Efficient electric vehicle charging infrastructure planning using data-driven optimization

Farhadi, F; Wang, S; Palacin, R; Blythe, P

doi:10.1049/icp.2023.3116

Efficient electric vehicle charging infrastructure planning using data-driven optimization

Lookup NU author(s): Farzaneh Farhadi ORCiD, Professor Roberto Palacin, Professor Phil Blythe ORCiD

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

© The Institution of Engineering & Technology 2023. This paper presents a high-level overview of a data-driven methodology for optimising the implementation of policy commitments in the transportation sector, specifically focusing on electric vehicle (EV) charging infrastructure in Newcastle upon Tyne, United Kingdom. The study utilises a simulation model provided by the industrial partner, Arup Group Limited, and combines it with a genetic optimization algorithm inspired by Long Short-Term Memory (LSTM) and fuzzy logic. Four future energy scenarios from National Grid are considered to predict EV quantities and the energy demand, reflecting varying levels of decarbonisation and societal change. The optimization algorithm is applied to each scenario to determine the optimal charging point types, locations, quantities, total capital and operational expenditures, and operating hours of the charging points. This paper provides a high-level explanation of the methodology and results, without delving into the mathematical equations or detailed aspects of the simulation and optimization processes. The proposed methodology demonstrates a promising approach to efficiently implement policy commitments in the transport sector, particularly in the context of EV charging infrastructure, enabling local authorities to effectively plan and manage the transition to zero-emission vehicles.