Short-term load prediction method based on similar day segmentation and LM-BP network

Abstract

The invention discloses a short-term load prediction method based on similar day segmentation and an LM-BP network. According to the method, through quantitative calculation of comprehensive correlative coefficients between meteorological factors and a historical load curve corresponding to a to-be-predicted day, the load curve of the to-be-predicted day is segmented, and according to prediction load curves within different time intervals, corresponding similar days are separately figured out; selection of the similar days is conducted through comprehensive consideration of a multi-feature similarity judgement standard of tendency similarity and shape similarity which are based on historical day meteorological similarity and historical load data. A similar day sample with the highest similarity is selected form historical data of the same kind; different neural network models are constructed through different training samples within different load prediction time intervals, and therefore the prediction precision of the neural network models is further improved. By means of the method, the calculation speed and convergence speed of a prediction algorithm are increased.

Description

Technical field [0001] The invention belongs to the field of power system load forecasting, and specifically relates to a short-term load forecasting method based on similar daily segmentation and LM-BP neural network. Background technique [0002] As an important part of the load forecasting work, short-term load forecasting of the power system is mainly to forecast the load in the next few hours, one day or several days. Its prediction accuracy is of great significance to improve the utilization rate of power generation equipment and the effectiveness of economic dispatch, and to develop and improve the current power market. Short-term load forecasting methods can be divided into classic forecasting methods and modern forecasting methods according to their development history. Traditional forecasting methods are mainly based on the theory of probability and statistics. Common methods include time series method and regression analysis method. The modern prediction methods comm...

AI Technical Summary

Problems solved by technology

Although the literature [6] proposed the method of segmenting the daily load curve and then selecting similar days in segments, this literature did not propose a method for quantitative calculation of the specific load curve segment, but simply carried out a qualitative calculation based on the load curve. section

Images