Forecasting Electric Vehicle Charging Demand in Smart Cities Using Hybrid Deep Learning of Regional Spatial Behaviours

Muhammed Cavus (), Huseyin Ayan, Dilum Dissanayake (), Anurag Sharma, Sanchari Deb and Margaret Bell
Additional contact information
Muhammed Cavus: Department of Mathematics, Physics and Electrical Engineering, Northumbria University, Newcastle upon Tyne NE1 8SA, UK
Huseyin Ayan: School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK
Dilum Dissanayake: School of Geography, Earth and Environmental Sciences, University of Birmingham, Birmingham B15 2TT, UK
Anurag Sharma: Faculty of Science, Agriculture & Engineering (SAgE), Newcastle University, Newcastle upon Tyne NE1 7RU, UK
Sanchari Deb: School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK
Margaret Bell: School of Engineering, Newcastle University, Newcastle upon Tyne NE1 7RU, UK

Energies, 2025, vol. 18, issue 13, 1-30

Abstract: This study presents a novel predictive framework for estimating electric vehicle (EV) charging demand in smart cities, contributing to the advancement of data-driven infrastructure planning through behavioural and spatial data analysis. Motivated by the accelerating regional demand accompanying EV adoption, this work introduces HCB-Net: a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) for spatial feature extraction with Extreme Gradient Boosting (XGBoost) for robust regression. The framework is trained on user-level survey data from two demographically distinct UK regions, the West Midlands and the North East, incorporating user demographics, commute distance, charging frequency, and home/public charging preferences. HCB-Net achieved superior predictive performance, with a Root Mean Squared Error (RMSE) of 0.1490 and an R 2 score of 0.3996. Compared to the best-performing traditional model (Linear Regression, R 2 = 0.3520 ), HCB-Net improved predictive accuracy by 13.5% in terms of R 2 , and outperformed other deep learning models such as LSTM ( R 2 = − 0.3756 ) and GRU ( R 2 = − 0.6276 ), which failed to capture spatial patterns effectively. The hybrid model also reduced RMSE by approximately 23% compared to the standalone CNN (RMSE = 0.1666). While the moderate R 2 indicates scope for further refinement, these results demonstrate that meaningful and interpretable demand forecasts can be generated from survey-based behavioural data, even in the absence of high-resolution temporal inputs. The model contributes a lightweight and scalable forecasting tool suitable for early-stage smart city planning in contexts where telemetry data are limited, thereby advancing the practical capabilities of EV infrastructure forecasting.

Keywords: electric vehicles; charging infrastructure; machine learning; deep learning; hybrid models; smart cities; demand forecasting (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/18/13/3425/pdf (application/pdf)
https://www.mdpi.com/1996-1073/18/13/3425/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:18:y:2025:i:13:p:3425-:d:1690568

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().