Zixin Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zixin Feng has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Alison Heppenstall
University of Glasgow
4 shared publications - Qunshan Zhao
University of Glasgow
4 shared publications - Xinyan Xian
School of Geographical and Earth Sciences, University of Glasgow, Glasgow, UK
1 shared publication - Yahya Gamal
University of Glasgow
1 shared publication
Latest Publications
- 30 July 2026
- Published by Springer Nature
- p. 137-146
Evaluating RL and Rule-Based Agents for Replicating Electric Vehicle Charging Behaviours
- 30 July 2026
- Published by Springer Nature
- p. 137-146
Evaluating RL and Rule-Based Agents for Replicating Electric Vehicle Charging Behaviours
- Open Access
- 1 June 2026
- Published by SAGE Publications in Environment and Planning B: Urban Analytics and City Science
Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
Despite the rapid expansion of electric vehicle (EV) charging networks, questions remain about their efficiency in meeting the growing needs of EV drivers. Previous rule-based ABMs have struggled to capture the adaptive behaviours of human drivers. Although reinforcement learning has been applied in EV simulation studies, its application has primarily focused on optimising fleet operations rather than modelling private drivers who make independent charging decisions. To address this gap, we propose a multi-stage reinforcement learning framework that simulates the charging demand of private EV drivers across a national-scale road network. We validate the model against real-world data and identify the training stage that most closely reflects actual driver behaviour. Based on the simulation results, we identify critical ‘charging deserts’ where EV drivers face high risks of battery depletion. Our findings further highlight recent policy shifts toward expanding rapid charging hubs along motorway corridors and urban boundaries to meet growing demand from long-distance trips.
- 1 June 2026
- Published by SAGE Publications in Environment and Planning B: Urban Analytics and City Science
Open AccessReplicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
Despite the rapid expansion of electric vehicle (EV) charging networks, questions remain about their efficiency in meeting the growing needs of EV drivers. Previous rule-based ABMs have struggled to capture the adaptive behaviours of human drivers. Although reinforcement learning has been applied in EV simulation studies, its application has primarily focused on optimising fleet operations rather than modelling private drivers who make independent charging decisions. To address this gap, we propose a multi-stage reinforcement learning framework that simulates the charging demand of private EV drivers across a national-scale road network. We validate the model against real-world data and identify the training stage that most closely reflects actual driver behaviour. Based on the simulation results, we identify critical ‘charging deserts’ where EV drivers face high risks of battery depletion. Our findings further highlight recent policy shifts toward expanding rapid charging hubs along motorway corridors and urban boundaries to meet growing demand from long-distance trips.
- 26 October 2025
- Published by Springer Nature
- p. 113-127
Exploring the Complex Behaviours of Electric Vehicle Drivers Based on an Agent-Based Reinforcement Learning Method
- 26 October 2025
- Published by Springer Nature
- p. 113-127
Exploring the Complex Behaviours of Electric Vehicle Drivers Based on an Agent-Based Reinforcement Learning Method
- Open Access
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 733-736
Optimizing the locations of electric vehicle charging stations in Georgia, USA
In recent years, the optimal deployment of charging stations has become crucial to meet the growing demand from electric vehicle drivers. Previous studies have applied both node-based and flow-based models to determine the best locations for public chargers. In this study, using existing gas stations and parking lots as candidate sites, we applied the Maximal Coverage Location Problem (MCLP) model to establish a three-phase deployment strategy in Georgia, USA. The applied approach aims to maximize coverage of local travel demand and EV ownership while minimizing coverage in areas with high electricity outage potential. Our results show that the deployed stations are primarily located along high-traffic highways and in key economic hubs in Georgia.
- 29 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 733-736
Open AccessOptimizing the locations of electric vehicle charging stations in Georgia, USA
In recent years, the optimal deployment of charging stations has become crucial to meet the growing demand from electric vehicle drivers. Previous studies have applied both node-based and flow-based models to determine the best locations for public chargers. In this study, using existing gas stations and parking lots as candidate sites, we applied the Maximal Coverage Location Problem (MCLP) model to establish a three-phase deployment strategy in Georgia, USA. The applied approach aims to maximize coverage of local travel demand and EV ownership while minimizing coverage in areas with high electricity outage potential. Our results show that the deployed stations are primarily located along high-traffic highways and in key economic hubs in Georgia.