A Novel Deep Neural Network-Based Ensemble Approach for Forecasting Renewable Energy Consumption Using Metaheuristic Optimization and Nonlinear Prediction Stacking
2026· Journal of Environmental Informatics· 0 citations
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.
This study presents a comprehensive analysis of renewable energy forecasting using deep learning techniques, focusing on short-term and medium-term prediction horizons, and shows that deep learning models provide significantly better forecasting accuracy, particularly under highly variable weather conditions.
Lucas Martin, Chloe Bernard· International Journal of Mod...· 0 citations
The paper gives a Hybrid Evolutionary Optimization and Neural Network Model of climate adaptive renewable energy forecasting. The need to increase renewable energy has led to the creation of more precise and flexible forecasting tools. This paper integrates evolutionary optimization techniques, including Genetic algorithms (GA) and Particle Swarm optimization (PSO), with deep learning neural networks, specifically Long short-term memory (LSTM), to predict renewable energy production using solar and wind energy. The methodology will consist of gathering up-to-date environmental measurements (temperature, wind speed, and solar radiation), as well as the previous data on energy generation by using renewable resources. The hyperparameters of the deep learning model are optimized using evo0.lutionary optimization algorithms to make accurate predictions of the model under different climatic conditions. The proposed hybrid model was compared to the conventional models, such as ARIMA and SVM, and the outcomes indicate that it has a better performance with respect to the accuracy of the prediction, the Mean Squared Error (MSE), the Root Mean Squared Error (RMSE), and the R2 value. The hybrid model also saves a lot of time when it comes to predicting failure, thus it is more effective in proactive energy management. Also, the model can be adjusted to changing conditions of the environment and offers real-time predictions and useful information concerning the optimization of energy production and its integration into the power grid. The results indicate that this mixed method has the potential to maximize the accuracy and effectiveness of renewable energy prediction, which will further result in improved energy grid management and low operation costs.
Nidhi Mishra, Aakansha Soy· 2026 International Conferenc...· 0 citations
Accurately forecasting solar power is essential for secure and efficient operations of contemporary power systems, particularly in the smart grid and renewable energy integration context. In this paper, we present a new hybrid deep learning model, the BiLSTM Model using Improved PSO (BiLSTM-IPSO), for improved short-term prediction of solar power, which incorporates the Bidirectional Long Short-Term Memory (BiLSTM) model with an Improved Particle Swarm Optimization (IPSO) algorithm. The IPSO algorithm successively arranges the BiLSTM hyperparameters with chaotic initialization, adaptive inertia weights, and velocity clamping, to converge globally and avoid stagnating locally. The proposed BiLSTM-IPSO model performance is compared with various state-of-the-art techniques, including TLBO-DL, CNN-LBO, BiLSTM-AADC, and HCLN, using standard indicators, such as MSE, RMSE, MAE, MBE, and R². Results show that our model consistently performs better than all the baselines, and the lowest RMSE and the highest R² are 0.0565 and 0.955, respectively, on the 0.5-hour horizon. The excellent generalization performance of the framework in all of its forecast horizons indicates its feasibility for applications in real-time deployment in solar energy management systems and smart-grid operations.
Dantuluru Venkata Satya Ravi Varma, Ajaya Kumar Parida, M. Nayak et al.· International Journal of Ele...· 0 citations
This study provides a comprehensive benchmarking of conventional machine learning (ML), ensemble learning, deep neural networks, recurrent architectures, Transformers, graph based models, and hybrid ensemble deep learning approaches under complementary renewable energy scenarios. Three datasets are considered: a large scale WEC dataset, a 16 WEC dataset, and operational 10 min SCADA measurements at the Penmanshiel wind farm. For structured WEC layout data, tree ensembles exhibited a clear advantage over conventional ML and neural predictors because randomized partitioning and boosting efficiently captured nonlinear layout power interactions without requiring explicit feature representation learning. The Extra Trees was the strongest model, achieving considerable results. Relative to the MLP baseline, this corresponds to an approximately 63.7% reduction in MAE, demonstrating the suitability of randomized tree ensembles for high dimensional structured WEC data. Also, STGCN reduced the MAE to approximately 167.0 kW and achieved R = 0.93 by explicitly learning spatial and temporal turbine interactions. The best overall forecasting accuracy was obtained by the RF BiLSTM hybrid, with an MAE=150.5 kW. Compared with standalone LSTM, this represents an approximately 75% reduction in MAE, while improving on STGCN by approximately 10.0%. Finally, the experiments reveal that no single AI architecture is universally optimal: randomized and boosted ensembles are particularly effective for structured WEC surrogate modeling, graph networks become advantageous when explicit spatial interactions dominate, and ensemble recurrent hybrids provide the strongest balance when nonlinear tabular relationships and temporal dynamics coexist.
M. Masoumi, Asghar Dashtiy, Mohammad Dehghan et al.· 0 citations
A hybrid PV forecasting framework that combines stacking ensemble learning with a targeted residual correction strategy, and demonstrates that analyzing error distribution and forecasting robustness provides valuable insights beyond conventional aggregate metrics, contributing to the development of more reliable photovoltaic forecasting systems.
Khawla Oufrit, A. Mouadili, M. Zazoui· EPJ Web of Conferences· 0 citations
Sound prediction of existence of future generation based on stochastic sources is a critical issue because of high nonlinearities, high transitions in the environment, and the nature of inherent uncertainty in observational information. The paper proposes an integrated architecture of deep learning, which is the Hierarchical Regime-Adaptive Probabilistic Network (HRAPN) that aims to overcome these constraints using an end-to-end learning framework. The solution selection boasts of hierarchical representation induction with a latent regime adaptation mechanism that modulates dynamically the internal model behavior in a non-stationary environment. Besides that, attention guided dependency synthesis module performs informative temporal context aggregation selectively to allow an efficient long horizon modeling without impaired performance. In contrast to the more traditional deterministic approaches, HRAPN uses probabilistic model of output in order to explicitly model predictive uncertainty, which enhances robustness and reliability of the estimated decisions. The system takes directly heterogeneous and multivariate data, without explicit features or domain pre-treatment. It is experimentally assessed that the presented method achieves higher results as compared to existing baselines in accuracy, stability, and uncertainty calibration in various forecast periods. The findings validate the performance of regime perceiving, hierarchical abstraction and probabilistic inference in the same learning process. The proposed HRAPN model offers a scaffoldable and adaptable evaluation of the dynamic generation modeling under both variable operating conditions with data. The suggested framework attains an overall accuracy of 96.6%, illustrating its robust prediction reliability and exceptional performance relative to current methodologies.
Bal Krishna Saraswat, Sonu Lal, Anshu Malhotra et al.· 2026 International Conferenc...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
