Machine Learning Enhanced Dual Axis Solar Tracker for Optimized Energy Efficiency

In recent years, electricity has become an important component in people’s lives. Living is unimaginable without electricity. The increasing electricity demand has caused electricity distributors to heavily rely on fossil fuels. Not only are fossil fuels a type of non-renewable resource whose sources are depleted day by day but also, they are also responsible for harm to the environment. Therefore, a need arises for the replacement of fossil fuels. The best replacement for it is renewable energy, which is easily replenished as well as not harmful to the environment. The most abundant renewable energy is Solar energy generated from the sun. It is found that the efficiency of solar panels is maximum when the sunrays fall perpendicular to the panel. Since traditional solar panels are fixed, the panel only receives a limited number of perpendicular sunrays, hence the efficiency is less. In summary, non-renewable sources for electricity are on the verge of depletion and traditional solar panels have very less efficiency. This research work proposes a working dual-axis solar panel that can theoretically increase efficiency by 40% compared to the efficiency of traditional solar panels. By implementing an ML model, which trains itself with the data collected by the panel over time, it further increases efficiency and minimizes energy loss.