Multi-source data cross comparison-based household number difference analysis method during distribution transformer

Abstract

The invention discloses a distribution transformer household number difference analysis method based on multi-source data cross comparison, and belongs to the technical field of power grid power failure and recovery, and the method comprises the steps: S1, collecting multi-source power data based on a power grid structure, and constructing a multi-element signal cross comparison analysis model based on a household number appeal rule; s2, taking the multi-source power data as input of a multivariate signal cross comparison analysis model for cross comparison to obtain an event to which a repeated distribution transformer belongs, an hour household number set and a power failure and recovery time set; s3, establishing a power failure distribution transformer repeated integration list according to the event to which the repeated distribution transformer belongs and the power failure and recovery time set, and establishing an hour household number error integration list according to the hour household number set and the power failure and recovery time set; s4, constructing a household number appeal report according to the power failure distribution transformer repeated integration list and the household number error integration list; the problem that in the prior art, due to the fact that the poor quality of collected data and the interaction relation between data corresponding to different systems in a power grid are not considered, the accuracy of household number analysis during distribution and transformation is poor is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid outage and restoration, and in particular to a method for analyzing the difference in the number of households in a distribution transformer based on cross-comparison of multi-source data. Background Art

[0002] With the development of power supply technology in the electric power industry, the analysis of the number of households during power outages and restorations of distribution transformers has gradually been realized in an intelligent and information-based manner. Intelligent terminals and electricity consumption collection systems are used to monitor the load of distribution transformers and the power outage and restoration conditions in real time, and the number of households during power outages is calculated by collecting the power outage and restoration time of the terminal. However, at present, the analysis of the number of households during power outages of distribution transformers has the problems of low accuracy and poor practicality. This is due to the poor quality and incompleteness of the collected data. Especially in remote areas, power outage signals are often missed or delayed in being uploaded, which affects the accuracy of the analysis results, and the analysis results are not suitable for actual working conditions.

[0003] Chinese patent, publication number: CN117370764A, publication date: January 9, 2024, discloses a distribution network power outage accurate household number management method and system, including: step 1: connecting various distribution network management systems to obtain the fault power outage data of the distribution network; step 2: using the GBDT algorithm, based on the fault power outage data of the distribution network, considering the meteorological data of the distribution network, to build a power outage duration accurate prediction model, and use the power outage duration accurate prediction model to accurately predict the power outage duration of various faults to obtain the accurate power outage duration corresponding to each fault; step 3: constructing a precise calculation strategy for the number of households during power outages of all types, obtaining the precise power outage range, and combining the precise power outage duration to calculate the precise number of households during power outages; step 4: performing power outage reliability statistical analysis after power outage repair and generating reports; however, the invention does not take into account the poor quality of collected data and the interaction between the corresponding data of different systems in the power grid, resulting in poor accuracy in the analysis of the number of households during distribution transformation. Summary of the invention

[0004] The purpose of the present invention is to address the problem that the prior art does not consider the poor quality of collected data and the interactive relationship between the corresponding data of different systems in the power grid, resulting in poor accuracy of the household number analysis of the distribution transformer; a distribution transformer household number difference analysis method based on multi-source data cross-comparison is proposed, and the multi-source power data is compared and analyzed by a multivariate signal cross-comparison analysis model constructed based on the household number complaint rule to obtain the events, household number sets and power outage and restoration time sets of repeated distribution transformers, and generate a power outage distribution transformer duplicate integration list and a household number error integration list according to the events, household number sets and power outage and restoration time sets of repeated distribution transformers. Finally, a household number complaint report is constructed according to the power outage distribution transformer duplicate integration list and the household number error integration list, thereby overcoming the problems of poor accuracy of the distribution transformer household number analysis and the inconsistency of the analysis results with the actual working conditions caused by the poor and incomplete quality of collected data, and significantly improving the accuracy of the distribution transformer household number analysis.

