A method, device and medium for locating abnormal line loss in a transformer area based on multi-dimensional analysis

Abstract

This application relates to the field of substation line loss detection, and particularly to a method, device, and medium for abnormal positioning of substation line loss based on multi-dimensional analysis. The method includes: obtaining time-sharing power consumption data of a target substation, calculating the substation line loss rate according to the time-sharing power consumption data, and extracting the time-period fluctuation characteristics of the substation line loss rate. Based on the mutation time period of the time-period fluctuation characteristics, calculate the phase deviation rate of the user electricity meters, and mark the phases with a phase deviation rate exceeding the threshold as abnormal phases. Compare the zero-fire line current difference of the user electricity meters with abnormal phases, and screen out the current imbalance user electricity meters with a zero-fire line current difference exceeding the tolerance. Calculate the K value of the current imbalance user electricity meters, and lock the abnormal electricity consumption user electricity meters through the K value. It reduces the misjudgment rate of substation line loss anomalies, improves the efficiency of abnormal positioning of substation line loss, does not require strict experience requirements for technicians to execute the method of this application, and can directly locate the anomaly to the user dimension.

Description

Technical Field

[0001] The present application relates to the field of distribution transformer line loss detection, and particularly to a method, device and medium for abnormal location of distribution transformer line loss based on multi-dimensional analysis. Background Art

[0002] With the deepening of the power system reform, power supply enterprises are faced with the major tasks of energy conservation and loss reduction, and tapping potential and increasing efficiency. Strengthening line loss management has become the only way for power supply enterprises to improve the quality and efficiency of operation and management. Efficient line loss management will directly affect power supply efficiency and economy. However, due to the complex and diverse reasons for unqualified distribution transformer line losses, existing technologies often rely on experienced technicians to manually check for abnormal distribution transformer line losses from multiple angles and links. This results in technicians having to face a vast amount of electricity consumption data, investing a large amount of manual effort, with low checking efficiency, and having strict experience requirements for technicians. Summary of the Invention

[0003] In order to solve the problem of low efficiency in abnormal location of distribution transformer line losses in the prior art, the present application provides a method, device and medium for abnormal location of distribution transformer line loss based on multi-dimensional analysis. In the first aspect, the method provided by the present application includes the following steps:

[0004] Obtain the time-of-use power consumption data of the target distribution transformer, calculate the line loss rate of the distribution transformer according to the time-of-use power consumption data, and extract the time-of-fluctuation characteristics of the line loss rate of the distribution transformer. The time-of-use power consumption data comes from user electricity meters and the total meter on the power supply side;

[0005] Based on the mutation time period of the time-of-fluctuation characteristics, calculate the phase deviation rate of the user electricity meter, and mark the phase with the phase deviation rate exceeding the threshold as the abnormal phase. The phase deviation rate is obtained based on the phase-by-phase power consumption data;

[0006] Compare the zero-fire line current difference of the user electricity meter with an abnormal phase, and screen out the current-unbalanced user electricity meters with the zero-fire line current difference exceeding the tolerance. The zero-fire line current difference is obtained based on the zero-fire line current data;

[0007] Calculate the K value of the current-unbalanced user electricity meter, and lock the abnormal electricity-consuming user electricity meter through the K value. The K value is the ratio of the power change amount of the current-unbalanced user electricity meter to the change amount of the line loss rate of the distribution transformer.

[0008] Specifically, the phase-by-phase power consumption data comes from the user electricity meter, and the method for abnormal location of distribution transformer line loss further includes calculating the phase deviation rate of each phase power and the total power of the user electricity meter according to the phase-by-phase power consumption data.

[0009] Specifically, the zero-line and live-line current data comes from the user's electricity meter, and the method for locating abnormal substation area line losses further includes comparing the zero-line and live-line current differences of the zero-line and live-line current data.

[0010] Specifically, the method for locating abnormal substation area line losses further includes:

[0011] Identifying the inflection points of the period fluctuation characteristics through a sliding window, and marking M periods before and after the inflection points as the mutation periods, where M is an adjustable value set according to the historical data of the load fluctuation of the target substation area.

[0012] Specifically, mark the user electricity meters with abnormal phases as first-level abnormal user electricity meters, generate an abnormal user priority list based on the first-level abnormal user electricity meters, the current imbalance user electricity meters, and the electricity consumption abnormal user electricity meters, and classify and process the user abnormal situations according to the abnormal user priority list.

[0013] Specifically, the method for calculating the K value of the current imbalance user electricity meter includes:

[0014] Select the mutation inflection points in the mutation period, and calculate the power change amount δ Q _user of the user electricity meter and the change amount δ Q _loss of the substation area line loss rate at the mutation inflection point;

[0015] Eliminate the mutation inflection points corresponding to the substation area line loss rate change amount δ Q _loss that is less than the noise threshold, and calculate for the remaining mutation inflection points K =δ Q _user / δ Q _loss to obtain the K value.

