Hybrid Modeling System for Photovoltaic Monitoring of Solar Panels

Solar photovoltaic (PV) systems have emerged as a prominent source of clean and renewable electricity generation, yet their performance is influenced by various external factors. To effectively assess and optimize their performance, a real-time remote monitoring system is essential. This study proposes an Internet of Things (IoT)-based monitoring system for solar energy systems, aiming to enhance output efficiency by addressing factors such as panel connections and dust accumulation, which can significantly reduce output. The developed IoT system integrates physical modeling with machine learning to monitor and optimize PV system performance. A dedicated software platform enables hybrid modeling of expected versus actual power output, facilitating early anomaly detection and mitigation. Particularly in dusty environments where solar PV modules are commonly deployed, the system includes a cleaning mechanism to enhance module efficiency by removing accumulated dust. This research outlines the design, implementation, and testing of an affordable and effective PV monitoring solution. By accurately predicting electrical output and swiftly identifying performance deviations, the proposed system aims to maximize the efficiency and reliability of solar energy generation, contributing to sustainable energy practices.