Short-term wind speed forecasting for power generation in Hamirpur, Himachal Pradesh, India, using artificial neural networks

Abstract

In this paper, wind speed (WS) forecasting in the mountainous region of Hamirpur in Himachal Pradesh, India is presented. The time series utilized are 10 min averaged WS data are utilized. In order to do WS forecasting, ANN models are developed to forecast WS 10, 20, 30 min, and 1 h ahead. Statistical error measures such as the mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and mean error (ME) were calculated to compare the ANN models at 10, 20, 30 min, and 1 h ahead forecasting. It is found that statically error of 10 min ahead forecasting error is least. This study is useful for online monitoring of wind power.