[0016] Specifically, the method for generating the abnormal user priority list includes:

[0017] Score the usage scoring model with abnormal marks, where the abnormal marks are one or more of the first-level abnormal user electricity meters, the current imbalance user electricity meters, and the electricity consumption abnormal user electricity meters, and the scoring model is a model based on the phase deviation rate weight, the zero-line and live-line current difference weight, and the K value weight;

[0018] Generate the abnormal user priority list in descending order of scores.

[0019] Specifically, the method for locating abnormal substation area line losses further includes:

[0020] Retrieve the historical load curve of the electricity meter of the user with abnormal electricity consumption, match it with the current electricity consumption pattern. If the matching similarity is higher than the threshold, conduct on-site inspection of the user's electricity meter and correct the abnormal user priority list.

[0021] In a second aspect, the electronic device of the present application includes a processor and a memory. The memory stores a computer program, and when the program is executed by the processor, the steps of the method as described above are implemented.

[0022] In a third aspect, the computer-readable storage medium of the present application stores a computer program, and when the program is executed by the processor, the steps of the method as described above are implemented.

[0023] The present application has the following technical effects:

[0024] Reduce the misjudgment rate of abnormal substation area line losses, improve the efficiency of locating abnormal substation area line losses, the method of the present application can be executed without strict experience requirements for technicians, and the abnormality can be directly located to the user dimension. Description of the Drawings

[0025] By referring to the accompanying drawings and reading the following detailed description, the above and other purposes, features, and advantages of the exemplary embodiments of the present application will become easily understandable. In the drawings, several embodiments of the present application are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0026] Figure 1 is the flowchart of the analysis of abnormal substation area line losses in the embodiment of the present application;

[0027] Figure 2 is the flowchart of the method for locating abnormal substation area line losses based on multi-dimensional analysis in the embodiment of the present application. Detailed Embodiments

[0028] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0029] 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, in the new situation of the power system reform, power supply must further strengthen the management of substation area line losses, promote the improvement of the lean management level of substation area line losses, and effectively reduce the substation area line loss rate. Improving the ability and effectiveness of line loss governance is an inevitable requirement for enhancing the market competitiveness of enterprises.

[0030] At present, the reasons for the unqualified line losses in the substation area are complex and diverse. A large amount of big data has not been effectively analyzed and utilized, and grass-roots front-line employees lack effective line loss analysis skills in the substation area, resulting in problems such as inefficient on-site line loss work analysis, unclear rectification effects of line losses in the substation area, and disproportionate input-output of labor, which pose a great obstacle to the rectification work of line losses in the substation area.

[0031] Based on the above situation, in order to solve the problems of difficult and inefficient line loss analysis in grass-roots teams, this embodiment proposes a method for abnormal location of line losses in the substation area based on multi-dimensional analysis, and develops a calculation software based on the Vb.net language that can be used to execute these steps, solving the problems restricting the analysis duration and efficiency of line losses in the substation area. The popularization and application of this calculation software can effectively improve the work efficiency of line loss management, solve the problem of long time-consuming line loss analysis in grass-roots front-line teams, save energy and reduce losses for enterprises, improve benefits, and enhance the market competitiveness of enterprises.

[0032] The abnormal analysis of line losses in the substation area generally follows Figure 1 the process shown, and it can be seen from Figure 1 the process that the abnormal analysis of line losses in the substation area generally includes three steps: analysis of line loss change trend, analysis of basic information of the substation area, and in-depth analysis of each user in the substation area. According to the statistical table of the average time-consuming of each process in the abnormal line loss analysis of 10 power supply stations under the jurisdiction of Wuhu Power Supply Company in Wanzai District in 2022 (Table 1), the average time-consuming of the abnormal line loss work in the substation area is 259.1 minutes, of which the average time-consuming for in-depth analysis of each user in the substation area is 221.3 minutes, accounting for 85.5%, and the extreme difference is 60, with a relatively large value. Therefore, the main problem is the long time-consuming for in-depth analysis of each user in the substation area, and reducing the in-depth analysis time will effectively improve the work efficiency of line loss management in the substation area.

