Comparative-Analysis of Machine Learning Algorithms for Renewable Energy Forecasting

Recent emphasis on climate change and successive COP meetings have led global attention on renewable energy particularly solar and wind as a pivotal solution especially with many countries committing to complete clean energy by 2070. As we see increase in synchronization of renewable energy sources (RES) into the electricity grid, accurate forecasting and predictive modeling play pivotal roles in optimizing the utilization of sustainable energy sources. In this paper, we present the methodologies, results, conclusions and future scope and deploy Deep learning models instead of techniques, offering enhanced accuracy and computational efficiency utilizing datasets from authenticated sources, the study incorporates parameters like time, dew point, humidity, temperature, wind-speed, cloud cover etc. Furthermore, this paper explores different deep learning techniques like Long-Short term memory, Recurrent Neural networks, Support Vector Machines and asses their algorithmic efficacy using performance metrics like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Square Error (MSE).