Design and modelling of a neural network-based energy management system for solar PV, fuel cell, battery and ultracapacitor-based hybrid electric vehicle

The Hybrid Electric Vehicle's (HEV) fuel efficiency is directly related to the vehicle's Power Management Strategy (PMS). An Artificial Neural Network (ANN) is described here as a PMS. As more and more of our sources of electricity come from renewable sources, Artificial Intelligence (AI) is becoming more important for coordinating the use of these resources. With solar Photovoltaic (PV) panels and Proton Exchange Membrane Fuel Cells (PEMFCs) as the primary energy generators, and a battery bank and ultracapacitor / supercapacitor as the secondary energy storage devices, the hybrid power supply is an environmentally friendly system. The MATLAB Simulink programme family is used to create the suggested model. Assessment has been performed for various PMS based on hydrogen consumption, overall efficiency, State of Charge (SOC) of ultracapacitors and batteries, stress on hybrid sources and stability of the Direct Current (DC) system. Simulation results show that the proposed scheme meets the power demand of typical driving cycles like, the Highway Fuel Economy Test cycle (HWFET), New York City Cycle (NYCC) and Urban Dynamometer Driving Schedule (UDDS) for testing the vehicle's performance. When compared to the Proportional Integral (PI), State Machine Control (SMC), Frequency Decoupling Fuzzy Logic Control (FDFLC), Equivalent Consumption Minimization Strategy (ECMS) and External Energy Minimization Strategy (EEMS), the use of ANN in this proposed work reduces hydrogen consumption by 2.4% to 6.7% and battery SOC is maintained between 62 and 68%.