Electric vehicle demand estimation and charging station allocation using urban informatics

This paper performs a novel data-driven approach to optimize electric vehicle (EV) public charging. We translate the study area into a directed graph by partitioning it into discrete grids. A modified geographical PageRank (MGPR) model is developed to estimate EV charging demand, built upon trip origin–destination (OD) and social dimension features, and validated against real- world charging data. The results are fed into the capacitated maximal coverage location problem (CMCLP) model to optimize the spatial layout of public charging stations by maximizing their utilization. It is shown that MGPR can effectively quantify the EV charging demand with satis- factory accuracy. Optimized EV charging stations based on the CMCLP model can remedy the spatial mismatch between the EV demand and the existing charging station allocations. The developed methodological framework is highly generalizable and can be extended to other re- gions for EV charging demand estimation and optimal charging infrastructure siting.