CN-122017456-A - Low-voltage meter data-based distribution short-period overload early warning method and equipment

CN122017456ACN 122017456 ACN122017456 ACN 122017456ACN-122017456-A

Abstract

The invention discloses a low-voltage meter data-based short-period overload early warning method and equipment, which comprise the steps of obtaining historical electric data, collecting readings of a low-voltage meter according to a preset time period, extracting load data, weather association features and event features of the historical electric data, calculating a risk prediction value of a target period according to the load data, the weather association features and the event features, obtaining a dynamic risk threshold according to a scene type corresponding to the target period, comparing the risk prediction value with the dynamic risk threshold to obtain a risk grade, and generating early warning information according to the risk grade. The load fluctuation trend can be reflected more accurately based on the acquisition of the electric data by the low-voltage meter, the dynamic risk threshold can be acquired according to the scene type corresponding to the target period, and the situation of false alarm and missing report is reduced after different dynamic risk thresholds are acquired according to different scenes, so that the accuracy of early warning of the fluctuation peak value of the power grid is improved.

Inventors

LIN ZHICHAO
HE MINMIN
HUANG BINGHUANG
LIN CONGHUI
XU HAOYU
HUANG ZHI
Chen Kunwen
YANG WENJIE
ZHANG SHANSHAN
Liao Shangyu

Assignees

国网福建省电力有限公司
国网福建省电力有限公司三明供电公司
国网福建省电力有限公司大田县供电公司

Dates

Publication Date: 20260512
Application Date: 20260212

Claims (10)

1. The utility model provides a join in marriage short period overload early warning method based on low pressure gauge data which characterized in that includes: acquiring historical electric data, wherein the historical electric data is obtained by acquiring readings of a low-voltage meter in a preset time period; Extracting load data, weather-related features and event features of the historical electrical data; Calculating according to the load data, the weather association characteristics and the event characteristics to obtain a risk prediction value of a target period; acquiring a dynamic risk threshold according to the scene type corresponding to the target period; and comparing the risk prediction value with the dynamic risk threshold value to obtain a risk grade, and generating early warning information according to the risk grade.
2. The method for providing short-term overload early warning based on low-voltage meter data according to claim 1, wherein the extracting load data, weather-related features and event features of the historical electrical data comprises: Classifying the historical electrical data through a clustering algorithm to obtain target classification load data and target weather association features and target event features corresponding to the target classification load data; the target classification load data includes resident load data, agricultural load data, and business load data.
3. The method for pre-warning the short-term overload based on the configuration of the low-voltage meter data according to claim 2, further comprising: calculating a classification risk prediction value corresponding to each target classification load data; acquiring a classification dynamic risk threshold corresponding to each target classification load data; comparing each classified risk prediction value with the corresponding classified dynamic risk threshold value to obtain a classified risk level; And generating comprehensive early warning information according to the classification risk grade corresponding to each target classification load data.
4. The method for providing short-term overload early warning based on low-voltage meter data according to claim 1, wherein the calculating the risk prediction value of the target period according to the load data, the weather association characteristic and the event characteristic comprises: ; Wherein, the Obtaining average load rate from the load data And load increase rate Obtaining a temperature correction coefficient through the weather-related features Obtaining holiday factors through the event characteristics 。
5. The method for providing short-term overload pre-warning based on low-voltage meter data according to claim 4, wherein the temperature correction coefficient is obtained by the weather-related features Comprising the following steps: ; Wherein, the Is the elastic coefficient; Is the real-time ambient temperature; is the reference temperature.
6. The method for providing short-term overload early warning based on low-voltage meter data according to claim 4, wherein the step of obtaining the dynamic risk threshold according to the scene type corresponding to the target period comprises the following steps: Acquiring a basic risk threshold according to the scene type corresponding to the target period; Judging whether the target period has sudden rise of air temperature or/and abrupt change of load growth rate, if so, reducing the basic risk threshold value to obtain the dynamic risk threshold value.
7. The method for pre-warning of short-term overload based on configuration of low-voltage meter data according to claim 1, wherein the step of obtaining the historical electrical data further comprises: and eliminating abnormal values, filling missing values and normalizing the historical electric data.
8. The method for providing short-term overload early warning based on low-voltage meter data according to claim 1, wherein the generating early warning information according to the risk level further comprises: acquiring an execution result of the early warning information; and optimizing the dynamic risk threshold according to the execution result.
9. The method for pre-warning of a configuration short-term overload based on low-voltage meter data according to claim 1, wherein the dynamic risk threshold comprises at least two sub-thresholds of different levels; the comparing the risk prediction value with the dynamic risk threshold value to obtain a risk level includes: And comparing the risk prediction value with each sub-threshold value in sequence to obtain the highest risk as the risk level.
10. An electronic device further comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor, when executing the computer program, implements the steps of a low pressure gauge data based configuration short-term overload warning method as claimed in any one of claims 1 to 9.

