Short-term Load Combination Forecasting Based on Evidential Theory Combines with Ant Colony Algorithm-Neural Network

DOI

10.2991/mcei-16.2016.55How to use a DOI?

Keywords

Evidence theory; Ant colony algorithm; Neural network; Load forecasting; Combination forecasting

Abstract

In order to improve the accuracy of short-term load forecasting, a combination prediction method is applied of evidence theory combines with ant colony algorithm-neural network. According to a city's actual load data, the ant colony algorithm-neural network as single mode1 is used to its initial forecast. Then the BP and RBF neural network are selected to get the credibility of each model, with forecasting errors and environmental influence. And the evidence theory was employed to fuse them to obtain the combination weight, so short-term load forecast was fulfilled. Examples show that the method by evidence theory to determine the best combination of weight, thus fitting error is small, and with high prediction accuracy. The combination method is suitable for short-term load forecasting prediction and has a certain application value.

Copyright

© 2017, 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  - Jing Hua
AU  - Li Ai
AU  - Jiatang Cheng
PY  - 2016/12
DA  - 2016/12
TI  - Short-term Load Combination Forecasting Based on Evidential Theory Combines with Ant Colony Algorithm-Neural Network
BT  - Proceedings of the 2016 6th International Conference on Mechatronics, Computer and Education Informationization (MCEI 2016)
PB  - Atlantis Press
SP  - 262
EP  - 267
SN  - 1951-6851
UR  - https://doi.org/10.2991/mcei-16.2016.55
DO  - 10.2991/mcei-16.2016.55
ID  - Hua2016/12
ER  -