A MASPSO-Optimized CNN–GRU–Attention Hybrid Model for Short-Term Wind Speed Forecasting

Short-term wind speed forecasting is challenged by the nonlinear, non-stationary, and highly volatile characteristics of wind speed series, which hinder the performance of traditional prediction models. To improve forecasting capability, this study proposes a hybrid modeling framework that integrates multi-strategy adaptive particle swarm optimization (MASPSO), a convolutional neural network (CNN), a gated recurrent unit (GRU), and an attention mechanism. Within this modeling architecture, the CNN extracts multi-scale spatial patterns, the GRU captures dynamic temporal dependencies, and the attention mechanism highlights salient feature components. MASPSO is further incorporated to perform global hyperparameter optimization, thereby improving both prediction accuracy and generalization. Evaluation on real wind farm data confirms that the proposed modeling framework delivers consistently superior forecasting accuracy across different wind speed conditions, with significantly reduced prediction errors and improved robustness in multi-step forecasting tasks.