[0005] In a first aspect, a technical solution provided in an embodiment of the present invention is a method for analyzing the difference in the number of households in a distribution transformer based on cross-comparison of multi-source data, comprising the following steps: S1. Collect multi-source power data based on the power grid structure, and build a multi-signal cross-comparison analysis model based on the hourly household complaint rules; S2. Using the multi-source power data as the input of a multivariate signal cross-comparison analysis model for cross-comparison, and obtaining the events to which repeated distribution transformers belong, the number of households per hour, and the power outage and restoration time set; S3, establishing a repeated integrated list of power outage distribution transformers according to the events to which the repeated distribution transformers belong and the power outage and restoration time set, and establishing an incorrect integrated list of the number of households according to the number of households set and the power outage and restoration time set; S4. Complaint report on the number of households when constructing the duplicate integration list of power outage distribution transformers and the incorrect integration list of households.

[0006] In this scheme, multi-source power data is collected based on the power grid structure, so that various types of relevant data in the power grid can be fully acquired, laying a rich data foundation. A multi-signal cross-comparison analysis model is constructed based on the hourly household number complaint rule, which can conduct in-depth cross-comparison of multi-source power data, thereby breaking down data barriers and analyzing the interactive relationship between data, realizing effective combination of data, and preventing analysis errors caused by poor data quality and incompleteness. The multi-source power data is used as the input of the multi-signal cross-comparison analysis model for cross-comparison, and the events, hourly household number sets and power outage and restoration time sets belonging to repeated distribution transformers are obtained. According to the events belonging to repeated distribution transformers and the power outage and restoration time sets, a power outage is established. The duplicate integration list of distribution transformers can accurately identify the power outage and restoration events and related information implicit in multi-source power data, and establish an incorrect integration list of the number of households according to the hourly number of households set and the power outage and restoration time set. Finally, a complaint report on the number of households can be constructed based on the power outage distribution transformer duplicate integration list and the incorrect integration list of the number of households in time. Through cross-comparison of multi-source power data, the duplicate integration of distribution transformers, incorrect integration of the number of households in time, and other information when the corresponding transmission line has a power outage due to a fault can be analyzed, which significantly improves the accuracy of the analysis of the number of households in time of the distribution transformer. In addition, through the correspondence between multi-source power data and the power grid structure, the corresponding fault can be quickly located based on the results of the distribution transformer hourly number analysis and the corresponding multi-source power data.

[0007] Preferably, in S1, the specific process of collecting multi-source power data based on the power grid structure is: S111, collecting fault power outage event data based on the power supply and service system in the power grid and a preset collection cycle; Based on the power distribution automation master station of zone IV in the power grid and the preset collection cycle, the multi-source data source includes at least feeder switch tripping, branch switch tripping, and special transformer alarm signal; Based on the power consumption information collection system in the power grid, the power failure record data is collected in real time, and the power failure record data at least includes the power failure record of the dedicated transformer user and the power failure record of the low-voltage user; S112, integrating the fault power outage event data, multiple data sources and power failure record data to obtain multi-source power data.

[0008] Preferably, in S1, the specific process of constructing a multivariate signal cross comparison analysis model based on the hourly household number complaint rule is as follows: S121, constructing a power failure judgment module based on the power failure judgment rule in the household number complaint rule, wherein the power failure judgment module judges the power failure situation of the day according to the power failure record in the input data and the power failure and restoration time of the distribution transformer terminal; Synchronously, a fault analysis module is constructed based on the fault analysis rules in the hourly household number complaint rules. The fault analysis module performs fault time analysis based on the power outage situation of the day combined with the fault type in the input data to determine the power outage time and power restoration time corresponding to the fault; Synchronously, a time-based household outage and restoration module is constructed based on the hourly household number calculation rule and the power outage and restoration event status analysis rule in the hourly household number appeal rule, the hourly household outage and restoration module calculates the hourly household number set according to the power outage time and the power restoration time, and determines the power outage and restoration event status according to the power outage time and the power restoration time; S122, establishing a multi-signal cross-comparison analysis model according to the power-off judgment module, the fault analysis module and the user shutdown and recovery module.

