Sumit Saroha* and S. K. Aggarwal
The estimation accuracy of wind power is an important subject of concern for reliable grid operations & taking part into open access. So, with an objective to improve the estimation accuracy of wind power, this article presents Wavelet Transform (WT) based General Regression Neural Network (GRNN) with statistical time series input selection technique. The results of proposed model have compared with four different (Naive, Feed Forward Neural Networks, Recurrent Neural Networks & GRNN) benchmark models on Mean absolute error (MAE) and mean absolute percentage error (MAPE) accuracy scale. The historical data used by presented models has been collected from Ontario Electricity Market for the year 2011-14 and tested for such a long time period of two years from November 2012 to October 2014 with one month estimation moving window.
General Regression Neural Network, Time Series, Wavelet Transform, Wind Power Forecasting
Electical & Electronics Engineering, SRM Institute of Science & Technology, Delhi NCR Campus, EIED, Thapar Institute of Engineering and Technology, Patiala, Punjab, 147001