Electric network metering early-warning system and method based on load characteristic pre-estimation

Abstract

The invention discloses an electric network metering early-warning system and method based on load characteristic pre-estimation. Historical data of power load is collected, a load curve is drafted, a sample set is constructed, and a K-MEDOIDS algorithm is used to determine a typical load curve of a power user; sample data is segmented in a unified manner according to time interval, multiple targets are used as characteristic vectors, and a characteristic index is selected from a typical daily load curve; and a clustering result is combined with a Markov chain to establish a prediction chain, prediction is carried out, a prediction result is compared with actual measurement data detected by a metering device to determine whether invalid power utilization occurs and whether the metering device works normally, and it is determined that invalid power utilization occurs or the metering device is abnormal, invalid power utilization or the metering device is marked, and early warning is carried out.

Description

technical field [0001] The invention relates to a grid metering and early warning system and method based on load characteristic estimation. Background technique [0002] In recent years, with the development of the economy, the demand for electricity is increasing. During many peak hours, there will be a tight supply and demand of electricity. Whether it is an individual user or a large enterprise user, it is necessary to measure and calculate electricity consumption and electricity charges. It is very important to be able to measure and calculate correctly, and it can also be of great help to the safe and efficient operation of the power grid. [0003] Therefore, it is very important to be able to accurately count the user's power consumption during metering, and to judge whether the value is within the normal range, and there is no leakage, stealing or stealing of electricity. [0004] However, the current monitoring of electricity consumption mainly relies on manual wo...

AI Technical Summary

Problems solved by technology

Kalman filtering can predict the predicted value at the next moment through the state space model. The disadvantage is that when the statistical characteristics of the noise are completely unknown or partially known, the filtering efficiency will be too low or even invalid.

The exponential smoothing method is simple and easy to implement. It uses a weighted moving average method to eliminate the fluctuation data of the historical power load, and can find out the development trend of the power load. It is suitable for data preprocessing. The disadvantage is that it will produce a lag effect and seriously affect the forecast. precision

[0006] At the same time, the current forecasting methods, when establishing load optimization characteristic indicators in the data preprocessing process, are currently too single to achieve multi-objective load characteristic analysis, and lack comprehensive consideration of uncertainty and multi-objective attributes. The clustered results cannot eliminate the influence of uncertain factors under the multi-objective framework, and it is difficult to meet the actual operation requirements

Images