Short-term load prediction method based on improved least square support vector machine

Abstract

The invention relates to a short-term load prediction method based on an improved least square support vector machine, and the method comprises the following steps: 1, collecting historical load data, and carrying out the selection of the historical load data through a similar day method, and obtaining a training sample; 2, establishing a prediction model of a least square support vector machine to perform load prediction on the training sample, and when it is judged that the precision of a prediction result does not reach the standard, improving the prediction model of the least square support vector machine by using an improved artificial bee colony algorithm to obtain the improved prediction model of the least square support vector machine; 3, inputting the training sample into the improved prediction model of the least square support vector machine for load prediction and error analysis, and outputting a prediction result. Compared with the prior art, the method has the advantages that the numerical value of the load is accurately predicted before the power distribution network is subjected to power scheduling, the network loss is reduced, redundant power and economic loss are reduced, and the safety of the line is enhanced.

Description

Technical field [0001] The present invention relates to the field of distribution mesh load prediction techniques, and more particularly to a short-term load prediction method based on improved minimum multiplier support vector. Background technique [0002] Power distribution network load prediction technology is divided into three categories. The first category is a conventional load prediction method, using a load guide, similar day, Kalman filtering, index smoothization, and the like. The second category is a classic load prediction method, mainly including time series, regression analysis and trend extracts. The third type of method is the intelligent method. With the continuous application of a series of intelligent algorithms such as artificial neural network in recent years, more and more intelligent algorithms are also predicted on load prediction. The method of load prediction of intelligent algorithm is mainly used by artificial neural network method, support vector ma...

AI Technical Summary

Problems solved by technology

However, there are large human factors in the selection of optional parameters and kernel functions, which have a great impact on the prediction accuracy

Images