Short-term load forecasting based on correlation coefficient and weighted support vector regression machine

DOI

10.2991/icitmi-15.2015.181How to use a DOI?

Keywords

power system, support vector regression machine, short-term load forecasting, feature selection, correlation coefficient

Abstract

Accurate load forecasting can keep the safety of power grid operation stability and guarantee the normal production and life of society. Support vector regression machine is suitable to load forecasting. Its nature of learning method is to give a good forecasting ability according to a small amount of data information. An algorithm is combining weighted support vector regression machine with feature selection to predict electricity load. It is good significance to forecasting short-term load. The algorithm is used to have feature selection by correlation coefficient and forecast short-term load by weighted support vector regression machine on optimization of data sets. The simulation experimental results indicate that the algorithm made good predicting results and valuable attempts.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Limei Liu
PY  - 2015/10
DA  - 2015/10
TI  - Short-term load forecasting based on correlation coefficient and weighted support vector regression machine
BT  - Proceedings of the 4th International Conference on Information Technology and Management Innovation
PB  - Atlantis Press
SP  - 1077
EP  - 1081
SN  - 2352-538X
UR  - https://doi.org/10.2991/icitmi-15.2015.181
DO  - 10.2991/icitmi-15.2015.181
ID  - Liu2015/10
ER  -