Accelerated Energy Forecasting Models with Metaheuristics for Swift Solutions in Building Management

This work presents a CUDA-accelerated methodology for training multiple neural networks in parallel using population-based metaheuristics. The goal is to obtain fast and accurate short-term energy-forecasting models for time-sensitive building-management applications. We evaluate five metaheuristic optimizers and their memetic variants, for which a local-search stage based on the ADAM optimizer is incorporated. The models are assessed on eleven real-world energy-consumption time series using training time, root mean squared error (RMSE), mean absolute error (MAE), and normalized RMSE (NRMSE). The results show that the proposed memetic approaches are competitive under strict training-time budgets, although unconstrained ADAM remains a strong overall reference.