[0009] Preferably, in S2, the multi-source power data is used as the input of the multivariate signal cross comparison analysis model for cross comparison, and the specific process of obtaining the repeated distribution transformer events, hourly household number set and power outage and restoration time set is: S211, extracting the time scale of the power outage record data in the multi-source power data and the time scale of the power outage and restoration time in the fault power outage event data, and determining the actual power outage and restoration time according to the time scale of the power outage record data and the time scale of the power outage and restoration time; S212, judging the power outage situation of the day according to the actual power outage and restoration time and the power outage and restoration time in the multi-source power data; S213, when the power outage occurs on the day, the fault type is determined based on the multi-source data source in the multi-source power data, and the fault time node is determined according to the fault type and the fault corresponding special transformer alarm signal; S214, judging the power outage and restoration time state when the power is lost on the day according to the fault time node and the power outage and restoration time in the multi-source power data, and calculating the number of households and the difference in the number of households in time according to the fault time node and the power outage and restoration time in the multi-source power data; S215, sorting the hourly household numbers and fault types to obtain the events to which the repeated distribution transformer belongs, and sorting the hourly household numbers, hourly household number differences, and fault types to obtain an hourly household number set; Synchronously, the fault types, fault time nodes, and power outage and restoration time states are sorted to obtain a power outage and restoration time set.

[0010] In this scheme, the actual power outage and restoration time is determined by the time scale of the power outage record data and the time scale of the power outage and restoration time, which can reduce the size of the data that needs to be processed. The power outage situation of the day is judged according to the actual power outage and restoration time and the power outage and restoration time in the multi-source power data. The operating status of the corresponding power grid can be judged, and the type of fault can be judged in combination with the multiple data sources when a power outage occurs. Then, the corresponding special transformer alarm signal can be extracted according to the specific type of fault to clarify the corresponding time period of the fault, thereby eliminating unnecessary data in the data that needs to be processed. This method of reducing the amount of data can significantly improve the efficiency of household analysis at the corresponding distribution transformer.

[0011] Preferably, in S214, the calculation formula of the hourly number of households and the hourly number of households difference is: A1=(B1-C1)×24; A2=(B2-C2)×24; D = A1-A2; In the formula, A1 is the number of households at the time of fault, B1 is the power restoration time after fault, C1 is the power outage time after fault, A2 is the actual number of households at the time of fault, B2 is the actual power restoration time, C2 is the actual power outage time, and D is the difference in the number of households at the time of fault.

[0012] Preferably, in S3, the specific process of establishing the power outage distribution transformer duplicate integration list according to the event to which the duplicate distribution transformer belongs and the power outage and restoration time set is: S311, determining the main event and sub-event based on the number of households corresponding to the fault in the event to which the repeated distribution transformer belongs, and determining the power outage and restoration time of the main event according to the fault type and power outage and restoration time set corresponding to the main event; Synchronously, determining the power outage and restoration time of the sub-event according to the fault type and power outage and restoration time set corresponding to the sub-event; S312. According to the power outage and restoration time of the main event and the power outage and restoration time of the sub-event, the overlap between the main event and the sub-event is adjusted to obtain a repeated integrated list of power outage distribution transformers.

[0013] In this solution, the main event and sub-event are distinguished to show the hierarchy between events, so as to quickly trace the root cause of power outage and corresponding fault, and adjust the event overlap, so as to avoid multiple calculations on the same power outage event, save computing resources and effectively improve computing efficiency.

[0014] Preferably, in S3, the specific process of establishing the hourly household number error set list according to the hourly household number set and the power outage and restoration time set is: S321, determining an abnormal fault event according to the hourly household number difference in the hourly household number set and the power outage and restoration time state in the power outage and restoration time set, and modifying the power outage and restoration time of the abnormal fault event based on the power outage and restoration time in the multi-source power data; S322. Establish a household number error integration list based on the abnormal fault event and the modified abnormal fault event power outage and restoration time.

[0015] In this solution, abnormal fault events are determined based on the hourly household number difference in the hourly household number set and the power outage and restoration time status in the power outage and restoration time set. The analysis results of the multivariate signal cross-comparison analysis model can be tested to ensure the accuracy of the faults in the analysis results.

[0016] Preferably, in S4, the specific process of reporting household complaints when constructing the repeated integration list of power outage distribution transformers and the timely wrong integration list of households is as follows: S411, obtaining the actual power outage records of the power grid, and verifying the duplicate integrated list of power outage distribution transformers based on the actual power outage records; synchronously, verifying the wrong integrated list of household numbers based on the actual power outage records; S412. Arrange the verified duplicate integration list of power outage distribution transformers and the verified incorrect integration list of hourly households to obtain the hourly household complaint report.

