International Research Journal of Education and Technology

The efficiency of solar photovoltaic (PV) systems depends on the precise optimization of various parameters, including panel tilt angle, orientation, temperature, and irradiance levels. Traditional methods of PV optimization often rely on static models, which fail to adapt to real-time environmental changes and system inefficiencies. This study presents a data-driven approach for optimizing solar PV parameters using real-time data and machine learning algorithms. A key feature of the proposed system is fault detection using the Random Forest algorithm, which identifies and classifies anomalies such as shading, degradation, and connectivity issues. By continuously analyzing real-time sensor data, the model dynamically

adjusts PV parameters to maximize energy output while minimizing losses. Experimental results demonstrate that the integration of real-time optimization with machine learning-based fault detection significantly enhances system performance, reliability, and operational efficiency. This approach provides a scalable and intelligent solution for improving solar energy generation and ensuring the long-term sustainability of PV systems.

Key Words: Solar Photovoltaic (PV), Optimization, Real-Time Data, Machine Learning, Random Forest Algorithm, Fault Detection, Energy Efficiency, Solar Panel Performance, Predictive Analytics, Renewable Energy, Smart Monitoring, Anomaly Detection, Sensor Data Analysis.