R.-J. Kuo

Using hybrid machine learning model with an improved driving training-based optimization algorithm for wind power forecasting

A hybrid model combining TCN and NLSTM to leverage the strengths of both architectures is proposed, achieving up to a 12.7% reduction in Root Mean Square Error (RMSE) and a mutation-inspired modification of the Driving Training-Based Optimization algorithm dynamically tunes the model’s hyperparameters.