[0017] In this scheme, the data in the duplicate integration list of power outage distribution transformers and the timely incorrect integration list of households are verified through the actual power outage records of the corresponding power grid, which effectively improves the accuracy and rationality of the data, and can also identify potential errors and abnormal conditions in the data, further ensuring that the analysis results of the multivariate signal cross-comparison analysis model are consistent with the actual operating conditions of the corresponding power grid.

[0018] In a second aspect, a technical solution provided in an embodiment of the present invention is an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the processor implements the steps of a method for analyzing the difference in the number of households during distribution and transformation based on cross-comparison of multi-source data.

[0019] In a third aspect, a technical solution provided in an embodiment of the present invention is a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of a method for analyzing the difference in the number of households during distribution and transformation based on cross-comparison of multi-source data are implemented.

[0020] Beneficial effects of the present invention: (1) This application collects multi-source power data based on the power grid structure, which can comprehensively obtain various relevant data in the power grid and lay a rich data foundation. In addition, through the correspondence between multi-source power data and the power grid structure, the corresponding fault can be quickly located according to the results of the household number analysis during the distribution transformation and the corresponding multi-source power data; (2) This application constructs a multi-signal cross-comparison analysis model based on the hourly household number complaint rules, which can conduct in-depth cross-comparison of multi-source power data, thereby breaking down data barriers and analyzing the interactive relationship between data, achieving effective combination of data, and preventing analysis errors caused by poor data quality and incompleteness, significantly improving the accuracy of hourly household number analysis of distribution transformers.

[0021] The above invention content is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Other features, objects and advantages of the present invention will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings. The drawings are only for the purpose of illustrating preferred embodiments and are not to be considered as limiting the present invention. Also, the same reference symbols are used throughout the drawings to represent the same parts.

[0023] Figure 1 The present invention is a flowchart of a method for analyzing the difference in the number of households during distribution and transformation based on cross-comparison of multi-source data. DETAILED DESCRIPTION

[0024] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific implementation method described herein is only an optimal embodiment of the present invention, which is only used to explain the present invention and does not limit the scope of protection of the present invention. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0025] Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations (or steps) as sequential processes, many of the operations (or steps) therein can be implemented in parallel, concurrently, or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the drawings; the process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0026] Embodiment 1: like Figure 1 As shown, this embodiment provides a method for analyzing the difference in the number of households during distribution and transformation based on cross-comparison of multi-source data, comprising the following steps: S1. Collect multi-source power data based on the power grid structure, and build a multi-signal cross-comparison analysis model based on the hourly household complaint rule; S111. Collect fault power outage event data based on the power supply and service system in the power grid and the preset collection cycle; Based on the power distribution automation master station of zone IV in the power grid and the preset collection cycle, the multi-source data source includes at least feeder switch tripping, branch switch tripping, and special transformer alarm signal; Based on the power consumption information collection system in the power grid, the power failure record data is collected in real time, and the power failure record data at least includes the power failure record of the dedicated transformer user and the power failure record of the low-voltage user; S112, integrating the fault power outage event data, multiple data sources and power failure record data to obtain multi-source power data.

[0027] In this embodiment, the data on power outage events caused by faults in the service system are periodically acquired based on a preset collection cycle, and multiple data sources such as the feeder switch tripping, branch switch tripping and public-private transformer alarm signals of the distribution automation master station in zone IV are collected in combination with the line name, power outage time and the list of affected distribution transformers. Secondly, the power consumption information collection system is used to call for power outage record data of private transformer users and low-voltage users in real time.

