Leveraging Big Data and Coordinated Charging for Effective Taxi Fleet Electrification: The 100% EV Conversion of Shenzhen, China

Abstract

vehicles (EVs), but long charging durations and limited charger availability have prevented rapid adoption. Leveraging over two weeks of high-resolution GPS and battery data from almost 20,000 EVs in the all-electric Shenzhen taxi fleet, we analyze the potential to improve fleet-wide operations by optimizing both the location and timing of vehicle charging. We construct machine learning models to predict travel time, queuing time at charging stations, and charge consumption by time of day. Contrary to the emphasis on charging station siting in the literature, we find that optimizing charging locations would have a relatively limited impact. Instead, providing drivers with better real-time information about queuing times at charging stations, and enabling flexibility in battery charge during shift changes could reduce down-time per vehicle by over 30 minutes per day, while increasing the number of economically viable charging stations by over 50%. Moreover, taking full advantage of break periods and nighttime to charge could reduce downtime per vehicle by over one hour per day, reducing revenue losses due to charging by roughly 90%. These results are verified with evidence from real-time charging station data and driver shift-change data. Policy recommendations from this study include establishing citywide open data platforms to integrate real-time data on vehicle trajectory, battery charge, and charger availability, and providing drivers and companies with training on best charging practices. As a number of cities worldwide move toward fully electrified taxi fleets, this analysis has large-scale implications for decarbonized, cleaner urban areas.

On-Demand Automotive Fleet Electrification Can Catalyze Global Transportation Decarbonization and Smart Urban Mobility

“…Bauer et al (2020) , showed that this inefficiency is largely due to a lack of data: without proper information on the best places and times to charge, drivers tend to charge at large stations right before they end their shifts, during afternoon peak demand. The authors found that providing drivers with complete information including forecasts of trip demand could reduce revenue losses by up to 90%, and even just providing accurate information on queues at each charging station could reduce overall queuing time by half.…”

“…We assume that vehicles must be replaced at 80% of original capacity when uncoordinated, and at 50% when coordinated, as found in Bauer et al (2018) . Revenue lost due to charging is based on Bauer et al (2020), and includes the opportunity cost from time spent both queuing and charging. , In both (c) and (d), we assume an annual discount rate of 5%. See Supporting Information for more details on calculations and assumptions.…”

“…The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acs.est.0c01609. Additional information on relevant electrification policies by region; details for calculations of demand for on-demand mobility services by region; current state of electrification of bus and taxi fleets in largest Chinese cities; details on calculations and assumptions for Figure ; key results from Bauer et al (2020) (PDF) …”