ANFIS Based Energy Management System for V2G Integrated Micro-Grids
Femina Mohammed Shakeel, O.P. Malik
Abstract
Description and evaluation of an adaptive neuro-fuzzy inference system (ANFIS) based energy management system (EMS) for a vehicle-to-grid integrated micro-grid is given in this paper. A grid-tied micro-grid with a wind turbine and a photovoltaic solar panel as primary energy sources, and an energy storage system based on electric vehicle (EV) batteries is considered in this study. The ANFIS-based supervisory controller determines the power that must be generated by or stored in the EV batteries, taking into account the power demanded by the micro-grid and available EV power considering the battery state of charge, rated capacity, and time remaining for departure of the EVs. The Sugeno based ANFIS EMS is compared with a Mamdani based fuzzy EMS, thus evaluating two different artificial intelligence approaches for solving the same power allocation problem. Dynamic simulations demonstrate that the ANFIS based EMS is able to allocate power optimally among available resources during various uncertainties simulated in the system and is also able to provide a better power allocation when compared to the fuzzy based EMS.