Design and Implementation of a Smart Dual-Axis Solar Tracking System with Predictive and AI-Based Control

This research developed a Dual-Axis Solar Tracking (DAST) system with the primary objective of improving photovoltaic efficiency by precisely following the sun’s position throughout the day. Several control strategies were implemented and evaluated, including Light Dependent Resistor (LDR)-based tracking, GPS-based tracking, Model Predictive Control (MPC), and Artificial Neural Networks (ANN). The system was built and tested using a Raspberry Pi 4 platform. Experimental results confirmed that while all approaches achieved acceptable tracking performance, the MPC and ANN-based methods delivered superior efficiency. In particular, ANN demonstrated strong adaptability to dynamic environmental conditions, while MPC offered robust predictive control with reliable accuracy. Based on these findings, this study recommends the adoption of predictive and AI-driven control strategies in solar tracking applications where high precision and efficiency are required. Integrating such advanced methods into DAST systems represents a significant step toward increasing solar energy yield, reducing operational errors, and supporting the broader deployment of sustainable renewable energy technologies.