Distribution area visual intelligent monitoring method and system based on distribution network big data

Abstract

The invention relates to the technical field of power grid parameter monitoring, and discloses a distribution network big data-based transformer area visual intelligent monitoring method and system, and the method comprises the steps: determining a to-be-monitored transformer area, determining a to-be-monitored node set of the to-be-monitored transformer area, carrying out the distribution network parameter monitoring of a to-be-monitored node, and obtaining a node monitoring parameter set, querying a node historical parameter group set of a node to be monitored, calculating parameter richness of the node historical parameter group, obtaining an effective historical parameter group based on the parameter richness, obtaining a node failure rate based on the effective historical parameter group set and the node monitoring parameter group set, and drawing a parameter change curve graph based on the node monitoring parameter group set. And marking the parameter change curve graphs by utilizing the node fault rates to obtain fault change curve graphs, and summarizing the fault change curve graphs to obtain a fault change curve graph set. According to the invention, the intelligent degree of transformer area monitoring and the efficiency of transformer area power grid fault maintenance can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid parameter monitoring, and in particular to a method and system for visual intelligent monitoring of substations based on distribution network big data. Background Art

[0002] With the continuous expansion of the distribution network and the growing demand for electricity, the operation and management of the distribution network are facing increasingly higher requirements. The substation in the distribution network is a key link in power distribution and user access, and its operating status is directly related to the power supply quality and the user's power experience.

[0003] The current substation monitoring method is based on traditional sensor networks. This method deploys sensors at key nodes in the substation to collect parameters such as voltage, current, and power in real time, and transmits the data to the monitoring center for analysis through wired or wireless communications. However, this method lacks in-depth mining and utilization of historical data and cannot effectively evaluate the long-term change trend of parameters. Therefore, its intelligence needs to be improved. In addition, the fault analysis of this method is highly dependent on manual experience, which makes it difficult to quickly and accurately locate the faulty node, thereby reducing the efficiency of power grid fault maintenance. Summary of the invention

[0004] The present invention provides a method and system for visual intelligent monitoring of substations based on distribution network big data, the main purpose of which is to improve the intelligence level of substation monitoring and the efficiency of substation power grid fault maintenance.

[0005] To achieve the above-mentioned purpose, the present invention provides a visual intelligent monitoring method for substations based on distribution network big data, comprising: receiving a substation monitoring instruction, determining the substation to be monitored based on the substation monitoring instruction, and confirming a set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored; extracting the nodes to be monitored in turn in the set of nodes to be monitored, performing distribution network parameter monitoring on the nodes to be monitored, and obtaining a set of node monitoring parameter groups; querying the set of node historical parameter groups of the nodes to be monitored, extracting node historical parameter groups in turn in the set of node historical parameter groups, calculating the parameter richness of the node historical parameter groups, and judging whether the parameter richness is greater than a preset standard richness; if the parameter richness is not greater than the standard richness, performing parameter expansion on the node historical parameter group to obtain a valid historical parameter group; if the parameter richness is greater than the standard richness degree, then the node historical parameter group is recorded as a valid historical parameter group; the valid historical parameter groups are summarized to obtain a valid historical parameter group set, and node fault analysis is performed based on the valid historical parameter group set and the node monitoring parameter group set to obtain a node failure rate; a parameter change curve diagram is drawn based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameters in the node monitoring parameter group; the parameter change curve diagram is marked with the node failure rate to obtain a fault change curve diagram, the fault change curve diagram is summarized to obtain a fault change curve atlas set, and based on the fault change curve atlas set, visual intelligent monitoring of the substation based on distribution network big data is completed.

[0006] Optionally, the query of the node historical parameter set of the node to be monitored includes: obtaining a historical monitoring database of the node to be monitored, and determining a monitoring parameter category group of the node monitoring parameter set, wherein the historical monitoring database includes historical parameters and corresponding monitored times; extracting monitoring parameter categories in the monitoring parameter category group in sequence; recording the start monitoring time in the step of performing network parameter monitoring on the node to be monitored, and determining a historical data query period based on the start monitoring time and a preset data query duration, wherein the time length of the historical data query period is the data query duration; determining the total data duration of the monitoring parameter category in the historical monitoring database, and judging whether the total data duration is greater than the data query duration; if the total data duration is greater than the data query duration, querying the original historical parameters of the monitored time within the historical data query period in the historical monitoring database based on the monitoring parameter category to obtain an original historical parameter group; if the total data duration is not greater than the data query duration, extracting all original historical parameters belonging to the monitoring parameter category in the historical monitoring database to obtain an original historical parameter group; performing abnormal value replacement processing on the original historical parameter group to obtain a node historical parameter group, and summarizing the node historical parameter group to obtain a node historical parameter set.

[0007] Optionally, performing abnormal value replacement processing on the original historical parameter group to obtain the node historical parameter group includes: calculating the average historical parameter of the original historical parameter group; extracting original historical parameters in the original historical parameter group in sequence, and calculating parameter discrete values ​​of the original historical parameters and the average historical parameters, wherein the parameter discrete values ​​are expressed as: ,in, represents the discrete value of the parameter, represents the original historical parameters, represents the absolute value symbol, Represents an average historical parameter; if it is confirmed that the discrete value of the parameter is greater than the preset maximum discrete value, the original historical parameter is recorded as an abnormal historical parameter, and the abnormal monitoring time of the abnormal historical parameter is determined; based on the abnormal monitoring time and the preset central time, a replacement parameter period is determined in the original historical parameter group, wherein the abnormal monitoring time is the middle time of the replacement parameter period; a replacement historical parameter group included in the replacement parameter period is confirmed, and the abnormal monitoring time is removed from the replacement historical parameter group to obtain a decentralized parameter group, and the average replacement parameter of the decentralized parameter group is calculated; the average replacement parameters are summarized to obtain an average replacement parameter group, and the abnormal historical parameters in the original historical parameter group are replaced with the average replacement parameter group to obtain a node historical parameter group.

[0008] Optionally, the calculating parameter richness of the node historical parameter group includes: counting the number of historical parameters in the node historical parameter group, and calculating the skewness coefficient of the node historical parameter group based on the number of historical parameters using the following formula: ,in, represents the skewness coefficient, Indicates the number of historical parameters, Indicates the node in the historical parameter group. Node historical parameters, Represents the average value of the node's historical parameter group, Represents the standard deviation of the node historical parameter group; based on the skewness coefficient, the parameter richness is calculated using a preset richness calculation formula, wherein the richness calculation formula is expressed as: ,in, Indicates parameter richness, Represents the sum of all node historical parameters in the node historical parameter group. Indicates the node in the historical parameter group. Node historical parameters, Represents the base 10 logarithmic function.

