A comparative analysis of ANN and chaotic approach-based wind speed prediction in India

Abstract

In this paper, we have discussed the application of the artificial neural networks in wind speed prediction. They will be used to predict the average monthly wind speed at three wind gauging stations in Gujarat, India. The wind speed data on an hourly basis are collected by NIWE (National Institute of Wind Energy) and located in the coastal areas of Western India, primarily Gujarat. The short-term and long-term data consisting of wind speeds have been considered for the period from 2015 to 2017. An artificial neural network is utilized for wind speed prediction using data measured from these stations for training and testing the given information. The data were studied using the nonlinear autoregressive models, NAR and NARX and the chaotic time series prediction models. The model is predicted using the historical data of the same station. The data are measured at a height of 100 m. The mean absolute percentage error (MAPE) and mean average error (MAE) concerning the predicted and measured wind speed were found to be 5.09 × 10−3, 5.33 × 10−3 and 2.9 × 10−3, respectively. The results of the ANN technique were compared with the Mackey–Glass equation-based time series prediction. Additionally, studies have been done on calculating the production and supply capacity of wind energy.