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 directed graph by partitioning it discrete grids. A modified geographical PageRank (MGPR) model is developed estimate EV charging demand, built upon trip origin–destination (OD) and social dimension features, validated against real-world data. The results are fed capacitated maximal coverage location problem (CMCLP) spatial layout of stations maximizing their utilization. It shown that MGPR can effectively quantify demand with satisfactory accuracy. Optimized based on CMCLP remedy mismatch between existing station allocations. methodological framework highly generalizable be extended other regions for estimation optimal infrastructure siting.