This project explores the integration of Artificial Intelligence (AI) and Internet of Things (IoT) technologies to enhance the efficiency and predictive capability of solar energy systems. A real-time embedded monitoring system was designed using a microcontroller-based architecture to collect and process environmental and electrical data from a polycrystalline silicon solar cell.

The system integrates multiple sensors, including temperature and humidity (DHT22), light intensity (LDR), and current measurement (INA219), alongside voltage monitoring to capture key performance indicators such as open-circuit voltage and short-circuit current. Data is stored locally via SD card and transmitted to the ThingSpeak cloud platform for real-time visualization and analysis.

Over an eight-day period, the system collected more than 57,000 readings per day, capturing detailed variations in solar performance under changing weather and lighting conditions. Machine learning models, including Random Forest and Support Vector Machines (SVM), were trained to classify weather conditions based on sensor inputs. Random Forest achieved the highest classification accuracy, while SVM showed slightly lower performance under cloudy conditions.

Overall, the research demonstrates how AI-driven analytics combined with IoT-enabled monitoring can significantly improve solar energy management, enabling smarter, more efficient, and scalable renewable energy solutions.

4_Integration of IoT with AI for solar monitoring and optimization