New Zealand Journal of Agricultural Research abstracts

---

Application of a hybrid model on short-term load forecasting based on support vector machines (SVM)

Limin Ao

Department of Information Engineering
Northeast Dianli University
Jilin, Jilin 132012
China
aolm@163.com

Yongchun Wang

Changchun Heating Group Company Limited
Changchun, Jilin 130022
China

Qian Zhang

Baishan Electric Power Company
Baishan, Jilin 134300
China

Abstract    To overcome the shortcoming of single train set of support vector machines (SVM), a novel hybrid model based on dual support vector machines (DSVM) is presented in this paper. The first SVM takes the recent samples in the vicinity of the demand day as its train samples. It can capture the most recent dynamic changing load. The second one takes the same season’s load samples in historic years that have the similar attributes with the demand days as its train samples to reflect the season-period rule. Final results can be archived by converging both SVM. The raw dataset related to experiments was obtained from the EUNITE network. The experiments have proved that the accuracy of proposed model is better than traditional one in general and showed this model’s feasibility in practical application.

Keywords    daily load curve; empirical risk minimisation; kernel function; separating hyperplane; support vector machines

A07063; Online publication date 4 December 2007; Received and accepted 10 August 2007

New Zealand Journal of Agricultural Research, 2007, Vol. 50: 567–572
0028–8233/07/5005–0567 © The Royal Society of New Zealand 2007

PDF file of entire paper: Print-quality (707K) | screen-quality (294K)

---

This year's abstracts | Journal home page | All abstracts | Publishing home page