[0028] In one embodiment, the specific process of constructing a multivariate signal cross comparison analysis model based on the hourly household number complaint rule is as follows: S121, constructing a power failure judgment module based on the power failure judgment rule in the household number complaint rule, wherein the power failure judgment module judges the power failure situation of the day according to the power failure record in the input data and the power failure and restoration time of the distribution transformer terminal; Synchronously, a fault analysis module is constructed based on the fault analysis rules in the hourly household number complaint rules. The fault analysis module performs fault time analysis based on the power outage situation of the day combined with the fault type in the input data to determine the power outage time and power restoration time corresponding to the fault; Synchronously, a time-based household outage and restoration module is constructed based on the hourly household number calculation rule and the power outage and restoration event status analysis rule in the hourly household number appeal rule, the hourly household outage and restoration module calculates the hourly household number set according to the power outage time and the power restoration time, and determines the power outage and restoration event status according to the power outage time and the power restoration time; S122, establishing a multi-signal cross-comparison analysis model according to the power-off judgment module, the fault analysis module and the user shutdown and recovery module.

[0029] In this embodiment, the hourly household number complaint rule specifically includes: a. When multiple power outage records are returned in the multi-source power data, the power outage and restoration time closest to the distribution transformer terminal is selected as the actual power outage and restoration time; b. If the actual power outage and restoration time is less than 24 hours of the terminal power outage and restoration time, it is judged that there is no power outage record on that day; c. When the fault type is feeder power outage, it is necessary to determine whether there is a feeder power outage reclosing success alarm event on the line to which the distribution transformer belongs on that day. If there is, it is determined that the corresponding feeder switch reclosing is successful according to the analysis result; d. When the fault type is a branch line power outage, it is necessary to determine whether there is an intelligent switch reclosing success alarm event on the line to which the distribution transformer belongs on that day. If there is, it is determined that the analysis result corresponds to the intelligent switch reclosing success; e. When the actual power outage and restoration time of the call test and the power outage and restoration time of the distribution transformer terminal are on the same day, if the power outage time comparison value is greater than 3 minutes, and the power restoration time comparison value is less than or equal to 3 minutes, the analysis result is determined to be abnormal power outage time; if the power outage time comparison value is less than or equal to 3 minutes, and the power restoration time comparison value is greater than 3 minutes, the analysis result is determined to be abnormal power restoration time; if the power outage time comparison value is greater than 3 minutes, and the power restoration time comparison value is greater than 3 minutes, the analysis result is determined to be abnormal power outage and restoration time; if the power outage time comparison value is less than or equal to 3 minutes, and the power restoration time comparison value is less than or equal to 33 minutes, the analysis result is determined to be normal; f. Calculation rules for the number of households at the hour: The number of households at the hour of judgment is equal to the difference between the power restoration time judged by the system and the power outage time judged by the system multiplied by 24; the actual number of households at the hour of judgment is equal to the difference between the actual power restoration time and the actual power outage time multiplied by 24; the difference value of the number of households at the hour of judgment is equal to the difference between the number of households at the hour of judgment and the actual number of households at the hour of judgment; Among them, the power-off judgment rules include the above-mentioned rules a and b, the fault analysis rules include the above-mentioned rules c and d, the hourly household number calculation rules include the above-mentioned rule f, and the power-off and power-restore event status analysis rules include the above-mentioned rule e.

[0030] S2. Using the multi-source power data as the input of a multivariate signal cross-comparison analysis model for cross-comparison, and obtaining the events to which repeated distribution transformers belong, the number of households per hour, and the power outage and restoration time set; S211, extracting the time scale of the power outage record data in the multi-source power data and the time scale of the power outage and restoration time in the fault power outage event data, and determining the actual power outage and restoration time according to the time scale of the power outage record data and the time scale of the power outage and restoration time; S212, judging the power outage situation of the day according to the actual power outage and restoration time and the power outage and restoration time in the multi-source power data; S213, when the power outage occurs on the day, the fault type is determined based on the multi-source data source in the multi-source power data, and the fault time node is determined according to the fault type and the fault corresponding special transformer alarm signal; S214, judging the power outage and restoration time state when the power is lost on the day according to the fault time node and the power outage and restoration time in the multi-source power data, and calculating the number of households and the difference in the number of households in time according to the fault time node and the power outage and restoration time in the multi-source power data; S215, sorting the hourly household numbers and fault types to obtain the events to which the repeated distribution transformer belongs, and sorting the hourly household numbers, hourly household number differences, and fault types to obtain an hourly household number set; Synchronously, the fault types, fault time nodes, and power outage and restoration time states are sorted to obtain a power outage and restoration time set.

