Transformer area line loss abnormity positioning method and device based on multi-dimensional analysis and medium

Abstract

The invention relates to the field of transformer area line loss detection, in particular to a transformer area line loss anomaly positioning method and device based on multi-dimensional analysis and a medium. The method comprises the following steps: acquiring time-sharing electric quantity data of a target transformer area, calculating a transformer area line loss rate according to the time-sharing electric quantity data, and extracting time period fluctuation characteristics of the transformer area line loss rate; and based on the abrupt change time period of the time period fluctuation characteristic, performing phase deviation rate calculation on the user electric meter, and marking the phase with the phase deviation rate exceeding a threshold value as an abnormal phase. And carrying out null line and live line current difference value comparison on the user electricity meters with the abnormal phases, and screening out current-unbalanced user electricity meters with null line and live line current difference values exceeding tolerance. And calculating a K value of the user ammeter with unbalanced current, and locking the user ammeter with abnormal electricity utilization through the K value. According to the method, the misjudgment rate of the transformer area line loss abnormity is reduced, the positioning efficiency of the transformer area line loss abnormity is improved, the method can be executed without strict experience requirements on technicians, and the abnormity can be directly positioned to the user dimension.

Description

Technical Field

[0001] The present application relates to the field of line loss detection in a substation, and in particular to a method, device and medium for locating abnormal line loss in a substation based on multi-dimensional analysis. Background Art

[0002] With the deepening of the reform of the power system, power supply companies are faced with the major tasks of energy conservation and loss reduction, potential tapping and efficiency improvement. Strengthening line loss management has become the only way for power supply companies to improve the quality and efficiency of their operations and management. Efficient line loss management will directly affect the efficiency and economy of power supply. However, due to the complexity and diversity of the reasons for unqualified line losses in substations, existing technologies often rely on experienced technicians to manually troubleshoot abnormal line losses in substations from multiple angles and multiple links. This results in technicians having to face massive amounts of electricity consumption data, invest a lot of manual effort, have low troubleshooting efficiency, and have stringent experience requirements for technicians. Summary of the invention

[0003] In order to solve the problem of low efficiency of abnormal line loss positioning in the prior art, the present application provides a method, device and medium for abnormal line loss positioning in the area based on multi-dimensional analysis. In a first aspect, the method provided by the present application includes the following steps: Obtaining time-sharing electricity data of the target substation, calculating the substation line loss rate according to the time-sharing electricity data, and extracting the time period fluctuation characteristics of the substation line loss rate, wherein the time-sharing electricity data comes from the user's electricity meter and the power supply side total meter; Based on the mutation period of the period fluctuation characteristics, the phase deviation rate of the user's electric meter is calculated, and the phase whose phase deviation rate exceeds the threshold is marked as an abnormal phase, and the phase deviation rate is obtained based on the phase-by-phase power data; Comparing the zero-live current difference of the user electric meters with abnormal phases, and screening out the current unbalanced user electric meters whose zero-live current difference exceeds the tolerance, wherein the zero-live current difference is obtained based on the zero-live current data; The K value of the electric meter of the user with unbalanced current is calculated, and the electric meter of the user with abnormal power consumption is locked by the K value. The K value is the ratio of the change in the electric quantity of the electric meter of the user with unbalanced current to the change in the line loss rate of the substation.

[0004] Specifically, the phase-separated electricity quantity data comes from the user's electricity meter, and the abnormal line loss location method in the substation also includes calculating the phase deviation rate of each phase electricity quantity and the total electricity quantity of the user's electricity meter based on the phase-separated electricity quantity data.

[0005] Specifically, the zero-live line current data comes from the user's electric meter, and the abnormal line loss location method in the substation area further includes comparing the zero-live line current difference of the zero-live line current data.

[0006] Specifically, the abnormal line loss location method in the substation area further includes: The inflection point of the fluctuation characteristics of the time period is identified through a sliding window, and M periods before and after the inflection point are marked as the mutation period, where M is an adjustable value set according to the historical data of the load fluctuation of the target substation.

[0007] Specifically, the user meter with the abnormal phase is marked as a first-level abnormal user meter, an abnormal user priority list is generated based on the first-level abnormal user meter, the current imbalance user meter and the abnormal power consumption user meter, and user abnormal situations are graded according to the abnormal user priority list.

