ANN Optimized DA-STS Under Partial Shading Conditions

Solar energy constitutes the primary source of energy within the universe. A variety of methodologies may be employed to effectively harness this energy. The deployment of solar panels is distinguished as a widely adopted and innovative method for the accumulation of this energy. When compared to stationary panels, rotating panels have demonstrated the capacity to produce greater energy outputs under certain circumstances, like partial shading conditions. Solar Tracking Systems (STS) are one of the main methods to track sun movement. The objective of STSs is to optimize energy production by orienting the load, typically solar panels, towards the sun. This is achieved by minimizing the angle of incidence between the incoming sunlight and the Photovoltaic (PV) panel, thereby enhancing the quantity of energy generated. The existing system, Grey Wolf Optimization (GWO) with Maximum Power Point Tracking (MPPT) method, yields a diminished amount of energy, resulting in a significant tracking error. To reduce the tracking error and enhance energy efficiency, the initially proposed method employing Particle Swarm Optimization (PSO) with Artificial Neural Networks (ANNs) has been implemented. This Neural Network (NN) mainly consists of an Adaptive Neuro-Fuzzy Inference System (ANFIS), which includes a workflow from data collection to deployment. This method generates better results than the existing one because of proper training, testing, and data implementation.