[0031] In this embodiment, the six rules in the hourly household number complaint rule are corresponded to construct the functional module of the multi-signal cross-comparison analysis model, and the collected multi-source power data is processed.

[0032] In one embodiment, the calculation formula of the hourly number of households and the hourly number of households difference is specifically: A1=(B1-C1)×24; A2=(B2-C2)×24; D = A1-A2; In the formula, A1 is the number of households at the time of fault, B1 is the power restoration time after fault, C1 is the power outage time after fault, A2 is the actual number of households at the time of fault, B2 is the actual power restoration time, C2 is the actual power outage time, and D is the difference in the number of households at the time of fault.

[0033] S3. Establish a duplicate integrated list of power outage distribution transformers according to the events to which the duplicate distribution transformers belong and the power outage and restoration time set, and establish an incorrect integrated list of the number of households according to the number of households by time set and the power outage and restoration time set.

[0034] In one embodiment, the specific process of establishing a power outage distribution transformer duplicate integration list according to the events to which the duplicate distribution transformer belongs and the power outage and restoration time set is as follows: S311, determining the main event and sub-event based on the number of households corresponding to the fault in the event to which the repeated distribution transformer belongs, and determining the power outage and restoration time of the main event according to the fault type and power outage and restoration time set corresponding to the main event; Synchronously, determining the power outage and restoration time of the sub-event according to the fault type and power outage and restoration time set corresponding to the sub-event; S312. According to the power outage and restoration time of the main event and the power outage and restoration time of the sub-event, the overlap between the main event and the sub-event is adjusted to obtain a repeated integrated list of power outage distribution transformers.

[0035] In this embodiment, the record with the largest number of households when the event to which the distribution transformer belongs is repeated is determined as the main event, and the rest are classified as sub-events; if the power outage and power restoration time of the sub-event is within the power outage and power restoration time range of the main event, the main event analysis result is a repeated power outage; if the power outage or power restoration time of the sub-event is not within the power outage and power restoration time range of the main event, the main event analysis result is that the power outage time is extended to the power outage time of the sub-event, or the power restoration time is extended to the power restoration time of the sub-event.

[0036] In one embodiment, the specific process of establishing the hourly household number error set list according to the hourly household number set and the power outage and restoration time set is as follows: S321, determining an abnormal fault event according to the hourly household number difference in the hourly household number set and the power outage and restoration time state in the power outage and restoration time set, and modifying the power outage and restoration time of the abnormal fault event based on the power outage and restoration time in the multi-source power data; S322. Establish a household number error integration list based on the abnormal fault event and the modified abnormal fault event power outage and restoration time.

[0037] In this embodiment, based on the calculation results of the hourly household number difference, the analysis results corresponding to the hourly household number difference less than 0.05, the hourly household number difference is a negative number, and the power outage and restoration time deviation is within 3 minutes are determined as normal analysis results and eliminated; for the remaining analysis results that are not eliminated, such as abnormal power outage and restoration time, no power-off record, etc., the "earliest power outage time" in the return value of the distribution transformer user call test is set to the actual power outage time of the analysis results that are not eliminated, and the "latest power restoration time" in the return value of the distribution transformer user call test is set to the actual power restoration time of the analysis results that are not eliminated.

[0038] S4. Report on household number complaints when constructing the repeated integration list of power outage distribution transformers and the wrong integration list of households; S411, obtaining the actual power outage records of the power grid, and verifying the duplicate integrated list of power outage distribution transformers based on the actual power outage records; synchronously, verifying the wrong integrated list of household numbers based on the actual power outage records; S412. Arrange the verified duplicate integration list of power outage distribution transformers and the verified incorrect integration list of hourly households to obtain the hourly household complaint report.

[0039] Embodiment 2: An optional embodiment also provided in the embodiments of the present invention is: an electronic device, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, it implements the steps of a method for analyzing the difference in the number of households during distribution and transformation based on cross-comparison of multi-source data.

[0040] Embodiment 3: An optional embodiment also provided in the embodiments of the present invention is: a storage medium, in which computer executable instructions are stored. When the computer executable instructions are loaded and executed by a processor, the steps of a method for analyzing the difference in the number of households during distribution and transformation based on cross-comparison of multi-source data are implemented.