[0009] Optionally, the parameter expansion of the node historical parameter group to obtain a valid historical parameter group includes: calculating the standard parameter quantity of the node historical parameter group based on the richness calculation formula and the standard richness; calculating the standard parameter quantity and the to-be-supplemented quantity of the historical parameter quantity, wherein the to-be-supplemented quantity is the absolute difference between the standard parameter quantity and the historical parameter quantity; obtaining the parameter transition value group and the transition value quantity of the node historical parameter group, and judging whether the transition value quantity is greater than the to-be-supplemented quantity, wherein the parameter transition value group includes a plurality of parameter transition values, and the parameter transition value is the slope between two adjacent node historical parameters in the node historical parameter group; if the transition value quantity is greater than the to-be-supplemented quantity, the parameter transition value group is recorded as the to-be-supplemented transition value group, and the node historical parameter group is expanded based on the to-be-supplemented transition value group. The method further comprises the following steps: performing supplementation to obtain a supplemented historical parameter group; counting the number of supplemented parameters in the supplemented historical parameter group; recording the supplemented historical parameter group and the number of supplemented parameters as the node historical parameter group and the number of historical parameters respectively, and returning to the step of calculating the number of standard parameters and the number of historical parameters to be supplemented until the number of transition values ​​is not greater than the number to be supplemented; if the number of transition values ​​is not greater than the number to be supplemented, calculating the supplemented number difference between the number to be supplemented and the number of transition values, and based on the supplemented number difference, identifying a completely supplemented transition value group in the parameter transition value group, wherein the completely supplemented transition value group is composed of multiple parameter transition values ​​with the smallest values ​​in the parameter transition value group, and the number of completely supplemented transition values ​​is equal to the supplemented number difference; based on the completely supplemented transition value group, supplementing the node historical parameter group to obtain a valid historical parameter group.

[0010] Optionally, the obtaining of the parameter transition value group and the number of transition values ​​of the node historical parameter group includes: extracting the node historical parameters in the node historical parameter group in sequence, extracting the subsequent neighboring historical parameters of the node historical parameters, and calculating the parameter transition values ​​of the node historical parameters and the subsequent neighboring historical parameters, wherein the parameter transition values ​​are expressed as: ,in, represents the parameter transition value, Represents the node's historical parameters, represents the subsequent neighbor history parameter, Indicates the time when the node's historical parameters are monitored, Indicates the monitored time of the subsequent historical parameter; summarizes the parameter transition values ​​to obtain a parameter transition value group, and counts the number of transition values ​​in the parameter transition value group, wherein the number of transition values ​​refers to the number of parameter transition values ​​in the parameter transition value group.

[0011] Optionally, based on the transition value group to be supplemented, the node historical parameter group is supplemented to obtain a supplemented historical parameter group, including: extracting the transition values ​​to be supplemented in the transition value group to be supplemented in sequence, and determining an adjacent historical parameter group based on the transition value to be supplemented, wherein the adjacent historical parameter group includes: a first adjacent historical parameter and a second adjacent historical parameter, and the first adjacent historical parameter and the second adjacent historical parameter are respectively the node historical parameter and the subsequent adjacent historical parameter corresponding to the parameter transition value; calculating the average adjacent parameter of the first adjacent historical parameter and the second adjacent historical parameter, and inserting the average adjacent parameter into the adjacent historical parameter group to obtain a supplemented adjacent parameter group, wherein the insertion position of the average adjacent parameter is located between the first adjacent historical parameter and the second adjacent historical parameter; merging the supplemented adjacent parameter groups to obtain a supplemented historical parameter group.

[0012] Optionally, the node failure analysis is performed based on the valid historical parameter group set and the node monitoring parameter group set to obtain the node failure rate, including: extracting valid historical parameter groups in sequence from the valid historical parameter group set, and extracting valid monitoring parameter groups corresponding to the valid historical parameter groups from the node monitoring parameter group set; using the valid historical parameter groups to machine train the pre-acquired LSTM model to obtain a parameter fault identification model; inputting the valid monitoring parameter group into the parameter fault identification model to obtain a unit failure rate; summarizing the unit failure rates to obtain a unit failure rate set; if the unit failure rate set contains a unit failure rate greater than a preset maximum failure rate, the node failure rate is recorded as 100%; if the unit failure rate set does not contain a unit failure rate greater than the maximum failure rate, the node failure rate is calculated based on the preset parameter category weight group and the unit failure rate set.

[0013] Optionally, the calculating the node failure rate based on the preset parameter category weight group and the unit failure rate set includes: calculating the node failure rate using the following formula: ,in, represents the node failure rate, represents the number of parameter class weights in the parameter class weight group or the number of unit failure rates in the unit failure rate set, Represents the first parameter in the weight group parameter class weights, Indicates the unit failure rate concentration Unit failure rate.

[0014] To achieve the above-mentioned purpose, the present invention also provides a visual intelligent monitoring system for substations based on distribution network big data, including: a node parameter monitoring module, which is used to receive substation monitoring instructions, determine the substation to be monitored based on the substation monitoring instructions, and confirm the set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored, and the nodes to be monitored are extracted in turn from the set of nodes to be monitored, and distribution network parameters are monitored on the nodes to be monitored to obtain a node monitoring parameter group set; a historical parameter query module, which is used to query the node historical parameter group set of the node to be monitored, extract the node historical parameter group in turn from the node historical parameter group set, calculate the parameter richness of the node historical parameter group, and determine whether the parameter richness is greater than a preset standard richness. If the parameter richness is not greater than the standard richness, the node historical parameter group is parameter expanded to obtain a valid historical parameter group. If the parameter richness is greater than the standard richness, the node historical parameter group is recorded as a valid historical parameter group; a change curve drawing module is used to summarize the valid historical parameter group to obtain a valid historical parameter group set, and perform node fault analysis based on the valid historical parameter group set and the node monitoring parameter group set to obtain a node failure rate, and draw a parameter change curve diagram based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameters in the node monitoring parameter group; a node fault marking module is used to mark the parameter change curve diagram with the node failure rate to obtain a fault change curve diagram, summarize the fault change curve diagram, and obtain a fault change curve diagram set.

[0015] In order to solve the above problems, the present invention also provides an electronic device, which includes: a memory storing at least one instruction; a processor executing the instructions stored in the memory to implement the above-mentioned visual intelligent monitoring method of substations based on distribution network big data.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned visual intelligent monitoring method of substations based on distribution network big data.

