ERI: Data-Driven Expansion of Electrified Transportation Network

Tennessee Technological University, Cookeville TN

Investigators

Abstract

With their mobility, charging/discharging, and networking capabilities, electric vehicles (EVs) will bridge the planning and operation of multiple systems: power grid, transportation system, and communication network, known as electrified transportation network (ETN). As the interface between EVs and the ETN, the EV charging station (EVCS) demands precise and long-term planning to meet the versatile power, transportation, and communication demands of the ETN. However, the limited availability of EV data impedes accurate demand forecasting for EVCS planning. Further, overlooking the impacts of socio-economic factors (such as the growth of urban and rural areas and population distribution) will degrade the long-term EVCS planning. This project will develop a scalable EV data generation model that only needs publicly available data to generate EV data at the individual vehicle level and system level. The project team will use the data for EV demand forecasting to shed light on ETN planning, including EVCS deployment, potential network hotspot installation, and road expansion. The project will use land use and land cover change analysis to explore the impact of urban area and population growth on long-term ETN planning. The project contributes to the sustainable planning and efficient operation of the ETN and the project results will serve as the guidance for the National Electric Vehicle Infrastructure (NEVI) program, promoting net-zero transportation in the United States in the long run. The project will advance the research of EV infrastructure expansion profoundly from three aspects. First, a scalable travel motif-based EV generation model will be developed to generate close-to-real EV travelling data using open-access data. Then, a recurrent-graph convolutional network-based learning model for EV demand forecasting will be developed for spatiotemporal multi-system resource forecasting. Finally, a land use land change analysis model will be developed and integrated into the multi-stage ETN expansion strategy by predicting the land change and correspondingly the population growth and EV distribution change over time. The ETN expansion strategy will guarantee the quality of service during the multi-stage planning horizon with inter-system infrastructure investment. The inter-disciplinary project will provide a powerful range of interdisciplinary tools for data-driven EV operation, and EV-related infrastructure planning and operation, therefore enhancing scientific and technological understanding in the related field. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.