[0008] Specifically, the method for calculating the K value of the current unbalanced user meter includes: Select the mutation inflection point in the mutation period, and calculate the power change δ of the user's electric meter at the mutation inflection point Q _user and area line loss rate change δ Q _loss; Eliminate the line loss rate change δ of the substation area that is less than the noise threshold Q The mutation inflection point corresponding to _loss is calculated for the remaining mutation inflection points K =δ Q _user / δ Q _loss obtains the K value.

[0009] Specifically, the method for generating an abnormal user priority list includes: Scoring the use scoring model with abnormal marks, wherein the abnormal mark is one or more of the first-level abnormal user meter, the current unbalanced user meter and the abnormal power consumption user meter, and the scoring model is a model based on the phase deviation rate weight, the zero-live current difference weight and the K value weight; The abnormal user priority list is generated according to the descending order of the scores.

[0010] Specifically, it is characterized in that the abnormal line loss location method in the substation area further includes: The historical load curve of the electric meter of the user with abnormal electricity consumption is retrieved and matched with the current electricity consumption pattern. If the matching similarity is higher than a threshold, the user's electric meter is inspected on site and the priority list of the abnormal users is corrected.

[0011] In a second aspect, the electronic device of the present application includes a processor and a memory, wherein the memory stores a computer program, and when the program is executed by the processor, the steps of the method described above are implemented.

[0012] In a third aspect, the computer-readable storage medium of the present application stores a computer program, and when the program is executed by a processor, the steps of the method described above are implemented.

[0013] This application has the following technical effects: The misjudgment rate of abnormal line loss in the substation area is reduced, and the efficiency of locating abnormal line loss in the substation area is improved. The method of the present application can be executed without strict experience requirements for technical personnel, and the abnormality can be directly located to the user dimension. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become easily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-restrictive manner, and the same or corresponding numbers represent the same or corresponding parts.

[0015] Figure 1 It is a flow chart of abnormal line loss analysis in a transformer area in an embodiment of the present application; Figure 2 It is a flow chart of a method for locating abnormal line loss in a substation based on multi-dimensional analysis in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0017] In recent years, with the deepening of the power system reform, the profit space of power supply enterprises has been gradually compressed. Digging inward, saving energy and reducing losses, tapping potential and increasing efficiency, and strengthening line loss management have become the only way for power supply enterprises to improve the quality and efficiency of operation and management. Therefore, under the new situation of power system reform, power supply must further strengthen the line loss management of substations, promote the improvement of the lean management level of line loss in substations, and effectively reduce the line loss rate in substations. Improving the ability and effectiveness of line loss management is an inevitable requirement for improving the market competitiveness of enterprises.

[0018] At present, the reasons for the unqualified line loss in substations are complex and diverse, massive big data has not been effectively analyzed and utilized, and grassroots front-line employees lack effective substation line loss analysis skills, resulting in inefficient on-site line loss analysis, unclear results of substation line loss remediation, and disproportionate labor input and output, which have created major obstacles to substation line loss remediation work.

[0019] Based on the above situation, in order to solve the problem of difficulty and low efficiency in line loss analysis of grassroots teams, this embodiment proposes a method for locating abnormal line loss in the substation area based on multi-dimensional analysis, and develops calculation software that can be used to execute these steps based on the Vb.net language to solve the problem of restricting the time and efficiency of line loss analysis in the substation area. The promotion and application of this calculation software can effectively improve the efficiency of line loss management, solve the problem of long time consumption of line loss analysis of grassroots front-line teams, save energy and reduce losses for enterprises, improve benefits, and enhance the market competitiveness of enterprises.

[0020] The abnormal analysis of line loss in the substation area is generally carried out according to Figure 1 The process shown is carried out from Figure 1 It can be seen from the process that the abnormal analysis of line loss in the substation generally includes three steps: line loss change trend analysis, basic information analysis of the substation, and in-depth analysis of each user in the substation. According to the statistical table of the average time consumption of each process in the abnormal substation line loss analysis of the 10 power supply stations under the Wuhu Power Supply Company in Wanzhi District in 2022 (Table 1), it can be seen that the average time consumption of the abnormal substation line loss work is 259.1 minutes, of which the average time consumption for in-depth analysis of each user in the substation is 221.3 minutes, accounting for 85.5%, and the range value is 60, which is a large value. Therefore, the duration of in-depth analysis of each user in the substation is the main crux. Reducing the time for in-depth analysis will effectively improve the efficiency of substation line loss management.