[0017] In order to solve the problems described in the background technology, the present invention first monitors the distribution network parameters of the monitored nodes to obtain the node monitoring parameter set. This step obtains the real-time monitoring data of the monitored nodes, providing sufficient basis for subsequent analysis. Then, the node historical parameter set of the monitored nodes is queried, and the parameter richness of the node historical parameter set is calculated. By calculating the parameter richness, the integrity and reliability of the historical parameter set can be evaluated to ensure that the subsequent analysis is based on high-quality data. Further, it is determined whether the parameter richness is greater than the standard richness. By determining whether the parameter richness meets the standard, valid historical data can be automatically screened out to avoid misjudgment caused by missing or incomplete data. For the node historical parameter set that does not meet the richness requirements, it can be expanded to obtain a valid historical parameter set. This step can improve the missing part of the node historical parameter set through parameter expansion, so that it meets the integrity and richness requirements required for analysis. Therefore, the expanded valid historical parameter set can more accurately reflect the historical operating status of the monitored nodes, and provide a more reliable data basis for fault analysis and trend prediction, thereby improving the accuracy of the overall fault analysis. Then, based on the valid historical parameter set and the node monitoring parameter set, node fault analysis is performed to obtain Node failure rate, this step combines historical data and real-time monitoring data for fault analysis, can more comprehensively evaluate the operating status of the node to be monitored, improve the accuracy of fault diagnosis, and by calculating the node failure rate, can discover potential fault risks in advance, and then can take timely measures to prevent and deal with them. In addition, the present invention also draws a parameter change curve based on the node monitoring parameter set. The parameter change curve in this step can intuitively display the changing trend of the monitoring parameters of the node to be monitored over time, which is convenient for operation and maintenance personnel to quickly understand the operating status of the equipment, and the parameter change curve can present complex data in a graphical manner, which is convenient for management personnel to perform visual management. Finally, the parameter change curve is marked with the node failure rate to obtain a fault change curve. By marking the failure rate on the parameter change curve, the time and location of the fault can be intuitively displayed, which improves the intelligent level of monitoring. At the same time, the fault change curve set summarizes the fault conditions of multiple nodes to be monitored, and can comprehensively display the fault distribution and trend of the entire monitored area, providing a reference for overall operation and maintenance, and by visually displaying fault information, it can help operation and maintenance personnel quickly formulate maintenance plans and resource allocation plans, thereby improving the efficiency of power grid fault maintenance. Therefore, the present invention can improve the intelligence level of substation monitoring and the efficiency of substation power grid fault maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flow chart of a method for visual intelligent monitoring of distribution areas based on distribution network big data provided by an embodiment of the present invention; Figure 2 A functional module diagram of a visual intelligent monitoring system for a substation based on distribution network big data provided by an embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the method for visual intelligent monitoring of substations based on distribution network big data provided by one embodiment of the present invention.

[0019] Explanation of the reference numerals: 1. electronic device; 10. processor; 11. memory; 12. bus.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides a visual intelligent monitoring method for a substation based on distribution network big data. The execution subject of the visual intelligent monitoring method for a substation based on distribution network big data includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the visual intelligent monitoring method for a substation based on distribution network big data can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1 As shown, it is a flow chart of a method for visual intelligent monitoring of a substation based on distribution network big data provided by an embodiment of the present invention. In this embodiment, the method for visual intelligent monitoring of a substation based on distribution network big data includes: S1, receiving a substation monitoring instruction, determining a substation to be monitored based on the substation monitoring instruction, and confirming a set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored.

[0024] It can be understood that the substation monitoring instruction refers to an instruction initiated manually to perform intelligent monitoring on a specific substation, the substation to be monitored refers to a specific substation included in the substation monitoring instruction, and the node set to be monitored refers to a collection of nodes to be monitored, wherein the node to be monitored refers to a point or equipment that needs to be specifically monitored in the substation to be monitored, and the specific location of the node set to be monitored is determined manually, wherein the nodes to be monitored include: distribution transformers, branch points and junction points in the line, electric meters at the user end, reactive compensation devices and switching equipment in the circuit, etc.

[0025] S2. Extract the nodes to be monitored from the set of nodes to be monitored in sequence, monitor the network distribution parameters of the nodes to be monitored, and obtain a node monitoring parameter set.

[0026] It can be understood that the distribution network parameter monitoring of the monitored node refers to monitoring various parameters in the monitored node according to a preset monitoring frequency and monitoring duration, wherein the category of the monitored parameter is determined manually, for example: monitoring the current and voltage in the monitored node, the monitoring frequency refers to the time interval between two parameter detections, the monitoring duration refers to the total duration of monitoring, and the node monitoring parameter group set refers to a set of multiple node monitoring parameter groups, wherein the parameter types represented by each node monitoring parameter group are different.

[0027] Exemplarily, when monitoring the configuration parameters of a node to be monitored, the current and voltage are monitored. Then, the node monitoring parameter group set at this time includes two node monitoring parameter groups, which respectively represent the current and voltage of the node to be monitored.

[0028] S3. Query the node historical parameter group set of the node to be monitored, extract the node historical parameter groups in the node historical parameter group set in sequence, calculate the parameter richness of the node historical parameter groups, and determine whether the parameter richness is greater than a preset standard richness.

[0029] It should be explained that the node historical parameter group set refers to a collection of multiple node historical parameter groups, wherein the node historical parameter group refers to a data combination of a parameter monitored by the node to be monitored in the historical period changing over time. It should be noted that the parameter types in the node historical parameter group set should match the parameter types in the node monitoring parameter group set. For example, when the node monitoring parameter group set includes monitoring parameter groups for current and voltage, the node historical parameter group set should also include historical parameter groups for current and voltage.

[0030] Furthermore, the parameter richness refers to the value of the parameter information richness represented by the node historical parameter group. The richer the parameter information represented by the node historical parameter group, the greater the parameter richness. The standard richness refers to the minimum value of the parameter richness set artificially that can be used for subsequent fault analysis.

[0031] It is clear that when performing node fault analysis based on the node historical parameter group set in the future, the parameter richness of each node historical parameter group in the node historical parameter group set is crucial. When the parameter richness of the node historical parameter group is not enough, that is, the parameter richness is not greater than the standard richness, it means that continuing to use the node historical parameter group at this time for fault analysis may cause the analysis results to deviate from the actual situation due to insufficient data richness. When the parameter richness of the node historical parameter group is sufficient, that is, the parameter richness is greater than the standard richness, it means that the node historical parameter group at this time can be used for subsequent fault analysis.

[0032] In detail, the query of the node historical parameter set of the node to be monitored includes: obtaining the historical monitoring database of the node to be monitored, and determining the monitoring parameter category group of the node monitoring parameter set, wherein the historical monitoring database includes historical parameters and corresponding monitored times; extracting the monitoring parameter categories in the monitoring parameter category group in sequence; recording the start monitoring time in the step of performing network distribution parameter monitoring on the node to be monitored, and determining the historical data query period based on the start monitoring time and the preset data query duration, wherein the time length of the historical data query period is the data query duration; determining the total data duration of the monitoring parameter category in the historical monitoring database, and judging whether the total data duration is greater than the data query duration; if the total data duration is greater than the data query duration, querying the original historical parameters of the monitored time within the historical data query period in the historical monitoring database based on the monitoring parameter category to obtain the original historical parameter group; if the total data duration is not greater than the data query duration, extracting all the original historical parameters belonging to the monitoring parameter category in the historical monitoring database to obtain the original historical parameter group; performing abnormal value replacement processing on the original historical parameter group to obtain the node historical parameter group, summarizing the node historical parameter group to obtain the node historical parameter set.

