AI-OPTIMIZED RENEWABLE ENERGY MICROGRIDS: A MACHINE LEARNING APPROACH FOR DYNAMIC LOAD BALANCING IN OFF-GRID COMMUNITIES

Abstract

The development of renewable energy-based microgrids is becoming increasingly important in increasing sustainable energy access and reducing dependence on fossil fuels. However, effective energy load management in microgrids remains a major challenge.This research aims to develop and apply machine learning algorithms to optimize dynamic load balancing in renewable energy-based microgrids.This study uses a Systematic Literature Review (SLR) approach to identify and analyze studies related to the application of machine learning in microgrids. Data were collected from academic databases Scopus and Web of Science, and analyzed using thematic coding methods.The results show that machine learning algorithms can be effective in optimizing dynamic load balancing in microgrids. The main findings show that a hybrid approach combining multiple machine learning algorithms can improve prediction accuracy and system stability.This study concludes that the application of machine learning algorithms can be an effective solution in optimizing dynamic load balancing in renewable energy-based microgrids. This finding has important implications in the development of more efficient and sustainable microgrids.