Description

Low-voltage meter data-based distribution short-period overload early warning method and equipment Technical Field The invention relates to the technical field of operation and maintenance of power grids, in particular to a low-voltage meter data-based short-period overload early warning method and equipment. Background In the running process of the power grid, the problem of short-term overload of the distribution transformer caused by seasonal load surge scenes such as spring festival return rural areas, busy agricultural irrigation, extremely high temperature and the like exists. Short-term overload of distribution network transformers can pose a serious threat to power system stability and equipment life. In the related art, transient load fluctuation is difficult to capture by a SCADA (supervisory control and data acquisition) system, so that the problem of peak value omission is frequent. Disclosure of Invention The invention aims to solve the technical problem of providing a low-voltage meter data-based short-period overload early warning method and equipment, and improving the accuracy of early warning of a power grid fluctuation peak value. In order to solve the technical problems, the invention adopts the following technical scheme: a low-voltage meter data-based configuration short-term overload early warning method comprises the following steps: acquiring historical electric data, wherein the historical electric data is obtained by acquiring readings of a low-voltage meter in a preset time period; Extracting load data, weather-related features and event features of the historical electrical data; Calculating according to the load data, the weather association characteristics and the event characteristics to obtain a risk prediction value of a target period; acquiring a dynamic risk threshold according to the scene type corresponding to the target period; and comparing the risk prediction value with the dynamic risk threshold value to obtain a risk grade, and generating early warning information according to the risk grade. In order to solve the technical problems, the invention adopts the following technical scheme: the electronic equipment further comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the steps in the low-voltage meter data-based short-term overload pre-warning method are realized when the processor executes the computer program. The method has the advantages that compared with a SCADA system, the method adopting 30-minute-level data sampling mode to collect the electric data based on the low-voltage meter can reflect the load fluctuation trend more accurately, when historical electric data is processed, the dynamic risk threshold value is obtained according to the scene type corresponding to the target period after the risk prediction value of the target period is calculated by extracting the load data, the weather association characteristic and the event characteristic of the historical electric data, so that the method can adapt to different scenes to obtain different dynamic risk threshold values, and then the risk prediction value is compared with the dynamic risk threshold value, so that the occurrence of false alarm missing is reduced, and the accuracy of early warning of the power grid fluctuation peak is improved. Drawings FIG. 1 is a flow chart of steps of a method for providing short-term overload warning based on low-voltage meter data in an embodiment of the invention; FIG. 2 is a flowchart showing steps of a method for providing short-term overload early warning based on low-voltage meter data according to an embodiment of the present invention; FIG. 3 is a schematic structural diagram of an overload early warning system with reduced period in an embodiment of the present invention; FIG. 4 is a load prediction output diagram of a low-voltage meter data-based configuration short-term overload early warning method in an embodiment of the invention; FIG. 5 is a graph showing the comparison of model performance at different early warning thresholds according to an embodiment of the present invention; FIG. 6 is a schematic diagram of an early warning interface output by a low-voltage meter data based short-period overload early warning method; fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. Detailed Description In order to describe the technical contents, the achieved objects and effects of the present invention in detail, the following description will be made with reference to the embodiments in conjunction with the accompanying drawings. Noun interpretation: In the related art, the traditional SCADA system adopts 30-minute-level data sampling, so that instantaneous load fluctuation is difficult to capture, and the problem of peak value missing detection is frequently caused. Studies have shown that when residential distribution changes are