data and output data, and the input data is the intelligent distribution cabinet information, application environment information and object power consumption information; the equipment feature number, environmental feature number and usage feature number of the intelligent distribution cabinet in three directions are output, and integrated into the intelligent distribution cabinet features; because neural networks are common knowledge, they are not described in detail.

[0082] Step S4: Real-time identification of monitoring data of each display node in the monitoring diagram, and grouping the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; establishing an abnormality identification model, analyzing the monitoring analysis data through the abnormality identification model, determining whether there is abnormal monitoring data, and obtaining corresponding abnormality identification results, which include identification of normal and identification of abnormal;

[0083] In one embodiment, the expression of the anomaly recognition model is: The historical monitoring data of each coordinated power distribution cabinet is used for training setting, that is, the historical monitoring data is used for simulation training, so that it can be judged whether it is abnormal monitoring data according to the monitoring data; x is the input data, the input data is the monitoring data; the output data is the abnormal monitoring value f(x);

[0084] The abnormality identification result is subsequently determined based on the obtained abnormal monitoring value.

[0085] In another embodiment, the anomaly recognition model can be a model established based on other existing technologies using abnormal data recognition; such as an anomaly recognition model established using a neural network; it can also be identified using models established using various clustering algorithms to determine monitoring data that is not within the cluster.

[0086] Step S5: Processing is performed according to the abnormal identification result. When the abnormal identification result is normal identification, no corresponding operation is performed; when the abnormal identification result is abnormal identification, the corresponding intelligent power distribution cabinet is identified and a corresponding alarm mark is made in the monitoring diagram; such as various marks different from those displayed by other intelligent power distribution cabinets, indicating that its monitoring data is abnormal;

[0087] Step S6: Real-time identification of the monitoring data of each display node in the monitoring diagram, when the preset time is reached, data meter reading is recorded, and the meter reading data is sent to the corresponding staff.

[0088] Through collaborative classification, all intelligent distribution cabinets with the same or similar changes are classified into one category, and the historical monitoring data within the collaborative classification is used to establish an anomaly recognition model. Subsequently, based on the monitoring data of each collaborative distribution cabinet in the collaborative classification, a joint analysis is performed to identify abnormal data that is different from other monitoring data. Because the difference in monitoring data of each collaborative distribution cabinet under ideal conditions is very small, even in actual application, the gap between each monitoring data will not be very large, making it easier to identify abnormal data; this helps to improve the accuracy of anomaly recognition.

[0089] Remote meter reading can also be realized, and the working status of each intelligent distribution cabinet can be obtained in real time through the monitoring diagram.

[0090] An intelligent power distribution cabinet operation supervision and optimization control system, comprising a transmission module, a monitoring module and an analysis module;

[0091] The transmission module is used to establish a data transmission channel with each intelligent distribution cabinet, obtain the monitoring data of each intelligent distribution cabinet in real time through the data transmission channel, and send the monitoring data to the monitoring module; and perform network abnormality preprocessing on the data transmission channel.

[0092] The monitoring module is used to monitor each intelligent power distribution cabinet, set a corresponding monitoring diagram according to the information of each intelligent power distribution cabinet, and input the received monitoring data into the corresponding display node in the monitoring diagram for real-time display.

[0093] The analysis module is used to analyze according to the monitoring diagram, collaboratively classify each intelligent power distribution cabinet according to the information of each intelligent power distribution cabinet in the monitoring diagram, and mark each intelligent power distribution cabinet with a corresponding collaborative classification label;

[0094] Identify the monitoring data of each display node in the monitoring map in real time, and classify the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; establish an anomaly recognition model, analyze the monitoring analysis data through the anomaly recognition model, and obtain the corresponding anomaly recognition results, which include normal recognition and abnormal recognition;

[0095] Processing is performed according to the abnormal identification result. When the abnormal identification result is normal identification, no corresponding operation is performed; when the abnormal identification result is abnormal identification, the corresponding intelligent distribution cabinet is identified and a corresponding alarm mark is made in the monitoring diagram.

[0096] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet are implemented.

[0097] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.

[0098] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet, characterized in that: Methods include: Step S1: Acquire information of each intelligent power distribution cabinet, set a corresponding monitoring diagram according to the information of each intelligent power distribution cabinet; and supplement the display node corresponding to each intelligent power distribution cabinet in the monitoring diagram; the display node is used to display the monitoring data of each intelligent power distribution cabinet in real time; Step S2: establishing a data transmission channel with each of the intelligent power distribution cabinets, acquiring monitoring data of each of the intelligent power distribution cabinets in real time through the data transmission channel, and inputting the monitoring data into a corresponding display node in the monitoring diagram for real-time display; Step S3: collaboratively classify each of the intelligent power distribution cabinets according to the information of each intelligent power distribution cabinet in the monitoring diagram, and mark each of the intelligent power distribution cabinets with a corresponding collaborative classification label; Step S4: real-time identification of monitoring data of each display node in the monitoring graph, and grouping the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; establishing an abnormality identification model, and analyzing the monitoring analysis data through the abnormality identification model to obtain corresponding abnormality identification results, wherein the abnormality identification results include normal identification and abnormal identification; Step S5: Processing is performed according to the abnormal identification result. When the abnormal identification result is normal identification, no corresponding operation is performed; when the abnormal identification result is abnormal identification, the corresponding intelligent distribution cabinet is identified and a corresponding alarm mark is made in the monitoring diagram; Step S6: Real-time identification of the monitoring data of each display node in the monitoring diagram, when the preset time is reached, data meter reading is recorded, and the meter reading data is sent to the corresponding staff.

