A Novel Deep Neural Network-Based Ensemble Approach for Forecasting Renewable Energy Consumption Using Metaheuristic Optimization and Nonlinear Prediction Stacking
TL;DR
A Meta-Optimized Deep Learning Fusion with Nonlinear Stacking (MODLF-NS) for forecasting RE usage, which combines Elman Recurrent Neural Networks (ERNN) with Particle Swarm Optimization (PSO) and Harris Hawks Optimization (HHO) to enhance model performance.
Abstract
The accurate prediction of renewable energy (RE) demand is vital for shaping effective national energy decisions, enabling energy providers to manage demand efficiently, reduce costs, and improve overall performance. Existing predictive models often struggle to capture the intricate, nonlinear patterns in RE consumption. Given the evolving nature of demand trends and the delayed impacts of RE adoption, predictive algorithms with a strong memory of past trends are crucial. This study introduces a Meta-Optimized Deep Learning Fusion with Nonlinear Stacking (MODLF-NS) for forecasting RE usage, which combines Elman Recurrent Neural Networks (ERNN) with Particle Swarm Optimization (PSO) and Harris Hawks Optimization (HHO) to enhance model performance. It also integrates a Radial Basis Function Multivariate Nonlinear Regression (RBF MNLR) meta-learner, uniquely designed to effectively interpret and combine the evidence-based predictions of the most synergistic algorithms. Our methodology introduces six main novelties: (1) exclusive use of ERNN for ensemble prediction, (2) novel integration of RBF MNLR for nonlinear meta-prediction, (3) incorporation of demographic, economic, industrial, and energy-related predictor variables, (4) implementation of HHO for deep learning optimization, (5) development of a hybrid metaheuristic-optimized stacking ensemble framework, and (6) practical application of stacking ensemble models, addressing real-world complexities and enabling proactive RE scenario analysis. Through rigorous evaluation using multi-country datasets (1993 ~ 2022), the MODLF-NS framework demonstrates superior performance, achieving an ensemble test R² of 0.91 for Iran and robust stacked generalization, significantly outperforming LightGBM (0.78), XGBoost (0.55), and CatBoost (0.48). Based on the model’s projections, renewable energy consumption in Iran is expected to reach approximately 41 TWh by 2027.