Optimal placement of electric vehicle charging infrastructures utilizing deep learning

The increasing level of air pollution caused by the transport sector necessitates countries to adopt Electric Vehicles (EVs). To espouse EVs, the charging infrastructures' location should be optimal to fulfill the mass‐market consumer needs and reduce the governmental expenses. In this work, th...

Full description

Saved in:
Bibliographic Details
Published inIET intelligent transport systems Vol. 18; no. 8; pp. 1529 - 1544
Main Authors Alansari, Mohamad, Al‐Sumaiti, Ameena Saad, Abughali, Ahmed
Format Journal Article
LanguageEnglish
Published Wiley 01.08.2024
Subjects
Online AccessGet full text
ISSN1751-956X
1751-9578
DOI10.1049/itr2.12527

Cover

More Information
Summary:The increasing level of air pollution caused by the transport sector necessitates countries to adopt Electric Vehicles (EVs). To espouse EVs, the charging infrastructures' location should be optimal to fulfill the mass‐market consumer needs and reduce the governmental expenses. In this work, the placement of two categories of charging infrastructures, specifically Charging Station (CS) and Dynamic Wireless Charging (DWC) infrastructure is planned in Dubai, United Arab Emirates (UAE) as a case study. For this study, Dubai is divided into 14 districts as per its new addressing system, and the allocation of the two types of charging infrastructures is based on the projection of population growth, EVs adoption forecasting, and other factors with the objective of meeting the consumers' needs and minimizing the government's expenditure. The proposal introduces a novel hybrid model for forecasting, integrating the strengths of the Seasonal AutoRegressive Integrated Moving Average with eXogenous regressors (SARIMAX) model for capturing time‐series statistical characteristics, and the deep learning Attention‐based Convolutional Neural Network (ACNN) for modeling nonlinear relationships in time‐series data. The model's effectiveness was validated through comparative analyses against state‐of‐the‐art (SOTA) models on standard benchmarks, showing significant improvements: 29.70% reduction in Mean Absolute Error (MAE), and 19.15% reduction in Root Mean Square Error (RMSE). The study pioneers novel AI models to strategically place Charging Stations and Dynamic Wireless Charging, optimizing for the city's projected population growth and other influential factors. By marrying innovation with eco‐conscious planning, we aim to supercharge Electric Vehicle adoption.
ISSN:1751-956X
1751-9578
DOI:10.1049/itr2.12527