Wind power forecasting using a GRU attention model for efficient energy management systems

Modern energy management systems play a crucial role in integrating multiple renewable energy sources into electricity grids, enabling a balanced supply-demand relationship while promoting eco-friendly energy consumption. Among these renewables, wind energy, with its environmental and economic advantages, poses challenges due to its inherent variability, demanding accurate prediction models for seamless integration. This paper presents an innovative hybrid deep learning model that integrates a gated recurrent unit (GRU)-based attention mechanism neural network for wind power generation forecast. The developed model's performance is compared against six other models, comprising four deep learning approaches-long short-term memory (LSTM), 1D convolutional neural network, convolutional neural short-term memory (CNN-LSTM), and convolutional long short-term memory (ConvLSTM)-as well as two machine learning models-random forest and support vector regression. The proposed GRU-based attention model demonstrates superior performance, particularly in 1-step to 3-step ahead predictions, with mean absolute error values of 59.45, 114.95, and 176.06, root mean square error values of 109.03, 201.83, and 296.55, normalized root mean square error values of 0.080, 0.148, and 0.218, and coefficient of determination (R2) values of 0.992, 0.975, and 0.948, for forecast horizons of 10, 20, and 30 min, respectively. These results underscore the robust predictive capability of the proposed algorithm. Significantly, this research constitutes the first application of the hybrid GRU-based attention model to the Yalova wind turbine dataset, achieving better accuracy when compared to prior studies utilizing the same data.