Optimizing Renewable Energy Use with Advanced Predictive Models under Changing Weather Conditions

Optimizing the utilization and distribution of renewable resources has become necessary due to the rise in their use under various weather situations. One of the most important ways to boost productivity, lessen reliance on fossil fuels, and create energy management plans is to forecast the quantity of energy renewable sources will consume. Researchers are interested in using machine learning (ML) techniques since they are among the best instruments for precisely forecasting energy usage patterns. The forecast of energy consumption has been the subject of numerous studies up to this point, but less attention has been paid to thoroughly examining how climate affects machine learning models' effectiveness. The current research investigates the efficiency of two machine learning methods, including Adaptive reinforcement Algorithm Regression (ADAR) and Stochastic Regression (SR), in predicting renewable energy consumption under variable weather conditions. Also, the Pelican Optimization (POA) and Crystal Structure (CSA) algorithms have been used to improve the performance of these models, and by combining them, SRPO, SRCS, ADPO, and ADCS hybrid models have been developed to increase the prediction accuracy. This study investigates the effect of climate change on the performance of the models and shows that the ADCS model provides the most accurate forecast. The findings of this research can help policymakers and energy analysts to make more optimal decisions for renewable energy management and pave the way for sustainable development by considering the weather conditions.