[0041] This embodiment has at least the following substantial effects: (1) This application collects multi-source power data based on the power grid structure, which can comprehensively obtain various relevant data in the power grid and lay a rich data foundation. In addition, through the correspondence between multi-source power data and the power grid structure, the corresponding fault can be quickly located according to the results of the household number analysis during the distribution transformation and the corresponding multi-source power data; (2) This application constructs a multi-signal cross-comparison analysis model based on the hourly household number complaint rules, which can conduct in-depth cross-comparison of multi-source power data, thereby breaking down data barriers and analyzing the interactive relationship between data, achieving effective combination of data, and preventing analysis errors caused by poor data quality and incompleteness, significantly improving the accuracy of hourly household number analysis of distribution transformers.

[0042] The above specific embodiments are preferred embodiments of the present invention, and are not intended to limit the specific implementation scope of the present invention. The scope of the present invention includes but is not limited to the present specific embodiments. All equivalent changes made in accordance with the shape, structure, and method of the present invention are within the protection scope of the present invention.

Claims

1. A method for analyzing the difference in the number of households in distribution transformers based on cross-comparison of multi-source data, characterized in that: The following steps are involved: S1. Collect multi-source power data based on the power grid structure, and build a multi-signal cross-comparison analysis model based on the hourly household complaint rules; S2. Using the multi-source power data as input of a multivariate signal cross-comparison analysis model for cross-comparison, and obtaining a set of events, hourly household numbers, and power outage and restoration time to which repeated distribution transformers belong; S3, establishing a power outage distribution transformer duplicate integration list according to the duplicate distribution transformer event and the power outage restoration time set, and establishing an hourly household number incorrect integration list according to the hourly household number set and the power outage restoration time set; S4. Report on household complaints when constructing the duplicate integration list of power outage distribution transformers and the incorrect integration list of households.

2. According to claim 1, a method for analyzing the difference in the number of households in a distribution transformer based on cross-comparison of multi-source data, characterized in that: In S1, the specific process of collecting multi-source power data based on the power grid structure is: S111, collecting fault power outage event data based on the power supply and service system in the power grid and a preset collection cycle; Based on the power distribution automation master station of zone IV in the power grid and the preset collection cycle, the multi-source data is collected, and the multi-source data includes at least feeder switch tripping, branch line switch tripping, and special transformer alarm signal; Based on the power consumption information collection system in the power grid, the power failure record data is collected in real time, and the power failure record data at least includes the power failure record of the dedicated transformer user and the power failure record of the low-voltage user; S112, integrating the fault power outage event data, multiple data sources and power failure record data to obtain multi-source power data.

3. The method for analyzing the difference in the number of households when the distribution transformer is in operation based on cross-comparison of multi-source data according to claim 1 is characterized in that: In S1, the specific process of constructing a multivariate signal cross-comparison analysis model based on the hourly household number complaint rule is as follows: S121, constructing a power failure judgment module based on the power failure judgment rule in the household number complaint rule, wherein the power failure judgment module judges the power failure situation of the day according to the power failure record in the input data and the power failure and restoration time of the distribution transformer terminal; Synchronously, a fault analysis module is constructed based on the fault analysis rules in the hourly household number complaint rules. The fault analysis module performs fault time analysis based on the power outage situation of the day combined with the fault type in the input data to determine the power outage time and power restoration time corresponding to the fault; Synchronously, a time-based household outage and restoration module is constructed based on the hourly household number calculation rule and the power outage and restoration event status analysis rule in the hourly household number appeal rule, the hourly household outage and restoration module calculates the hourly household number set according to the power outage time and the power restoration time, and determines the power outage and restoration event status according to the power outage time and the power restoration time; S122, establishing a multi-signal cross-comparison analysis model according to the power-off judgment module, the fault analysis module and the user shutdown and recovery module.

