AI-Driven Solar Panel Optimization during Cloudy times Using Real-Time Image Processing

This research investigates a sophisticated system for optimizing solar panel alignment by capturing and analyzing sky images with a high-resolution planetary camera. The system utilizes image processing techniques, including grayscale conversion, binary thresholding, and contour detection, to identify the brightest spot in the sky. By calculating the centroid of the brightest contour, and determining the East-West and North-South angles, the system enables precise adjustments to solar panels, ensuring maximum sunlight capture throughout different times of the day and seasonal variations. Our innovative system boosts solar panel efficiency by automatically adjusting their angles to capture the most sunlight, overcoming challenges posed by changing cloud patterns. Real-time data acquisition and storage are managed through MongoDB, complemented by a web interface for live and historical data access. The methodology includes validation against ground truth values to ensure accuracy and identify the brightest sky areas even in low light, crucial for discerning cloud presence and thickness. Challenges related to environmental factors, computational power, and prediction accuracy are discussed, emphasizing the system's potential to enhance solar energy efficiency and reduce dependence on non-renewable energy sources.