[0033] It is understandable that the historical monitoring database refers to a database of specific data of each parameter type monitored in the historical period. The database not only contains the specific values ​​of the parameters, but also records the time when each parameter is monitored. The monitoring parameter category group refers to the combination of parameter categories corresponding to each node monitoring parameter group in the node monitoring parameter group set, for example: the monitoring parameter category group is (current, voltage and power). The start monitoring time refers to the time when the monitoring starts when the distribution network parameter monitoring of the monitored node is carried out. The data query duration refers to the duration of the artificially set historical data query period, wherein the end time of the historical data query period is the start monitoring time, and its length is equal to the data query duration. It should be noted that the reason for setting the data query duration is that the environment when the data is monitored far away from the start monitoring time (that is, the time length from the start monitoring time is greater than the data query duration) has a certain deviation from the current environment, so the data far away from the start monitoring time does not have a reference function for the current node.

[0034] It can be understood that the total data duration refers to the span of the parameters contained in the monitoring parameter category in the historical monitoring database at the monitored time, and the original historical parameters refer to the historical parameters at the monitored time within the historical data query period. The abnormal value replacement process refers to identifying abnormal values ​​in the original historical parameter group and replacing the abnormal values ​​with normal values. The specific process of this step will be given later.

[0035] In detail, the abnormal value replacement process is performed on the original historical parameter group to obtain the node historical parameter group, including: calculating the average historical parameter of the original historical parameter group; extracting the original historical parameters in the original historical parameter group in sequence, and calculating the parameter discrete value of the original historical parameter and the average historical parameter, wherein the parameter discrete value is expressed as: ,in, represents the discrete value of the parameter, represents the original historical parameters, represents the absolute value symbol, Represents an average historical parameter; if it is confirmed that the discrete value of the parameter is greater than the preset maximum discrete value, the original historical parameter is recorded as an abnormal historical parameter, and the abnormal monitoring time of the abnormal historical parameter is determined; based on the abnormal monitoring time and the preset central time, a replacement parameter period is determined in the original historical parameter group, wherein the abnormal monitoring time is the middle time of the replacement parameter period; a replacement historical parameter group included in the replacement parameter period is confirmed, and the abnormal monitoring time is removed from the replacement historical parameter group to obtain a decentralized parameter group, and the average replacement parameter of the decentralized parameter group is calculated; the average replacement parameters are summarized to obtain an average replacement parameter group, and the abnormal historical parameters in the original historical parameter group are replaced with the average replacement parameter group to obtain a node historical parameter group.

[0036] It should be explained that the average historical parameter refers to the average value of all original historical parameters in the original historical parameter group. The parameter discrete value refers to the numerical difference between the original historical parameter and the average historical parameter. The larger the numerical difference between the original historical parameter and the average historical parameter, the larger the parameter discrete value. The maximum discrete value refers to the maximum value of the parameter discrete value set manually. The abnormal monitoring time refers to the monitored time of the abnormal historical parameter. The center duration refers to the manually set duration, which is used to determine the length of the replacement parameter period, wherein the replacement parameter period refers to a time period whose length is the center duration and the center is the abnormal monitoring time. The replacement historical parameter refers to the original historical parameter in the replacement parameter period at the monitored time in the original historical parameter group, the decentralized parameter group refers to the historical parameter group after the abnormal monitoring time is eliminated, and the average replacement parameter refers to the average value of all decentralized parameters in the decentralized parameter group. The use of the average replacement parameter group to replace the abnormal historical parameters in the original historical parameter group refers to: replacing the corresponding abnormal historical parameters in the original historical parameter group with the average replacement parameters in the average replacement parameter group, and when all the average replacement parameters in the average replacement parameter group are replaced, the original historical parameter group after replacement is recorded as the node historical parameter group.

[0037] In detail, the parameter richness of the node historical parameter group is calculated, including: counting the number of historical parameters in the node historical parameter group, and calculating the skewness coefficient of the node historical parameter group based on the number of historical parameters using the following formula: ,in, represents the skewness coefficient, Indicates the number of historical parameters, Indicates the node in the historical parameter group. Node historical parameters, Represents the average value of the node's historical parameter group, Represents the standard deviation of the node historical parameter group; based on the skewness coefficient, the parameter richness is calculated using a preset richness calculation formula, wherein the richness calculation formula is expressed as: ,in, Indicates parameter richness, Represents the sum of all node historical parameters in the node historical parameter group. Indicates the node in the historical parameter group. Node historical parameters, Represents the base 10 logarithmic function.

[0038] It is understandable that the number of historical parameters refers to the number of node historical parameters in the node historical parameter group. The skewness coefficient refers to a value used to represent the symmetry of parameter distribution in the node historical parameter group. The more symmetrical the parameter distribution in the node historical parameter group, the smaller the skewness coefficient.

[0039] S4. If the parameter richness is not greater than the standard richness, the node historical parameter group is expanded to obtain a valid historical parameter group.

[0040] It should be explained that the effective historical parameter group refers to the node historical parameter group after parameter expansion.

[0041] In detail, the parameter expansion of the node historical parameter group to obtain a valid historical parameter group includes: calculating the standard parameter quantity of the node historical parameter group based on the richness calculation formula and the standard richness; calculating the standard parameter quantity and the to-be-supplemented quantity of the historical parameter quantity, wherein the to-be-supplemented quantity is the absolute difference between the standard parameter quantity and the historical parameter quantity; obtaining the parameter transition value group and the transition value quantity of the node historical parameter group, and judging whether the transition value quantity is greater than the to-be-supplemented quantity, wherein the parameter transition value group includes multiple parameter transition values, and the parameter transition value is the slope between two adjacent node historical parameters in the node historical parameter group; if the transition value quantity is greater than the to-be-supplemented quantity, the parameter transition value group is recorded as the to-be-supplemented transition value group, and the node historical parameter group is expanded based on the to-be-supplemented transition value group. The method further comprises the following steps: performing supplementation to obtain a supplemented historical parameter group; counting the number of supplemented parameters in the supplemented historical parameter group; recording the supplemented historical parameter group and the number of supplemented parameters as the node historical parameter group and the number of historical parameters respectively, and returning to the step of calculating the number of standard parameters and the number of historical parameters to be supplemented until the number of transition values ​​is not greater than the number to be supplemented; if the number of transition values ​​is not greater than the number to be supplemented, calculating the supplemented number difference between the number to be supplemented and the number of transition values, and based on the supplemented number difference, identifying a completely supplemented transition value group in the parameter transition value group, wherein the completely supplemented transition value group is composed of multiple parameter transition values ​​with the smallest values ​​in the parameter transition value group, and the number of completely supplemented transition values ​​is equal to the supplemented number difference; based on the completely supplemented transition value group, supplementing the node historical parameter group to obtain a valid historical parameter group.

[0042] It can be understood that the standard number of parameters refers to the number of parameters that the node historical parameter group should have under the standard richness, and the detailed steps for calculating the standard number of parameters of the node historical parameter group are: replace the unknown number-parameter richness in the richness calculation formula with the known number-standard richness, and replace the known number-historical parameter number with the unknown number-standard parameter number, and then the standard parameter number can be calculated through the replaced richness calculation formula. The step of supplementing the node historical parameter group based on the fully supplemented transition value group is the same as the step of supplementing the node historical parameter group based on the transition value group to be supplemented, and the detailed steps of supplementing the node historical parameter group based on the transition value group to be supplemented will be given later and will not be repeated here.

