Wind Energy Prediction Using Artificial Neural Networks

Abstract

Renewable energy sources are one of the most vital alternatives to the conventional non-replenishable energy generating systems. Among several renewable power sources, the installed wind power capacity contributes to almost half of the total capacity. However, the variability and seasonality in wind speed, wind direction, atmospheric pressure, relative humidity and precipitation cause wind power generation to be highly volatile. In this regard, the present study aims to develop a wind speed prediction scheme using artificial neural network (ANN) techniques. Single step and multistep recurrent neural networks (RNNs) are implemented. The long short term memory (LSTM), rectified linear unit (ReLU) activation function and Adam optimization algorithm are considered to carry out daily to monthly prediction using the RNN process. Results, based on the data from Charanka solar energy park in Gujarat, indicate that root means square (RMS) errors for univariate single layer, multivariate single layer and univariate two-layer models are 0.601, 0.782 and 1.120, respectively. Therefore, a univariate single layer RNN architecture is recommended for wind speed prediction. We envisage that a multilayer RNN model may improve the prediction accuracy over longer period.