Code implementation for "DCA: Delayed Charging Attack on the Electric Shared Mobility System"

A Simulation Platform for Electric-Taxi Ride-Hailing System.

Primary contributors: Shuocheng Guo (U Alabama) and Xinwu Qian (U Alabama)

(Red dots: EVCS under attack. Blue dots: EVCS removed for repair. Green dots: EVCS under normal operation.)

Key features: Routing, Charging, Repositioning, Matching, Cybersecurity module (attack and detection algorithm), and interaction between EVs and EV charging stations (EVCSs).

Journal Publication

Our paper has been accepted by IEEE Transactions on Intelligent Transportation Systems. We are happy to help if you have any questions. If you used any part of the code, please cite the following paper (see guo2023dca)

@ARTICLE{guo2023dca, author={Guo, Shuocheng and Chen, Hanlin and Rahman, Mizanur and Qian, Xinwu}, journal={IEEE Transactions on Intelligent Transportation Systems}, title={DCA: Delayed Charging Attack on the Electric Shared Mobility System}, year={2023}, volume={}, number={}, pages={1-13}, doi={10.1109/TITS.2023.3287792} }

Our previous work for Gasoline-Taxi-based Ride-Hailing System

This simulation platform is extended from our previous work "DROP: Deep relocating option policy for optimal ride-hailing vehicle repositioning" that was accepted by Transportation Research Part C: Emerging Technologies (see Github repo here).

@article{qian2022drop, title={DROP: Deep relocating option policy for optimal ride-hailing vehicle repositioning}, author={Qian, Xinwu and Guo, Shuocheng and Aggarwal, Vaneet}, journal={Transportation Research Part C: Emerging Technologies}, volume={145}, pages={103923}, year={2022}, publisher={Elsevier} }

Prerequisite

Data Sources

Data	Link
EV charging station	AFDC
OD demand	NYCTLC

Data Preprocessing

The preprocessed large files can be fetched via OneDrive.

How to run the code

1. Clone the repo

git clone https://github.com/sguo28/DCA_Simulator.git
cd DCA_Simulator/code

2. Download the data

Download the data from OneDrive and put them in the data folder.

3. Run the code

python main_cnn.py