[0043] It should be explained that the number to be supplemented refers to the difference between the number of standard parameters and the number of historical parameters, the parameter transition value refers to the slope between two adjacent node historical parameters in the node historical parameter group at the monitored time, and the transition value number refers to the number of parameter transition values ​​in the parameter transition value group. The supplementary parameter number refers to the number of supplementary historical parameters in the supplementary historical parameter group, and the supplementary quantity difference refers to the difference between the number to be supplemented and the transition value number.

[0044] In detail, the obtaining of the parameter transition value group and the number of transition values ​​of the node historical parameter group includes: extracting the node historical parameters in the node historical parameter group in sequence, extracting the subsequent neighboring historical parameters of the node historical parameters, and calculating the parameter transition values ​​of the node historical parameters and the subsequent neighboring historical parameters, wherein the parameter transition values ​​are expressed as: ,in, represents the parameter transition value, Represents the node's historical parameters, represents the subsequent neighbor history parameter, Indicates the time when the node's historical parameters are monitored, Indicates the monitored time of the subsequent historical parameter; summarizes the parameter transition values ​​to obtain a parameter transition value group, and counts the number of transition values ​​in the parameter transition value group, wherein the number of transition values ​​refers to the number of parameter transition values ​​in the parameter transition value group.

[0045] It can be understood that the subsequent neighbor historical parameter refers to a node historical parameter whose monitored time is after the monitored time of the node historical parameter and is adjacent to the monitored time.

[0046] In detail, based on the transition value group to be supplemented, the node historical parameter group is supplemented to obtain a supplemented historical parameter group, including: extracting the transition values ​​to be supplemented in the transition value group to be supplemented in sequence, and determining the adjacent historical parameter group based on the transition value to be supplemented, wherein the adjacent historical parameter group includes: a first adjacent historical parameter and a second adjacent historical parameter, and the first adjacent historical parameter and the second adjacent historical parameter are respectively the node historical parameter and the subsequent adjacent historical parameter corresponding to the parameter transition value; calculating the average adjacent parameter of the first adjacent historical parameter and the second adjacent historical parameter, and inserting the average adjacent parameter into the adjacent historical parameter group to obtain a supplemented adjacent parameter group, wherein the insertion position of the average adjacent parameter is located between the first adjacent historical parameter and the second adjacent historical parameter; merging the supplemented adjacent parameter groups to obtain a supplemented historical parameter group.

[0047] It is understandable that the adjacent historical parameter group refers to the combination of two historical parameters corresponding to the transition value to be supplemented, and the average adjacent parameter refers to the average value of the first adjacent historical parameter and the second adjacent historical parameter. It should be noted that when the average adjacent parameter is inserted into the adjacent historical parameter group, the monitored time corresponding to the average adjacent parameter should also be defined, and the middle time between the monitored time of the first adjacent historical parameter and the monitored time of the second adjacent historical parameter can be selected as the monitored time corresponding to the average adjacent parameter. The supplemented adjacent parameter group refers to the adjacent historical parameter group after the average adjacent parameter is inserted.

[0048] For example, a certain adjacent historical parameter group is: (100A 110A), then the first adjacent historical parameter and the second adjacent historical parameter are 100A and 110A respectively, then their average adjacent parameter is: 105A, and then 105A is inserted into the middle position between the first adjacent historical parameter and the second adjacent historical parameter to obtain the supplementary adjacent parameter group: (100A 105A 110A).

[0049] S5. If the parameter richness is greater than the standard richness, the node historical parameter group is recorded as a valid historical parameter group.

[0050] It can be understood that when the parameter richness is greater than the standard richness, it means that the parameter richness of the node historical parameter group at this time is sufficient and it can be used as a valid historical parameter group.

[0051] S6. Summarize the valid historical parameter groups to obtain a valid historical parameter set, perform node failure analysis based on the valid historical parameter set and the node monitoring parameter set, and obtain a node failure rate.

[0052] It is understandable that the valid historical parameter set refers to a collection of valid historical parameter sets. The node failure rate refers to the probability of a failure of a node to be monitored. The higher the probability of a failure of a node to be monitored, the greater the node failure rate.

[0053] In detail, the node failure analysis is performed based on the valid historical parameter group set and the node monitoring parameter group set to obtain the node failure rate, including: extracting the valid historical parameter groups in sequence from the valid historical parameter group set, and extracting the valid monitoring parameter groups corresponding to the valid historical parameter groups from the node monitoring parameter group set; using the valid historical parameter groups to perform machine training on the pre-acquired LSTM model to obtain a parameter fault identification model; inputting the valid monitoring parameter group into the parameter fault identification model to obtain the unit failure rate; summarizing the unit failure rates to obtain a unit failure rate set; if the unit failure rate set contains a unit failure rate greater than a preset maximum failure rate, the node failure rate is recorded as 100%; if the unit failure rate set does not contain a unit failure rate greater than the maximum failure rate, the node failure rate is calculated based on the preset parameter category weight group and the unit failure rate set.

[0054] It should be explained that the effective monitoring parameter group refers to a node monitoring parameter group with the same monitoring parameter category as the effective historical parameter group in the node monitoring parameter group set. The LSTM model refers to a deep learning model that can process time series data, and the parameter fault identification model refers to an LSTM model after training with the effective historical parameter group. The unit failure rate refers to the output of the parameter fault identification model after the effective monitoring parameter group is input into the parameter fault identification model, and the unit failure rate set refers to the set of unit failure rates. The maximum failure rate refers to the maximum value of the unit failure rate set manually. When there is a unit failure rate greater than the maximum failure rate in the unit failure rate set, it can be artificially assumed that the node to be monitored is very likely to have a failure at this time, that is, the node failure rate is recorded as 100% at this time. When all unit failure rates in the unit failure rate set are not greater than the unit failure rate, it is necessary to combine the unit failure rate set and the parameters corresponding to these unit failure rates to comprehensively analyze the failure rate of the node to be monitored to obtain the node failure rate. The parameter category weight group refers to the combination of weights calculated for each monitoring parameter category in the manually set monitoring parameter category group when calculating the node failure rate.

[0055] Furthermore, the parameter category weight group is set manually according to the different degrees of influence of different monitoring parameter categories on the current monitored node. For example, Xiao Zhang is a maintenance personnel of a power grid fault. After analyzing the historical data of a certain monitored node of the power grid, Xiao Zhang found that the number of failures of the monitored node due to abnormal current was 10 times, and the number of failures due to abnormal voltage was 6 times. Xiao Zhang can think that compared with voltage, the current has a greater weight on whether the monitored node fails. Therefore, Xiao Zhang sets the weight of current to 0.6 and the weight of voltage to 0.4, that is, the parameter category weight group at this time is (0.6 0.4).