[0033] Table 1 Statistical table of the average time-consuming of each process in the abnormal line loss analysis of 10 power supply stations under the jurisdiction of Wuhu Power Supply Company in Wanzai District in 2022

[0034]

[0035] Taking the above-mentioned main problem of the long time-consuming for in-depth analysis of each user in the substation area as the research direction, this embodiment proposes a method as Figure 2 shown, including the following steps:

[0036] Obtain the time-of-use power consumption data of the target substation area, calculate the line loss rate of the substation area according to the time-of-use power consumption data, and extract the time-period fluctuation characteristics of the line loss rate of the substation area. The time-of-use power consumption data comes from the user electricity meter and the total power supply side meter. The user electricity meter and the total power supply side meter support a maximum acquisition accuracy of 10 times / minute, and can record three-phase currents independently. The user electricity meter can also support the analysis of neutral line current and phase line current;

[0037] For the mutation period based on the time period fluctuation characteristics, calculate the phase deviation rate of the user's electricity meter, mark the phase with a phase deviation rate exceeding the threshold as the abnormal phase, and the phase deviation rate is obtained based on the split-phase power data. In the calculation software of this embodiment, a time-sharing calculation unit is set to identify the inflection point of the sudden increase in the line loss rate by using the sliding window algorithm, and mark the M cycles before and after the inflection point as the abnormal period. M is adaptively adjusted according to the historical load curve of the transformer area. For example, for the commercial area transformer area with frequent load fluctuations, M can be set to 6 cycles, while for the residential area transformer area, it is set to 4 cycles to balance the detection sensitivity and calculation efficiency.

[0038] Compare the zero-fire line current difference of the user's electricity meter with abnormal phases, and screen out the current imbalance user's electricity meters with a zero-fire line current difference exceeding the tolerance. The zero-fire line current difference is obtained based on the zero-fire line current data;

[0039] Calculate the K value of the current imbalance user's electricity meter, and lock the abnormal electricity consumption user's electricity meter through the K value. The K value is the ratio of the power change amount of the current imbalance user's electricity meter to the change amount of the transformer area line loss rate.

[0040] Specifically, the split-phase power data comes from the user's electricity meter. The transformer area line loss abnormal positioning method further includes calculating the phase deviation rate of the phase power and the total power of the user's electricity meter according to the split-phase power data.

[0041] Specifically, the zero-fire line current data comes from the user's electricity meter. The transformer area line loss abnormal positioning method further includes comparing the zero-fire line current difference of the zero-fire line current data.

[0042] Specifically, the transformer area line loss abnormal positioning method further includes:

[0043] Identify the inflection point of the time period fluctuation characteristics through the sliding window, and mark the M cycles before and after the inflection point as the mutation period. M is an adjustable value set according to the historical data of the load fluctuation of the target transformer area.

[0044] Specifically, mark the user's electricity meter with an abnormal phase as the first-level abnormal user's electricity meter, generate an abnormal user priority list according to the first-level abnormal user's electricity meter, the current imbalance user's electricity meter, and the abnormal electricity consumption user's electricity meter, and classify and process the user's abnormal situation according to the abnormal user priority list.

[0045] Specifically, the method for calculating the K value of the current imbalance user's electricity meter includes:

[0046] Select the mutation inflection point in the mutation period, and calculate the power change amount δ Q _user of the user's electricity meter and the change amount δ Q _loss of the transformer area line loss rate at the mutation inflection point;

[0047] Eliminate the change amount δ of the transformer area line loss rate that is less than the noise threshold QThe mutation inflection point corresponding to _loss is calculated for the remaining mutation inflection points K = δ Q _user / δ Q The K value is obtained from _loss.

[0048] Specifically, the method for generating a list of abnormal user priorities includes:

[0049] Score the usage scoring model with abnormal markings, where the abnormal markings are one or more of the first-level abnormal user electricity meters, current imbalance user electricity meters, and abnormal electricity consumption user electricity meters, and the scoring model is a model based on the phase deviation rate weight, the zero-fire wire current difference weight, and the K value weight;

[0050] Generate a list of abnormal user priorities in descending order according to the scores.

[0051] Specifically, it is characterized in that the method for locating abnormal line losses in a distribution area further includes:

[0052] Retrieve the historical load curve of the abnormal electricity consumption user electricity meter and match it with the current electricity consumption pattern. If the matching similarity is higher than the threshold, conduct on-site detection of the user electricity meter and correct the list of abnormal user priorities.

[0053] The calculation software of this embodiment can run through a multi-core processor and a cache memory. The computer program of the above method is stored in the memory. The processor schedules tasks such as time-sharing, phase-separation, zero-fire wire comparison, and K value calculation through a parallel computing framework, and uses a message queue to achieve 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 applicable to the grid architecture of cloud-edge collaboration.