[0021] Table 1 Statistics of the average time consumption of each process in the abnormal area line loss analysis of 10 power supply stations under the Wuhu Power Supply Company in Wanzhi District in 2022 Taking the above-mentioned main crux of in-depth analysis of the duration of each user in the station area as the research direction, this embodiment proposes the following Figure 2 The method shown comprises the following steps: Obtain the time-sharing electricity data of the target substation, calculate the substation line loss rate based on the time-sharing electricity data, and extract the time period fluctuation characteristics of the substation line loss rate. The time-sharing electricity data comes from the user's electricity meter and the power supply side total meter. The user's electricity meter and the power supply side total meter support a collection accuracy of up to 10 times / minute, and can record three-phase current independently. The user's electricity meter can also support neutral current analysis and live current analysis; Based on the sudden change period of the period fluctuation characteristics, the phase deviation rate of the user's electric meter is calculated, and the phase whose phase deviation rate exceeds the threshold is marked as an abnormal phase. The phase deviation rate is obtained based on the phase-by-phase power data. The calculation software of this embodiment is provided with a time-sharing calculation unit that uses a sliding window algorithm to identify the inflection point of the sudden increase in line loss rate, and marks the M periods before and after the inflection point as abnormal periods. M is adaptively adjusted according to the historical load curve of the substation. For example, for commercial substations with frequent load fluctuations, M can be set to 6 cycles, while for residential substations it is set to 4 cycles to balance detection sensitivity and calculation efficiency.

[0022] Compare the zero-live current difference of the user meters with abnormal phases, and screen out the current unbalanced user meters whose zero-live current difference exceeds the tolerance. The zero-live current difference is obtained based on the zero-live current data; Calculate the K value of the electric meter of the user with current imbalance, and lock the electric meter of the user with abnormal power consumption through the K value. The K value is the ratio of the change in the electric quantity of the electric meter of the user with current imbalance and the change in the line loss rate of the substation.

[0023] Specifically, the phase power data comes from the user's electricity meter, and the method for locating abnormal line loss in the substation also includes calculating the phase deviation rate of each phase power and the total power of the user's electricity meter based on the phase power data.

[0024] Specifically, the zero-live line current data comes from the user's electric meter, and the method for locating abnormal line loss in the substation also includes comparing the zero-live line current difference of the zero-live line current data.

[0025] Specifically, the method for locating abnormal line loss in the substation area also includes: The inflection point of the period fluctuation characteristics is identified through a sliding window, and the M periods before and after the inflection point are marked as mutation periods, where M is an adjustable value set according to the historical data of load fluctuations in the target substation.

[0026] Specifically, the user meters with abnormal phases are marked as first-level abnormal user meters, and an abnormal user priority list is generated based on the first-level abnormal user meters, current imbalance user meters and abnormal power consumption user meters, and user abnormal situations are graded according to the abnormal user priority list.

[0027] Specifically, the method for calculating the K value of the current unbalanced user meter includes: Select the mutation inflection point in the mutation period and calculate the change of electricity consumption of the user's electricity meter at the mutation inflection point. Q _user and area line loss rate changeδ Q _loss; Eliminate the line loss rate change δ of the substation area that is less than the noise threshold Q The mutation inflection point corresponding to _loss is calculated for the remaining mutation inflection points K =δ Q _user / δ Q _loss gets the K value.

[0028] Specifically, the method for generating the abnormal user priority list includes: Scoring the use scoring model with abnormal marks, the abnormal mark is one or more of the first-level abnormal user meter, the current imbalance user meter and the abnormal power consumption user meter, and the scoring model is a model based on the phase deviation rate weight, the zero-live current difference weight and the K value weight; Generate a priority list of abnormal users in descending order of scores.

[0029] Specifically, it is characterized in that the method for locating abnormal line loss in a transformer area further comprises: The historical load curve of the electricity meter of users with abnormal electricity consumption is retrieved and matched with the current electricity consumption pattern. If the matching similarity is higher than the threshold, the user's electricity meter is inspected on site and the priority list of abnormal users is corrected.

[0030] The computing software of this embodiment can be run through a multi-core processor and a cache memory, and the memory stores a computer program of the above method. The processor schedules time-sharing, phase-sharing, zero-live line comparison and K value calculation tasks through a parallel computing framework, and uses a message queue to realize data interaction between modules to ensure real-time response in high-concurrency scenarios. In addition, the program code stored in the computer-readable storage medium supports distributed deployment and is suitable for cloud-edge collaborative power grid architecture.

