Answers are grounded in this paper and cite their sources.
Stable grid operation and the effective integration of renewable energy supplies depend heavily on accurate short-term solar irradiance predictions. However, accurate prediction is difficult due to the extremely nonlinear behavior of solar irradiance and the inherent unpredictability of climatic variables. This research proposes a more efficient regression-based forecasting approach by employing the integration of Tasmanian Devil Optimization (TDO) for adaptive hyperparameter tuning as well as a State-Space Latent Retention Autoencoder (SSLR-AE) network to address the aforementioned issues. The enhanced framework has been developed to perform better than the baseline SSLR-AE model as well as conventional Deep Neural Networks (DNN) in terms of a range of performance metrics, including R2, MSE, RMSE, MAE, and MAPE, respectively. The results demonstrate a substantial reduction in error rates as well as improved convergence stability. Overall, it can be observed that the proposed approach provides a reliable and accurate solution for short-term solar irradiance forecasting, and it can be used in sophisticated smart energy management.
No takes yet. Share an insight, caveat, or question.
Sunkara et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: