Application of Support Vector Machine Based on Particle Swarm Optimization in Low Voltage Line Loss Prediction

DOI

10.2991/jimet-15.2015.35How to use a DOI?

Keywords

support vector machine; particle swarm optimization; line loss prediction

Abstract

As low voltage line loss calculation is the difficulty of line loss, accurate prediction of low voltage line loss rate can guide energy-saving and consumption-reducing work effectively. In this paper, the support vector machine (SVM) Parameters Optimization Algorithm based on particle swarm optimization (PSO) is used to predict the low voltage line loss rate. After the analysis of the related factors that affecting line loss, the power supply average length of lines average capacity of transformers and maximum load are selected as parameters for the training of SVM prediction model, then use the line loss prediction model to predict the low voltage line loss rate. Predict results of model testing which uses part of the known data in typical year show the average prediction error is only1.92%, which can give a strong support for this line loss prediction model.

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  - Tan Min
AU  - Wang Xinghua
AU  - Li Qing
AU  - Guo Lexin
AU  - Yu Tao
AU  - Feng Yongkun
PY  - 2015/12
DA  - 2015/12
TI  - Application of Support Vector Machine Based on Particle Swarm Optimization in Low Voltage Line Loss Prediction
BT  - Proceedings of the 2015 Joint International Mechanical, Electronic and Information Technology Conference
PB  - Atlantis Press
SP  - 193
EP  - 196
SN  - 2352-538X
UR  - https://doi.org/10.2991/jimet-15.2015.35
DO  - 10.2991/jimet-15.2015.35
ID  - Min2015/12
ER  -