.png){kind=icon}
.png){kind=icon}
Return
Techno-Economic Analysis Framework for Potential EVCSs Using Data-Driven Approach
.png){kind=icon}
PRE
AI
DOI：10.1109/SOUTHEASTCON52093.2024.10500090.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In Tennessee, the state government has started to deploy DC fast charging stations (DCFC) every 50 miles along interstate highways to alleviate range anxiety incurred by electric vehicles (EVs). While the DCFC deployment provides a solid foundation to promote EVs, would this approach be technically and economically efficient with a dominant EV market share? To evaluate the economic feasibility of potential EV charging station (EVCS), this paper proposes a techno-economic analysis framework leveraging both analytical and data-driven approaches. First, a spatial-temporal graph convolutional network (STGCN) is developed to predict the traffic flow on both spatial and temporal scales. Based on the predicted data, the EV charging demand is estimated with the predicted EV penetration rate and various random factors such as EV battery capacity and charging preference. The EV charging demand is simulated using Monte Carlo simulation and the results are utilized for techno-economic assessment of potential EVCS locations to evaluate their value of return for a ten-year operation. The proposed work could become a benchmark for evaluating potential EVCS locations and providing a guideline for EV policymakers, stakeholders, and potential site hosts.