[0056] In detail, the node failure rate is calculated based on the preset parameter category weight group and unit failure rate set, including: calculating the node failure rate using the following formula: ,in, represents the node failure rate, represents the number of parameter class weights in the parameter class weight group or the number of unit failure rates in the unit failure rate set, Represents the first parameter in the weight group parameter class weights, Indicates the unit failure rate concentration Unit failure rate.

[0057] S7. Draw a parameter change curve diagram based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, and the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameters in the node monitoring parameter group.

[0058] It needs to be explained that the detailed steps of drawing the parameter change curve diagram based on the node monitoring parameter group set are: extracting the node monitoring parameter groups in the node monitoring parameter group set in turn, and drawing the parameter change curve based on the node monitoring parameter groups, wherein the horizontal axis of the parameter change curve represents the moment when the node monitoring parameters in the node monitoring parameter group are monitored, and the vertical axis represents the specific value of the node monitoring parameters in the node monitoring parameter group, summarizing the parameter change curves to obtain a parameter change curve set, and setting the parameter change curves in the parameter change curve set to share a common time horizontal axis, thereby obtaining a parameter change curve diagram.

[0059] S8. Use the node failure rate to mark the parameter change curve graph to obtain a fault change curve graph, summarize the fault change curve graph to obtain a fault change curve atlas, and complete the visual intelligent monitoring of the substation based on the distribution network big data based on the fault change curve atlas.

[0060] It is understandable that the use of node failure rate to mark the parameter change curve graph refers to marking the specific value of the node failure rate in the parameter change curve graph. The fault change curve graph set refers to a collection of fault change curve graphs of each node to be monitored in the monitored substation. Through the fault change curve graph set, relevant power grid fault maintenance personnel can timely view the real-time changes of different parameters in different nodes to be monitored, and according to the node failure rate in the fault change curve graph, timely discover and prevent possible faults in the nodes to be monitored.

[0061] In order to solve the problems described in the background technology, the present invention first monitors the distribution network parameters of the monitored nodes to obtain the node monitoring parameter set. This step obtains the real-time monitoring data of the monitored nodes, providing sufficient basis for subsequent analysis. Then, the node historical parameter set of the monitored nodes is queried, and the parameter richness of the node historical parameter set is calculated. By calculating the parameter richness, the integrity and reliability of the historical parameter set can be evaluated to ensure that the subsequent analysis is based on high-quality data. Further, it is determined whether the parameter richness is greater than the standard richness. By determining whether the parameter richness meets the standard, valid historical data can be automatically screened out to avoid misjudgment caused by missing or incomplete data. For the node historical parameter set that does not meet the richness requirements, it can be expanded to obtain a valid historical parameter set. This step can improve the missing part of the node historical parameter set through parameter expansion, so that it meets the integrity and richness requirements required for analysis. Therefore, the expanded valid historical parameter set can more accurately reflect the historical operating status of the monitored nodes, and provide a more reliable data basis for fault analysis and trend prediction, thereby improving the accuracy of the overall fault analysis. Then, based on the valid historical parameter set and the node monitoring parameter set, node fault analysis is performed to obtain Node failure rate, this step combines historical data and real-time monitoring data for fault analysis, can more comprehensively evaluate the operating status of the node to be monitored, improve the accuracy of fault diagnosis, and by calculating the node failure rate, can discover potential fault risks in advance, and then can take timely measures to prevent and deal with them. In addition, the present invention also draws a parameter change curve based on the node monitoring parameter set. The parameter change curve in this step can intuitively display the changing trend of the monitoring parameters of the node to be monitored over time, which is convenient for operation and maintenance personnel to quickly understand the operating status of the equipment, and the parameter change curve can present complex data in a graphical manner, which is convenient for management personnel to perform visual management. Finally, the parameter change curve is marked with the node failure rate to obtain a fault change curve. By marking the failure rate on the parameter change curve, the time and location of the fault can be intuitively displayed, which improves the intelligent level of monitoring. At the same time, the fault change curve set summarizes the fault conditions of multiple nodes to be monitored, and can comprehensively display the fault distribution and trend of the entire monitored area, providing a reference for overall operation and maintenance, and by visually displaying fault information, it can help operation and maintenance personnel quickly formulate maintenance plans and resource allocation plans, thereby improving the efficiency of power grid fault maintenance. Therefore, the present invention can improve the intelligence level of substation monitoring and the efficiency of substation power grid fault maintenance.

[0062] like Figure 2 The figure shows a functional module diagram of a substation visual intelligent monitoring system based on distribution network big data provided by an embodiment of the present invention.

[0063] The visual intelligent monitoring system 100 for substations based on distribution network big data of the present invention can be installed in an electronic device. According to the functions implemented, the visual intelligent monitoring system 100 for substations based on distribution network big data can include a node parameter monitoring module 101, a historical parameter query module 102, a change curve drawing module 103 and a node fault marking module 104. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0064] The node parameter monitoring module 101 is used to receive a substation area monitoring instruction, determine the substation area to be monitored based on the substation area monitoring instruction, and confirm the set of nodes to be monitored in the substation area to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored, and the nodes to be monitored are extracted in turn from the set of nodes to be monitored, and the distribution network parameters of the nodes to be monitored are monitored to obtain a node monitoring parameter group set; the historical parameter query module 102 is used to query the node historical parameter group set of the node to be monitored, extract the node historical parameter group in turn from the node historical parameter group set, calculate the parameter richness of the node historical parameter group, and determine whether the parameter richness is greater than a preset standard richness. If the parameter richness is not greater than the standard richness, the node historical parameter group is parameter expanded to obtain a valid historical parameter group. If the parameter richness is greater than the standard richness, The node historical parameter group is recorded as a valid historical parameter group; the change curve drawing module 103 is used to summarize the valid historical parameter group to obtain a valid historical parameter group set, perform node fault analysis based on the valid historical parameter group set and the node monitoring parameter group set to obtain a node failure rate, and draw a parameter change curve diagram based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameter in the node monitoring parameter group; the node fault marking module 104 is used to mark the parameter change curve diagram with the node failure rate to obtain a fault change curve diagram, summarize the fault change curve diagram, and obtain a fault change curve diagram set.

[0065] In detail, each module in the distribution network big data based visual intelligent monitoring system 100 of the substation area in the embodiment of the present invention is used in the same manner as described above. Figure 1 The technical means are the same as the method for visual intelligent monitoring of substations based on distribution network big data described in , and can produce the same technical effects, so they will not be repeated here.

[0066] like Figure 3, is a schematic diagram of the structure of an electronic device for implementing a method for visual intelligent monitoring of substations based on distribution network big data provided by an embodiment of the present invention.

[0067] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a visual intelligent monitoring method program for substations based on distribution network big data.

[0068] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the program of the visual intelligent monitoring method of the substation based on the distribution network big data, but also can be used to temporarily store the data that has been output or is to be output.

