Loading [a11y]/accessibility-menu.js
Short term load forecasting model using support vector machine based on artificial neural network | IEEE Conference Publication | IEEE Xplore

Short term load forecasting model using support vector machine based on artificial neural network


Abstract:

A new sample preprocessing method is put forward in this paper. Firstly, the data points are classified into three types as the following: the high load type, the medium ...Show More

Abstract:

A new sample preprocessing method is put forward in this paper. Firstly, the data points are classified into three types as the following: the high load type, the medium load type and the low load type; then, the artificial neural network is adopted to forecast the load type of the predict point; finally a support vector machine forecasting model is created on the basis of data points whose load type is the same as the predict point. It is the first time for artificial neural network to be combined with support vector machine in short term load forecasting. The practical examples show that the model established in this paper is better than other methods in forecasting accuracy and computing speed.
Date of Conference: 18-21 August 2005
Date Added to IEEE Xplore: 07 November 2005
Print ISBN:0-7803-9091-1

ISSN Information:

Conference Location: Guangzhou, China

1. Introduction

The short-term power load forecasting is very important to the electric network's economic and stable running. With the development of the electric power market in China, a high forecasting precision is much more required than before. According to the research in Britain, an increase of forecasting error by 1% will result in an additional annual running cost of 17 million US dollars [1].

References

References is not available for this document.