Short-term load prediction method based on C-means clustering fuzzy rough set

Abstract

The invention discloses a short-term load prediction method based on a C-mean clustering fuzzy rough set. The method considers various types of influence factors influencing the short-term load prediction, collects the historical load data and the data of the load influence factors, performs the attribute reduction on the influence factors influencing the short-term load by using a fuzzy rough set, obtains a reduced environment attribute set influencing the short-term load, takes the attribute of the set as the input data and the short-term load as the output data to train a support vector machine model, and then uses the trained model for predicting the short-term load, so that the short-term load prediction method becomes faster and more accurate. According to the method, the problem that the membership function is selected in the fuzzy rough set due to the artificial subjective consciousness is solved, and the problem that the prediction speed and the prediction performance of the support vector machine are reduced due to the fact that an influence factor set is too redundant, is also solved.

Description

technical field [0001] The present invention relates to the technical field of power system load forecasting, and more specifically, relates to a short-term load forecasting method based on C-means clustering fuzzy rough sets. Background technique [0002] Due to the influence of policy factors, weather conditions, electricity consumption habits and some random factors, the load of the power system has volatility and randomness. The error of short-term load forecasting will bring many problems to the safe, reliable and stable operation of the power grid and dispatch management. The commonly used short-term load forecasting methods mainly include the traditional method represented by the time series method and the intelligent method represented by the neural network method. The principle and model of the time series method are relatively simple, but the weather that affects the load is not fully considered. , holidays and other influencing factors, this method is difficult t...

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a short-term load forecasting method based on C-means clustering fuzzy rough sets in order to solve the problems of slow calculation speed and low forecasting accuracy of existing short-term load forecasting methods

Images