[0069] The processor 10 may be composed of an integrated circuit in some embodiments, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and a combination of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a visual intelligent monitoring method program for a substation based on distribution network big data, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0070] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0071] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0072] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0073] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0074] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0075] The program of the visual intelligent monitoring method for the substation based on the distribution network big data stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: receiving the substation monitoring instruction, determining the substation to be monitored based on the substation monitoring instruction, and confirming the set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored; extracting the nodes to be monitored in turn from the set of nodes to be monitored, performing distribution network parameter monitoring on the nodes to be monitored, and obtaining a set of node monitoring parameter groups; querying the node historical parameter group set of the node to be monitored, extracting the node historical parameter groups in turn from the node historical parameter group set, calculating the parameter richness of the node historical parameter group, and judging whether the parameter richness is greater than the preset standard richness; if the parameter richness is not greater than the standard richness, performing parameter expansion on the node historical parameter group to obtain a valid historical parameter group; If the parameter richness is greater than the standard richness, the node historical parameter group is recorded as a valid historical parameter group; the valid historical parameter groups are summarized to obtain a valid historical parameter group set, and node fault analysis is performed based on the valid historical parameter group set and the node monitoring parameter group set to obtain a node failure rate; a parameter change curve diagram is drawn based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameters in the node monitoring parameter group; the parameter change curve diagram is marked with the node failure rate to obtain a fault change curve diagram, the fault change curve diagram is summarized to obtain a fault change curve atlas, and based on the fault change curve atlas, visual intelligent monitoring of the substation based on distribution network big data is completed.

[0076] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0077] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0078] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor of an electronic device, it can achieve: receiving a substation monitoring instruction, determining a substation to be monitored based on the substation monitoring instruction, and confirming a set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored; extracting the nodes to be monitored in turn from the set of nodes to be monitored, performing network distribution parameter monitoring on the nodes to be monitored, and obtaining a set of node monitoring parameter groups; querying the node historical parameter group set of the node to be monitored, extracting the node historical parameter groups in turn from the set of node historical parameter groups, calculating the parameter richness of the node historical parameter groups, and judging whether the parameter richness is greater than a preset standard richness; if the parameter richness is not greater than the standard richness, performing parameter expansion on the node historical parameter group to obtain a valid historical parameter group; if the If the parameter richness is greater than the standard richness, the node historical parameter group is recorded as a valid historical parameter group; the valid historical parameter groups are summarized to obtain a valid historical parameter group set, and node fault analysis is performed based on the valid historical parameter group set and the node monitoring parameter group set to obtain a node failure rate; a parameter change curve diagram is drawn based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameters in the node monitoring parameter group; the parameter change curve diagram is marked with the node failure rate to obtain a fault change curve diagram, the fault change curve diagram is summarized to obtain a fault change curve atlas, and based on the fault change curve atlas, the visual intelligent monitoring of the substation based on the distribution network big data is completed.

[0079] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0080] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0081] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0082] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0083] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution 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 solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A visual intelligent monitoring method for distribution area based on distribution network big data, characterized in that: The method includes: receiving a substation monitoring instruction, determining a substation to be monitored based on the substation monitoring instruction, and confirming a set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored; extracting the nodes to be monitored in turn from the set of nodes to be monitored, performing network distribution parameter monitoring on the nodes to be monitored, and obtaining a set of node monitoring parameter groups; querying a set of node historical parameter groups of the nodes to be monitored, extracting node historical parameter groups in turn from the set of node historical parameter groups, calculating parameter richness of the node historical parameter groups, and judging whether the parameter richness is greater than a preset standard richness; if the parameter richness is not greater than the standard richness, performing parameter expansion on the node historical parameter group to obtain a valid historical parameter group; if the parameter richness is greater than the standard richness, recording the node historical parameter group as having effective historical parameter group; summarizing the effective historical parameter groups to obtain an effective historical parameter group set, performing node fault analysis based on the effective historical parameter group set and the node monitoring parameter group set to obtain a node failure rate; drawing a parameter change curve diagram based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameters in the node monitoring parameter group; marking the parameter change curve diagram with the node failure rate to obtain a fault change curve diagram, summarizing the fault change curve diagram to obtain a fault change curve atlas, and completing the visual intelligent monitoring of the substation based on the distribution network big data based on the fault change curve atlas.

2. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 1, characterized in that: The query of the node historical parameter set of the node to be monitored includes: obtaining the historical monitoring database of the node to be monitored, and determining the monitoring parameter category group of the node monitoring parameter set, wherein the historical monitoring database includes historical parameters and corresponding monitored moments; extracting the monitoring parameter categories in the monitoring parameter category group in sequence; recording the start monitoring moment in the step of performing network distribution parameter monitoring on the node to be monitored, and determining the historical data query period based on the start monitoring moment and the preset data query duration, wherein the time length of the historical data query period is the data query duration; determining the total data duration of the monitoring parameter category in the historical monitoring database, and judging whether the total data duration is greater than the data query duration; if the total data duration is greater than the data query duration, querying the original historical parameters of the monitored moment within the historical data query period in the historical monitoring database based on the monitoring parameter category to obtain the original historical parameter group; if the total data duration is not greater than the data query duration, extracting all the original historical parameters belonging to the monitoring parameter category in the historical monitoring database to obtain the original historical parameter group; performing abnormal value replacement processing on the original historical parameter group to obtain the node historical parameter group, and summarizing the node historical parameter group to obtain the node historical parameter set.

3. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 2, characterized in that: The abnormal value replacement process is performed on the original historical parameter group to obtain the node historical parameter group, including: calculating the average historical parameter of the original historical parameter group; extracting the original historical parameters in the original historical parameter group in sequence, and calculating the parameter discrete value of the original historical parameter and the average historical parameter, wherein the parameter discrete value is expressed as: ,in, represents the discrete value of the parameter, represents the original historical parameters, represents the absolute value symbol, Represents an average historical parameter; if it is confirmed that the discrete value of the parameter is greater than the preset maximum discrete value, the original historical parameter is recorded as an abnormal historical parameter, and the abnormal monitoring time of the abnormal historical parameter is determined; based on the abnormal monitoring time and the preset central time, a replacement parameter period is determined in the original historical parameter group, wherein the abnormal monitoring time is the middle time of the replacement parameter period; a replacement historical parameter group included in the replacement parameter period is confirmed, and the abnormal monitoring time is removed from the replacement historical parameter group to obtain a decentralized parameter group, and the average replacement parameter of the decentralized parameter group is calculated; the average replacement parameters are summarized to obtain an average replacement parameter group, and the abnormal historical parameters in the original historical parameter group are replaced with the average replacement parameter group to obtain a node historical parameter group.

4. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 3 is characterized in that: The parameter richness of the node historical parameter group is calculated, including: counting the number of historical parameters in the node historical parameter group, and calculating the skewness coefficient of the node historical parameter group based on the number of historical parameters using the following formula: ,in, represents the skewness coefficient, Indicates the number of historical parameters, Indicates the node in the historical parameter group. Node historical parameters, Represents the average value of the node's historical parameter group, Represents the standard deviation of the node historical parameter group; based on the skewness coefficient, the parameter richness is calculated using a preset richness calculation formula, wherein the richness calculation formula is expressed as: ,in, Indicates parameter richness, Represents the sum of all node historical parameters in the node historical parameter group. Indicates the node in the historical parameter group. Node historical parameters, Represents the base 10 logarithmic function.

5. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 4, characterized in that: The method of performing parameter expansion on the node historical parameter group to obtain a valid historical parameter group includes: calculating the standard parameter quantity of the node historical parameter group based on a richness calculation formula and a standard richness; calculating the to-be-supplemented quantity of the standard parameter quantity and the historical parameter quantity, wherein the to-be-supplemented quantity is the absolute difference between the standard parameter quantity and the historical parameter quantity; obtaining a parameter transition value group and a transition value quantity of the node historical parameter group, and determining whether the transition value quantity is greater than the to-be-supplemented quantity, wherein the parameter transition value group includes a plurality of parameter transition values, and the parameter transition value is the slope between two adjacent node historical parameters in the node historical parameter group; if the transition value quantity is greater than the to-be-supplemented quantity, the parameter transition value group is recorded as a to-be-supplemented transition value group, and the node historical parameter group is supplemented based on the to-be-supplemented transition value group. Supplement to obtain a supplementary historical parameter group; count the number of supplementary parameters in the supplementary historical parameter group; record the supplementary historical parameter group and the number of supplementary parameters as the node historical parameter group and the number of historical parameters respectively, and return to the step of calculating the number of standard parameters and the number of historical parameters to be supplemented until the number of transition values ​​is not greater than the number to be supplemented; if the number of transition values ​​is not greater than the number to be supplemented, calculate the supplementary quantity difference between the number to be supplemented and the number of transition values, and based on the supplementary quantity difference, identify a complete supplementary transition value group in the parameter transition value group, wherein the complete supplementary transition value group is composed of multiple parameter transition values ​​with the smallest values ​​in the parameter transition value group, and the number of complete supplementary transition values ​​is equal to the supplementary quantity difference; based on the complete supplementary transition value group, supplement the node historical parameter group to obtain a valid historical parameter group.

6. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 5, characterized in that: The obtaining of the parameter transition value group and the number of transition values ​​of the node historical parameter group includes: extracting the node historical parameters in sequence from the node historical parameter group, extracting the subsequent neighboring historical parameters of the node historical parameters, and calculating the parameter transition values ​​of the node historical parameters and the subsequent neighboring historical parameters, wherein the parameter transition values ​​are expressed as: ,in, represents the parameter transition value, Represents the node's historical parameters, represents the subsequent neighbor history parameter, Indicates the time when the node's historical parameters are monitored, Indicates the monitored time of the subsequent historical parameter; summarizes the parameter transition values ​​to obtain a parameter transition value group, and counts the number of transition values ​​in the parameter transition value group, wherein the number of transition values ​​refers to the number of parameter transition values ​​in the parameter transition value group.

7. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 6, characterized in that: The method of supplementing the node historical parameter group based on the transition value group to be supplemented to obtain the supplemented historical parameter group includes: extracting the transition values ​​to be supplemented in sequence from the transition value group to be supplemented, and determining the adjacent historical parameter group based on the transition value to be supplemented, wherein the adjacent historical parameter group includes: a first adjacent historical parameter and a second adjacent historical parameter, and the first adjacent historical parameter and the second adjacent historical parameter are respectively the node historical parameter and the subsequent adjacent historical parameter corresponding to the parameter transition value; calculating the average adjacent parameter of the first adjacent historical parameter and the second adjacent historical parameter, and inserting the average adjacent parameter into the adjacent historical parameter group to obtain the supplemented adjacent parameter group, wherein the insertion position of the average adjacent parameter is located between the first adjacent historical parameter and the second adjacent historical parameter; and merging the supplemented adjacent parameter groups to obtain the supplemented historical parameter group.

8. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 7, characterized in that: The node failure analysis is performed based on the valid historical parameter group set and the node monitoring parameter group set to obtain the node failure rate, including: extracting the valid historical parameter groups in sequence from the valid historical parameter group set, and extracting the valid monitoring parameter groups corresponding to the valid historical parameter groups from the node monitoring parameter group set; using the valid historical parameter groups to perform machine training on the pre-acquired LSTM model to obtain a parameter failure identification model; inputting the valid monitoring parameter group into the parameter failure identification model to obtain the unit failure rate; summarizing the unit failure rates to obtain a unit failure rate set; if the unit failure rate set contains a unit failure rate greater than a preset maximum failure rate, the node failure rate is recorded as 100%; if the unit failure rate set does not contain a unit failure rate greater than the maximum failure rate, the node failure rate is calculated based on the preset parameter category weight group and the unit failure rate set.

9. The method for visual intelligent monitoring of distribution area based on distribution network big data according to claim 8, characterized in that: The calculating the node failure rate based on the preset parameter category weight group and the unit failure rate set includes: calculating the node failure rate using the following formula: ,in, represents the node failure rate, represents the number of parameter class weights in the parameter class weight group or the number of unit failure rates in the unit failure rate set, Represents the first parameter in the weight group parameter class weights, Indicates the unit failure rate concentration Unit failure rate.

10. A visual intelligent monitoring system for distribution areas based on distribution network big data, characterized in that: The system includes: a node parameter monitoring module, which is used to receive a substation monitoring instruction, determine the substation to be monitored based on the substation monitoring instruction, and confirm the set of nodes to be monitored in the substation to be monitored, wherein the set of nodes to be monitored includes multiple nodes to be monitored, and the nodes to be monitored are sequentially extracted from the set of nodes to be monitored, and the distribution network parameters of the nodes to be monitored are monitored to obtain a node monitoring parameter group set; a historical parameter query module, which is used to query the node historical parameter group set of the node to be monitored, extract the node historical parameter group in sequence from the node historical parameter group set, calculate the parameter richness of the node historical parameter group, and judge whether the parameter richness is greater than a preset standard richness. If the parameter richness is not greater than the standard richness, the node historical parameter group is parameter expanded to obtain a valid historical parameter group. If the parameter richness is greater than the standard richness, the node historical parameter group is parameter expanded to obtain a valid historical parameter group. , then the node historical parameter group is recorded as a valid historical parameter group; a change curve drawing module is used to summarize the valid historical parameter group to obtain a valid historical parameter group set, perform node fault analysis based on the valid historical parameter group set and the node monitoring parameter group set to obtain a node failure rate, and draw a parameter change curve diagram based on the node monitoring parameter group set, wherein the parameter change curve diagram includes multiple parameter change curves, and the parameter change curves in the parameter change curve diagram correspond one-to-one to the node monitoring parameter groups in the node monitoring parameter group set, the horizontal axis of the parameter change curve represents time, and the vertical axis represents the node monitoring parameter in the node monitoring parameter group; a node fault marking module is used to mark the parameter change curve diagram with the node failure rate to obtain a fault change curve diagram, summarize the fault change curve diagram, and obtain a fault change curve diagram set.

Images