[0054] Before implementing the method and calculation software proposed in this embodiment, the Wuhu Power Supply Company in Wanzai District used tools such as Excel to assist manual calculation and analysis, which took about three and a half hours on average. After implementing the method and calculation software proposed in this embodiment for 10 randomly selected abnormal distribution areas, according to the recorded software operation schedule (Table 2), it can be seen that the software operation time, that is, the range of the abnormal line loss location time in the distribution area, is 6 ± 0.4 (min), the upper tolerance limit TU = 6.4 (min), the lower tolerance limit TL = 5.6 (min), then the process capability index is calculated as:

[0055]

[0056] The process capability index is at the first level, the process capability index is sufficient, and compared with manual intuitive analysis, the analysis accuracy rate ≥ 95%.

[0057] Table 2 Software operation schedule

[0058]

[0059] Obviously, the embodiments described above are some, but not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without creative efforts shall fall within the scope of protection of this application.

[0060] It should be understood that when the claims, the description, and the drawings of this application use terms such as "first" and "second", they are only used to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" used in the description and claims of this 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 combinations.

Claims

1. A method for abnormal positioning of substation area line loss based on multi-dimensional analysis, characterized in that, It includes the following steps: Obtain the time-of-use power consumption data of the target substation area, calculate the substation area line loss rate according to the time-of-use power consumption data, and extract the time period fluctuation characteristics of the substation area line loss rate. The time-of-use power consumption data comes from the user electricity meters and the total power supply side meter; Based on the mutation time period of the time period fluctuation characteristics, calculate the phase deviation rate of the user electricity meters, and mark the phase with the phase deviation rate exceeding the threshold as the abnormal phase. The phase deviation rate is obtained based on the phase-by-phase power consumption data; Compare the zero-fire wire current difference of the user electricity meters with abnormal phases, and screen out the current imbalance user electricity meters with the zero-fire wire current difference exceeding the tolerance. The zero-fire wire current difference is obtained based on the zero-fire wire current data; Calculate the K value of the current imbalance user electricity meter, and lock the abnormal electricity consumption user electricity meter through the K value. The K value is the ratio of the power change amount of the current imbalance user electricity meter to the change amount of the substation area line loss rate; Among them, the phase-by-phase power consumption data comes from the user electricity meters. The substation area line loss abnormal positioning method further includes calculating the phase deviation rate of the phase-by-phase power consumption and the total power of each phase of the user electricity meter according to the phase-by-phase power consumption data.

2. The method for abnormally locating the line loss in a transformer substation area according to claim 1, wherein The zero-fire wire current data comes from the user electricity meters. The substation area line loss abnormal positioning method further includes comparing the zero-fire wire current difference of the zero-fire wire current data.

3. The method for abnormal positioning of line loss in the substation area according to claim 1, characterized in that, The substation area line loss abnormal positioning method further includes: Identify the inflection point of the time period fluctuation characteristics through a sliding window, and mark the M cycles before and after the inflection point as the mutation time period. M is an adjustable value set according to the historical data of the load fluctuation of the target substation area.

4. The method for abnormal positioning of substation area line loss according to claim 1, characterized in that, Mark the user electricity meters with abnormal phases as first-level abnormal user electricity meters, generate an abnormal user priority list according to the first-level abnormal user electricity meters, the current imbalance user electricity meters, and the abnormal electricity consumption user electricity meters, and classify and process the user abnormal situations according to the abnormal user priority list.

5. The method for abnormal positioning of substation area line loss according to claim 1, wherein The method for calculating the K value of the current imbalance user electricity meter includes: Select the mutation inflection point in the mutation period, and calculate the power change amount δ of the user's electricity meter at the mutation inflection point Q _user and the change amount δ Q _loss; Eliminate the change amount δ of the line loss rate of the substation area that is less than the noise threshold Q The mutation inflection point corresponding to _loss, calculate for the remaining mutation inflection points K =δ Q _user / δ Q _loss to obtain the K value 6. The method for abnormally locating the line loss in a transformer substation area according to claim 4, wherein The method for generating the abnormal user priority list includes: Score the electricity meters with abnormal marks using a scoring model. The abnormal marks are one or more of the first-level abnormal user electricity meters, the current imbalance user electricity meters, and the abnormal electricity consumption user electricity meters. The scoring model is a model based on the phase deviation rate weight, the zero-fire wire current difference weight, and the K value weight; Generate the abnormal user priority list in descending order of scores.

7. The method for abnormal positioning of the line loss in the substation area according to claim 4, wherein The substation area line loss abnormal positioning method further includes: Retrieve the historical load curve of the abnormal electricity consumption user electricity meter, match it with the current electricity consumption mode. If the matching similarity is higher than the threshold, conduct on-site detection of the user electricity meter and correct the abnormal user priority list.

8. An electronic device, characterized in that, It includes a processor and a memory. The memory stores a computer program, and when the program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

Images