Artificial Intelligence for management of electric vehicles and vehicle to grid (V2G) resources optimization

Project Member(s): Hossain, J.

Funding or Partner Organisation: eleXsys Energy Pty Ltd T/A Planet Ark Power (Planet Ark Power CRC)
eleXsys Energy Pty Ltd T/A Planet Ark Power (Planet Ark Power CRC)
Race for 2030 Limited (Race for 2030 Limited CRC)
Race for 2030 Limited (Race for 2030 Limited CRC)

Start year: 2022

Summary: This project aims to develop and implement intelligent techniques to manage the charging and discharging of electric vehicle (EV) batteries and design EV management framework using state of the art artificial intelligence (AI) algorithms for addressing major grid-challenges that arise in the deployment and management of EVs. The following areas will be the key focus of this project: • Automated identification of grid congestion: Application of AI and machine learning to identify anomalies and find trends in order to locate and reinforce vulnerable points on the grid due to large scale EV integrations; • Vehicle to grid (V2G) resource optimization: Use of AI techniques and machine learning algorithm to optimize V2G resources dispatching for owners’ profit maximization and preference preservation while preventing grid congestions, complementing intermittency of the renewable-based power generations, smoothing of the power demand profiles, reducing peak demand on the grid, and minimizing electricity price-spikes due to supply-demand mismatch; • Predictive optimization of charging stations’ sizing and placement: Use of forecast charging demand of EV and EV penetration levels to optimize sizing and placement of charging stations; • Automated selections of charging locations: Use of machine learning and forecasting techniques to identify optimal charging point selection en-route for minimizing grid congestions, traffic congestion, and the delays incurred by the EVs. These will be implemented not only to predict optimal solutions but also to estimate uncertainty in EV usages and charging while combining with methods in Human Interpretable Machine Learning to ensure EV owners can have confidence in the models. The results will be verified using a real time simulator (OPAL RT) and power systems equipment available at Tech-Lab UTS.

FOR Codes: Electrical energy generation (incl. renewables, excl. photovoltaics), Renewable Energy not elsewhere classified

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.