International Journal of Modern Research in Electrical and Electronic Engineering

Solar tracking systems are commonly used in large-scale solar power installations, where maximizing energy production is crucial. By utilizing solar trackers, these systems can increase their energy output by up to 30% compared to fixed-tilt solar installations. These systems are more complex and expensive than fixed-tilt systems but can provide higher energy yields in locations with high solar insolation. The objective of solar power tracking systems is to maximize the capture of solar radiation by continuously adjusting the orientation and tilt of the solar panels. these systems can ensure that the solar panels receive the highest possible level of sunlight throughout the day. This optimized alignment allows for increased energy production and improved overall system performance. Two different ML approaches, such as support vector machine (SVM) and Gaussian process regression (GPR), were considered and compared. The basic input parameters, including solar PV panel temperature, ambient temperature, solar flux, time of day, and relative humidity. In this paper to showcase the effectiveness and accuracy of SVM and GPR models in forecasting solar PV power, the results of these models are compared using root mean squared error (RMSE) and mean absolute error (MAE) criteria.