A review on artificial neural network models for short term wind power prediction

  • Joseph N. Mathenge Jomo Kenyatta University of Agriculture and Technology
  • D. K. Murage Jomo Kenyatta University of Agriculture and Technology
  • J. N. Nderu Jomo Kenyatta University of Agriculture and Technology
  • C. N. Muriithi Murang’a University of Technology

Abstract

There has been a growing global need to develop tools or models that are able to perform accurate wind power prediction in a power system. This arises from the fact that modern day power systems have inclined towards using renewable sources of energy; key among them being solar and wind. On one hand, solar power is relatively predictable and easily dispatchable while on the other hand, wind power is highly variable and intermittent hence making it have limited dispatchability. Current research is geared towards developing tools that can easily and accurately predict the short term wind power expected and hence make it a dispatchable resource. There have been many algorithms developed by researchers across the world to do short term prediction of wind power. However, one tool still remains supreme among all and that is the artificial neural network. This is due to its learning ability. This paper reviews the use of artificial neural networks in short term wind power prediction. The aim is to achieve accuracy that shall make wind power a fully dispatchable resource to ensure power systems gain from this free resource.
Keywords— Artificial Intelligence, Artificial Neural Networks, Short Term Wind Power Prediction.
Published
Jun 24, 2018
How to Cite
MATHENGE, Joseph N. et al. A review on artificial neural network models for short term wind power prediction. Proceedings of Sustainable Research and Innovation Conference, [S.l.], p. 54-58, june 2018. ISSN 2079-6226. Available at: <http://sri.jkuat.ac.ke/ojs/index.php/proceedings/article/view/663>. Date accessed: 23 feb. 2019.