2. According to claim 1, a smart distribution cabinet operation supervision optimization control method is characterized in that: In step S2, network abnormality preprocessing is performed on the data transmission channel.

3. The intelligent power distribution cabinet operation supervision optimization control method according to claim 2 is characterized in that: The method for preprocessing network anomalies is network optimization processing, which includes: Acquire historical data transmission records of each of the data transmission channels, and identify transmission characteristic data corresponding to the data transmission channel in real time according to the historical data transmission records; the transmission characteristic data includes a delay time period and a corresponding delay item; Generate a transmission characteristic graph corresponding to each of the data transmission channels according to the transmission characteristic data; Setting an evaluation time period [t1, t0], marking the evaluation time period in real time in the transmission characteristic graph; integrating each delay value curve within the evaluation time period [t1, t0] into an evaluation curve, and fitting a corresponding evaluation function G(t) according to the evaluation curve; According to the evaluation formula Calculate the corresponding evaluation value, where: P assets is the evaluation value; the data transmission channel with the evaluation value greater than the threshold X1 is marked as the channel to be optimized, and the network transmission optimization is performed on the channel to be optimized.

4. The intelligent power distribution cabinet operation supervision optimization control method according to claim 3 is characterized in that: The method for setting the transmission characteristic map includes: Generate a transmission characteristic axis corresponding to each of the data transmission channels according to the transmission characteristic data; Mark the delayed items in the delay time period as i, i=1, 2, ..., n, and n is the number of delayed items; Determine the instantaneous delay value of each delay item within the delay time period; mark the instantaneous delay value of each delay item as Ti value ; then the comprehensive delay value of the delay time period Where: Tl value is the comprehensive delay value; i = 1, 2, ..., n, n is the number of delay items; Establish a corresponding coordinate graph according to the transmission characteristic axis; input each comprehensive delay value corresponding to the delay time period in the coordinate graph, and connect them to form a delay value curve corresponding to the delay time period; mark the current coordinate graph as a transmission characteristic graph.

5. The method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet according to claim 2 is characterized in that: The method for performing collaborative classification in step S3 includes: A preset feature matching table is used to count feature ranges and corresponding feature numbers corresponding to different intelligent power distribution cabinet information, application environment information and object power consumption information; Matching is performed according to the feature matching table and the data corresponding to the intelligent power distribution cabinet to obtain the intelligent power distribution cabinet features corresponding to each of the intelligent power distribution cabinets; The intelligent distribution cabinets with the same characteristics are classified into one category, which is marked as collaborative classification.

6. The method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet according to claim 5 is characterized in that: The method for preprocessing network anomalies is monitoring data simulation; the method for monitoring data simulation includes: Identify the collaborative distribution cabinets with the same collaborative classification label; identify the collaborative distribution cabinets with abnormal data transmission channels and mark them as simulated collaborative distribution cabinets, and mark the collaborative distribution cabinets corresponding to the data transmission channels without abnormal data transmission as reference collaborative distribution cabinets; Obtain the historical monitoring data of each of the collaborative distribution cabinets, and establish a data simulation model corresponding to the collaborative classification based on the historical monitoring data, wherein the input of the data simulation model is the target monitoring data of the simulated collaborative distribution cabinet, the monitoring data of each reference collaborative distribution cabinet at the same time as the target monitoring data, and the monitoring data of each reference collaborative distribution cabinet at a subsequent time; the output of the data simulation model is the simulated monitoring data of the simulated collaborative distribution cabinet at a subsequent time; Analyze through the data simulation model to obtain corresponding simulated monitoring data, and display the simulated monitoring data at the corresponding display node in the monitoring diagram; When corresponding monitoring data is received, the monitoring data replaces the simulated monitoring data.

7. The method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet according to claim 2 is characterized in that: The method for network anomaly preprocessing is a combined application of network optimization processing and monitoring data simulation.

8. The method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet according to claim 1 is characterized in that: The expression of the abnormality recognition model in step S4 is: In the formula: x is the input data, the input data is the monitoring data; the output data is the abnormal monitoring value f(x).

9. An intelligent distribution cabinet operation supervision and optimization control system, characterized in that: A method for optimizing and controlling the operation supervision of an intelligent power distribution cabinet according to any one of claims 1 to 8 is implemented, comprising a transmission module, a monitoring module and an analysis module; The transmission module is used to establish a data transmission channel with each intelligent power distribution cabinet, obtain the monitoring data of each intelligent power distribution cabinet in real time through the data transmission channel, and send the monitoring data to the monitoring module; and perform network abnormality preprocessing on the data transmission channel; The monitoring module is used to monitor each intelligent power distribution cabinet, set a corresponding monitoring diagram according to the information of each intelligent power distribution cabinet, and input the received monitoring data into the corresponding display node in the monitoring diagram for real-time display; The analysis module is used to analyze according to the monitoring diagram, collaboratively classify each intelligent power distribution cabinet according to the information of each intelligent power distribution cabinet in the monitoring diagram, and mark each intelligent power distribution cabinet with a corresponding collaborative classification label; Identify the monitoring data of each display node in the monitoring map in real time, and group the monitoring data belonging to the same collaborative classification into a group of monitoring analysis data; Establish an abnormality recognition model, analyze the monitoring and analysis data through the abnormality recognition model, and obtain the corresponding abnormality recognition results. The abnormality recognition results include normal recognition and abnormal recognition; Processing is performed according to the abnormal identification result. When the abnormal identification result is normal identification, no corresponding operation is performed; when the abnormal identification result is abnormal identification, the corresponding intelligent distribution cabinet is identified and a corresponding alarm mark is made in the monitoring diagram.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the intelligent distribution cabinet operation supervision and optimization control method as described in any one of claims 1 to 8 are implemented.

Images