A Hybrid LSTM-Single Candidate Optimizer Model for Short-Term Wind Power Prediction

Accurate prediction of wind energy plays a vital role in maintaining grid stability and supporting the broader shift toward renewable energy systems. Nevertheless, the inherently variable nature of wind and the intricacy of high-dimensional datasets pose major obstacles to reliable forecasting. To address these difficulties, this study presents an innovative hybrid method for short-term wind power prediction by combining a Long Short-Term Memory (LSTM) network with a Single Candidate Optimizer (SCO) algorithm. In contrast to conventional techniques that rely on random parameter initialization, the proposed LSTM-SCO framework leverages the distinctive capability of SCO to work with a single candidate solution, thereby substantially reducing the computational overhead compared to traditional population-based metaheuristics. The performance of the model was benchmarked against various classical and deep learning models across datasets from three geographically diverse sites, using multiple evaluation metrics. Experimental findings demonstrate that the SCO-optimized model enhances prediction accuracy by up to over standard LSTM implementations.