Wind Resource Assessment using Machine Learning Algorithm
Stanly Abraham S1, Meenal R2, Abishekkevin K, Pravina M3, Belsha Jackline Princess J4
1Stanly Abraham S*, Karunya Institute of Technology and Sciences, Coimbatore – 641114, Tamilnadu, India.
2Abishekkevin K, Karunya Institute of Technology and Sciences, Coimbatore – 641114, Tamilnadu, India.
3R. Meenal, Karunya Institute of Technology and Sciences, Coimbatore, Tamilnadu, India.
4Belsha Jackline Princess J, Karunya Institute of Technology and Sciences, Coimbatore, Tamilnadu, India.
5Pravina M, Karunya Institute of Technology and Sciences, Coimbatore – 641114, Tamilnadu, India.
Manuscript received on March 30, 2020. | Revised Manuscript received on April 05, 2020. | Manuscript published on April 30, 2020. | PP: 1062-1066 | Volume-9 Issue-4, April 2020. | Retrieval Number: D7836049420/2020©BEIESP | DOI: 10.35940/ijeat.D7836.049420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The wind speed prediction is very important for wind resource assessment, renewable energy integration in to the electricity grid, electricity marketing and so on. Because of the arbitrary fluctuation characteristics of wind, the prediction results may change quickly. This enhances the significance of the accurate wind speed prediction The objective of this paper is to predict the wind speed for Tamil Nadu cities using machine learning algorithm. There are three broad categories of wind forecasting models namely physical model, statistical and computational models and hybrid models. Artificial Neural Network is the most commonly used method for wind speed prediction. Recently machine learning and deep learning algorithms are widely used for forecasting applications. In this work wind speed is predicted for Tamil Nadu cities using decision tree regression algorithm. The Machine Learning (ML) model is trained using measured wind speed data for six cities of India collected from India Meteorological Department (IMD), Pune. The ML model based on decision tree regression algorithm is good in prediction with better performance metrics of MSE in the range of 0.3 to 1.2 m/s and R2 =0.87.
Keywords: Machine learning; wind speed; prediction; forecasting; ANN