Forecasting of wind energy generation using Self-Organizing Maps and Extreme Learning Machines

Tan, KH; Logenthiran, T; Woo, WL

doi:10.1109/TENCON.2016.7848039

Forecasting of wind energy generation using Self-Organizing Maps and Extreme Learning Machines

Lookup NU author(s): Dr Thillainathan Logenthiran, Dr Wai Lok Woo

Downloads

Accepted version [.pdf]

Licence

This is the authors' accepted manuscript of a conference proceedings (inc. abstract) that has been published in its final definitive form by IEEE, 2016.

For re-use rights please refer to the publisher's terms and conditions.

Abstract

This paper aims to forecast wind energy generation. With accurate forecasting of energy generation, it will aid the energy sector in managing of stability and grid planning for supplied energy. The main focus of this project is Artificial Neural Network (ANN) while the training algorithms used in this project is a combination of Self-Organizing Maps (SOM) and Extreme Learning Machines (ELM). Furthermore, the training algorithm is applied into MATLAB and simulated several times in order to obtain the optimal parameters setting so as to accurately forecast wind energy generation.