DUAL AXIS SOLAR BASED TRACKING SYSTEM

Abstract

Today’s world prefers the use of sustainable and renewable energy sources such as solar energy to reduce the reliance on non-renewable energy sources such as fossil fuels etc. Solar tracking system is the efficient approach to optimize the performance of solar panels under different weather conditions. This study explains the hardware design, implementation, and performance of a dual axis solar tracking system with different sensors. The paper highlights the increasing demand for solar tracking technology to maximize energy capture from photovoltaic (PV) cells embedded in solar panels. The tracker continuously aligns and adjusts both elevation angle and azimuth position of solar panel to follow sunlight entire day using microcontroller. The tracking system also incorporates weather sensors, such as rain and temperature detectors, to enhance performance and safety of panels during harsh weather conditions. The experimental findings according to different research shows that dual-axis system acquires 25-45% greater energy efficiency than single-axis trackers. However, Deep Neural Network (DNN)-based trackers use predictive algorithms for training phase to adapt the system to real-time environmental factors. This deep learning method is very complex to implement because large dataset is required for training purpose, but it is more accurate to give better results in varying sun patterns and climatic conditions. The increasing complexity and variability in demand explain the need for advanced technology in the upcoming centuries, which in this case comes in the form of DNN-based systems with superior performance and flexibility.