Exploiting PV System Performance: A Combined Approach Using MPPT, IoT, Cleaning, Cooling, and Neural Networks

Abstract

This paper investigates the effects of three foremost methodologies—Maximum Power Point Tracking (MPPT), Internet of Things (IoT)-driven cleaning and cooling, and Neural Network Training (NNT)—on improving the efficacy of solar photovoltaic (PV) systems. Solar photovoltaic systems have considerable complications in sustaining maximum performance due to environmental conditions such as dust collection, temperature variations, and an insufficient energy management. A new control method is presented to challenge these difficulties, including MPPT, IoT-based cleaning and cooling, and NNT for the real-time optimization of PV systems. The simulation findings indicate a substantial increase in power production when both technologies are used together. Power generation is improved throughout a 24-hour period, especially during periods of low solar irradiation, by the coordinated use of MPPT, IoT, cleaning, and cooling techniques. The IoT-controlled technology enhances power production by 7–9% across many operating situations, especially in advantageous geographic settings, while simultaneously decreasing energy consumption. NNT dynamically modifies system settings in real-time, exceeding conventional optimization methods. The results underscore the potential of MPPT, IoT, cleaning, cooling, and NNT to markedly enhance the efficiency and productivity of solar PV systems, tackling the primary concerns of dust collection, elevated temperatures, and suboptimal energy management.