A Novel Integration Forecasting Approach for Short-Term Wind Power

DOI

10.2991/eame-17.2017.18How to use a DOI?

Keywords

wind speed, power forecasting; autoregressive time series; integration forecasting model; generalized regression neural network

Abstract

As a kind of renewable energy, wind power energy has the characteristics of randomness and intermittence. The integration of wind farm will affect the safe and stable operation of power grid. Therefore, the accuracy of wind power output prediction is very important for power system operation and power quality. In order to improve the accuracy of short-term wind power forecasting, this paper presents a novel integration prediction model base on wind power and wind speed. The combination forecasting model of autoregressive time series and generalized regression neural network is used to forecast the wind power generation directly and forecast the wind power generation indirectly by wind speed. The final prediction model is obtained by combining the two models .The results show that the prediction accuracy of the model is improved effectively.

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  - Kailin Zhao
AU  - Lingyun Wang
AU  - Qiwei Ma
PY  - 2017/04
DA  - 2017/04
TI  - A Novel Integration Forecasting Approach for Short-Term Wind Power
BT  - Proceedings of the 2017 2nd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2017)
PB  - Atlantis Press
SP  - 73
EP  - 76
SN  - 2352-5401
UR  - https://doi.org/10.2991/eame-17.2017.18
DO  - 10.2991/eame-17.2017.18
ID  - Zhao2017/04
ER  -