Machine Learning for Sustainable Power Systems: AIoT-Optimized Smart-Grid Inverter Systems with Solar Photovoltaics

This research investigates the transformative role of Machine Learning (ML) in optimizing smart-grid inverter systems, specifically emphasizing solar photovoltaics. A comprehensive literature review informed the development of a robust methodology, leveraging Artificial Intelligence of Things (AIoT) and ML algorithms. Government grid data were employed for training and testing the ML-optimized system, leading to exceptional results: 97% accuracy, 95% prediction precision, 92% system efficiency, and 95% energy yield. These findings underscore the superior performance of ML in renewable energy integration, laying the groundwork for practical applications in smart-grid technology. The study not only contributes significantly to academic discourse but also suggests future directions for scaling these innovations in broader smart city initiatives and adapting them to evolving energy landscapes.