Application of LS-SVM in the Short-term Power Load Forecasting Based on QPSO

DOI

10.2991/lemcs-14.2014.52How to use a DOI?

Keywords

load forecasting;least square support vector machine(LS-SVM);quantum-behaved particle swarm optimization(QPSO);weather factor; date factor

Abstract

Electricity power load forecasting is the basis of power system planning and construction. In order to improve the precision, this paper proposes a model, in which the parameters in least square support vector machine (LS-SVM) are optimized by Quantum-behaved Particle Swarm Optimization (QPSO) and considering the weather and date factors. In the quantum space, particles can be search in the whole feasible solution space. We can obtain the global optimal solution. Therefore, QPSO algorithm is a global guaranteed algorithm, which is better than the original PSO algorithm in search capability. The simulation results show that the adaptive particle swarm optimization-based SVM load forecasting model is more accurate than the neural networks model and traditional LS-SVM model.

Copyright

© 2014, 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  - Xiaohui Liao
AU  - Qian Ding
PY  - 2014/05
DA  - 2014/05
TI  - Application of LS-SVM in the Short-term Power Load Forecasting Based on QPSO
BT  - Proceedings of the International Conference on Logistics, Engineering, Management and Computer Science
PB  - Atlantis Press
SP  - 225
EP  - 228
SN  - 1951-6851
UR  - https://doi.org/10.2991/lemcs-14.2014.52
DO  - 10.2991/lemcs-14.2014.52
ID  - Liao2014/05
ER  -