Leveraging machine learning for sustainable integration of renewable energy generation

Abstract

Long-term economic benefits and sustainability are provided by the integration of renewable energy sources (RESs) into electrical networks. However, because of their intermittent nature and reliance on environmental factors, RESs pose issues in production and consumption balance. Because renewable energy sources like wind and solar are unpredictable, forecasting their output is essential for planning purposes and maintaining grid stability. This thesis focuses on developing effective instruments and algorithms to improve renewable energy generation estimates and handle abnormalities in consumption. These tools and algorithms include maximum power point tracking and machine learning models like random forest (RF), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost). The methods' effectiveness is confirmed by accuracies higher than 80%, which provides speedier and more user-friendly solutions in comparison to the traditional ways. In the end, our effort seeks to offer practical instruments for anticipatory modelling and mitigating intermittentness in renewable energy sources, enabling their assimilation into current power structures to adequately supply energy requirements in a sustainable manner.