Design and Implementation of an Intelligent Energy Conversion System

The expeditious reduction of non-renewable fuel source and increasing environmental problems paved the way for renewable energy resources. Among various sources, solar energy is the most preferred choice of source. For green environment and sustainable energy growth of solar energy great attention is given for generation of electricity with PhotoVoltaic (PV) system. The system output is determined by solar irradiation and environmental temperature which are variable. Tracking the system’s Maximum Power Point (MPP) in such conditions is a difficult task due to the variable climatic conditions, and the algorithms for tracking the MPP become more complicated during partial shading conditions. The objectives of this work is to design and implement an Artificial Neural Network (ANN)-based Maximum Power Point Tracking (MPPT) system for solar photovoltaic (PV) with real-time monitoring using the Internet of Things (IoT). The network is trained for various solar irradiance and temperature conditions in order to measure the MPP voltage, which is then used as a reference voltage by the ANN controller to produce the desired control signal for the DC-DC converter, and the boost converter’s output is fed to a neural network-powered inverter control system to deliver the power to the desired load. A comprehensive simulation with intelligent controller to track MPP utmost under all conditions are designed and tested and the experimentation on the hardware setup lines are carried out.