[0031] Before implementing the method and calculation software proposed in this embodiment, the Wanzhi District Wuhu Power Supply Company used Excel and other tools to assist manual calculation and analysis, which took an average of about three and a half hours. After implementing the method and calculation software proposed in this embodiment on 10 random abnormal substations, it can be seen from the recorded software running time table (Table 2) that the range of the software running time, i.e., the substation line loss abnormality positioning time, is 6±0.4 (min), the upper tolerance limit TU=6.4 (min), and the lower tolerance limit TL=5.6 (min), then the calculation process capability index is: The process capability index is level one, the process capability index is sufficient, and compared with manual intuitive analysis, the analysis accuracy is ≥95%.

[0032] Table 2 Software running timetable Obviously, the embodiments described above are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0033] It should be understood that when the terms "first", "second", etc. are used in the claims, specification and drawings of the present application, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the specification and claims of the present application indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

Claims

1. A method for locating abnormal line loss in a transformer area based on multi-dimensional analysis, characterized in that: The following steps are involved: Obtaining time-sharing electricity data of the target substation, calculating the substation line loss rate according to the time-sharing electricity data, and extracting the time period fluctuation characteristics of the substation line loss rate, wherein the time-sharing electricity data comes from the user's electricity meter and the power supply side total meter; Based on the mutation period of the period fluctuation characteristics, the phase deviation rate of the user's electric meter is calculated, and the phase whose phase deviation rate exceeds the threshold is marked as an abnormal phase, and the phase deviation rate is obtained based on the phase-by-phase power data; Comparing the zero-live current difference of the user electric meters with abnormal phases, and screening out the current unbalanced user electric meters whose zero-live current difference exceeds the tolerance, wherein the zero-live current difference is obtained based on the zero-live current data; The K value of the electric meter of the user with unbalanced current is calculated, and the electric meter of the user with abnormal power consumption is locked by the K value. The K value is the ratio of the change in the electric quantity of the electric meter of the user with unbalanced current to the change in the line loss rate of the substation.

2. The method for locating abnormal line loss in a transformer area according to claim 1, characterized in that: The phase-separated electricity quantity data comes from the user's electricity meter, and the abnormal line loss location method in the substation area also includes calculating the phase deviation rate of each phase electricity quantity and the total electricity quantity of the user's electricity meter based on the phase-separated electricity quantity data.

3. The method for locating abnormal line loss in a transformer area according to claim 1, characterized in that: The zero-live line current data comes from the user's electric meter, and the abnormal line loss positioning method in the substation area further includes comparing the zero-live line current difference of the zero-live line current data.

4. The method for locating abnormal line loss in a transformer area according to claim 1, characterized in that: The abnormal line loss location method in the substation area also includes: The inflection point of the fluctuation characteristics of the time period is identified through a sliding window, and M periods before and after the inflection point are marked as the mutation period, where M is an adjustable value set according to the historical data of the load fluctuation of the target substation.

5. The method for locating abnormal line loss in a transformer area according to claim 1, characterized in that: The user meter with the abnormal phase is marked as a first-level abnormal user meter, and an abnormal user priority list is generated according to the first-level abnormal user meter, the current imbalance user meter and the abnormal power consumption user meter, and the user abnormal situations are graded according to the abnormal user priority list.

6. The method for locating abnormal line loss in a transformer area according to claim 1, characterized in that: The method for calculating the K value of the current unbalanced user electric meter includes: Select the mutation inflection point in the mutation period, and calculate the power change δ of the user's electric meter at the mutation inflection point Q _user and area line loss rate change δ Q _loss; Eliminate the line loss rate change δ of the substation area that is less than the noise threshold Q The mutation inflection point corresponding to _loss is calculated for the remaining mutation inflection points K =δ Q _user / δ Q _loss obtains the K value.

7. The method for locating abnormal line loss in a transformer area according to claim 5, characterized in that: The method for generating an abnormal user priority list comprises: Scoring the use scoring model with abnormal marks, wherein the abnormal mark is one or more of the first-level abnormal user meter, the current unbalanced user meter and the abnormal power consumption user meter, and the scoring model is a model based on the phase deviation rate weight, the zero-live current difference weight and the K value weight; The abnormal user priority list is generated according to the descending order of the scores.

8. The method for locating abnormal line loss in a transformer area according to claim 5, characterized in that: The abnormal line loss location method in the substation area also includes: The historical load curve of the electric meter of the user with abnormal electricity consumption is retrieved and matched with the current electricity consumption pattern. If the matching similarity is higher than a threshold, the user's electric meter is inspected on site and the priority list of the abnormal users is corrected.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores a computer program, and when the program is executed by the processor, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images