4. The method for analyzing the difference in the number of households when the distribution transformer is in operation based on cross-comparison of multi-source data according to claim 1 is characterized in that: In S2, the multi-source power data is used as the input of the multi-signal cross-comparison analysis model for cross-comparison, and the specific process of obtaining the events to which the repeated distribution transformer belongs, the hourly household number set, and the power outage and restoration time set is as follows: S211, extracting the time scale of the power failure record data in the multi-source power data and the time scale of the power failure and restoration time in the fault power failure event data, and determining the actual power failure and restoration time according to the time scale of the power failure record data and the time scale of the power failure and restoration time; S212, judging the power outage situation of the day according to the actual power outage and restoration time and the power outage and restoration time in the multi-source power data; S213, when the power outage occurs on the day, the fault type is determined based on the multi-source data source in the multi-source power data, and the fault time node is determined according to the fault type and the fault corresponding special transformer alarm signal; S214, judging the power outage and restoration time state when the power is lost on the day according to the fault time node and the power outage and restoration time in the multi-source power data, and calculating the number of households and the difference in the number of households in time according to the fault time node and the power outage and restoration time in the multi-source power data; S215, sorting the hourly household numbers and fault types to obtain the events to which the repeated distribution transformer belongs, and sorting the hourly household numbers, hourly household number differences, and fault types to obtain an hourly household number set; Synchronously, the fault types, fault time nodes, and power outage and restoration time states are sorted to obtain a power outage and restoration time set.

5. The method for analyzing the difference in the number of households when the distribution transformer is in operation based on cross-comparison of multi-source data according to claim 4 is characterized in that: In S214, the calculation formula of the difference between the hourly number of households and the hourly number of households is specifically: A1=(B1-C1)×24; A2=(B2-C2)×24; D = A1-A2; In the formula, A1 is the number of households at the time of fault, B1 is the power restoration time after fault, C1 is the power outage time after fault, A2 is the actual number of households at the time of fault, B2 is the actual power restoration time, C2 is the actual power outage time, and D is the difference in the number of households at the time of fault.

6. The method for analyzing the difference in the number of households when the distribution transformer is in operation based on cross-comparison of multi-source data according to claim 1 is characterized in that: In S3, the specific process of establishing a power outage distribution transformer duplicate integration list according to the event to which the duplicate distribution transformer belongs and the power outage and restoration time set is: S311, determining the main event and sub-event based on the number of households corresponding to the fault in the event to which the repeated distribution transformer belongs, and determining the power outage and restoration time of the main event according to the fault type and power outage and restoration time set corresponding to the main event; Synchronously, determining the power outage and restoration time of the sub-event according to the fault type and power outage and restoration time set corresponding to the sub-event; S312. According to the power outage and restoration time of the main event and the power outage and restoration time of the sub-event, the overlap between the main event and the sub-event is adjusted to obtain a repeated integrated list of power outage distribution transformers.

7. The method for analyzing the difference in the number of households when the distribution transformer is in operation based on cross-comparison of multi-source data according to claim 1 is characterized in that: In S3, the specific process of establishing the hourly household number error set list according to the hourly household number set and the power outage and restoration time set is as follows: S321, determining an abnormal fault event according to the hourly household number difference in the hourly household number set and the power outage and restoration time state in the power outage and restoration time set, and modifying the power outage and restoration time of the abnormal fault event based on the power outage and restoration time in the multi-source power data; S322. Establish a household number error integration list based on the abnormal fault event and the modified abnormal fault event power outage and restoration time.

8. The method for analyzing the difference in the number of households when the distribution transformer is in operation based on cross-comparison of multi-source data according to claim 1 is characterized in that: In S4, the specific process of household number complaint report when constructing the repeated integration list of power outage distribution transformers and the wrong integration list of households is as follows: S411, obtaining the actual power outage record of the power grid, and verifying the duplicate integrated list of power outage distribution transformers based on the actual power outage record; synchronously, verifying the wrong integrated list of household numbers based on the actual power outage record; S412. Arrange the verified duplicate integration list of power outage distribution transformers and the verified incorrect integration list of hourly households to obtain the hourly household complaint report.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor calls the computer program in the memory, the steps of a method for analyzing the difference in the number of households in a distribution transformer based on cross-comparison of multi-source data as described in any one of claims 1 to 8 are implemented.

10. A storage medium, characterized in that: The storage medium stores computer executable instructions, which, when loaded and executed by the processor, implement the steps of a method for analyzing differences in the number of households during distribution and transformation based on cross-comparison of multi-source data as described in any one of claims 1 to 8.

Images