Optimizing the deployment of electric vehicle charging stations using pervasive mobility data

Abstract

With recent advances in battery technology and the resulting decrease in the charging times, public charging stations are becoming a viable option for Electric Vehicle (EV) drivers. Concurrently, wide-spread use of location-tracking devices in mobile phones and wearable devices makes it possible to track individual-level human movements to an unprecedented spatial and temporal grain. Motivated by these developments, we propose a novel methodology to perform data-driven optimization of EV charging stations location. We formulate the problem as a discrete optimization problem on a geographical grid, with the objective of covering the entire demand region while minimizing a measure of drivers' discomfort. Since optimally solving the problem is computationally infeasible, we present computationally efficient, near-optimal solutions based on greedy and genetic algorithms. We then apply the proposed methodology to optimize EV charging stations location in the city of Boston, starting from a massive cellular phone data sets covering 1 million users over 4 months. Results show that genetic algorithm based optimization provides the best solutions in terms of drivers' discomfort and the number of charging stations required, which are both reduced about 10% as compared to a randomized solution. We further investigate robustness of the proposed data-driven methodology, showing that, building upon well-known regularity of aggregate human mobility patterns, the near-optimal solution computed using single day movements preserves its properties also in later months. When collectively considered, the results presented in this paper clearly indicate the potential of data-driven approaches for optimally locating public charging facilities at the urban scale.

Indicator-Based Methodology for Assessing EV Charging Infrastructure Using Exploratory Data Analysis

“…There seems to somehow be a tendency to separate electrical studies from their geospatial distribution. Other optimization problems [15][16][17][18][19] focus on case studies trying to find the optimal ratio of chargers per car and distribution intensity. No common approach is followed; different objective functions and variables are considered, but tend to be the following: charging costs, securing a minimal distance from a charger to a given point on a map, distance between chargers, relation to population density, or relation with fuel stations.…”

Electric Vehicles: A Data Science Perspective Review

“…Yes Machine Learning XGBoost, Clustering [36] Clustering [97,98] Optimization Greedy, Genetic [99] Mathematical programming [52,53,100] No Optimization Genetic [101][102][103] Mathematical programming [104][105][106][107] Simulation Queuing theory [51] Agent-based modelling [108,109] He et al [104] proposed a mathematical framework for the macroscopic deployment of charging stations taking into account the equilibrium between demand and supply of energy. User's desire to choose a destination was formulated based on: time, price, and availability of chargers.…”

“…A study by Vaziveh et al [99] is using real-world data collected through the cell phone data over the Boston area, and with that, whole trip of a user was known. The goal of that research was to minimize the aggregate distance all drivers have to drive, from the end of their intended trip to the nearest charging station.…”

Location-Allocation of Electric Vehicle Fast Chargers—Research and Practice

“…If the objective of the study is to capture all traffic, no constraint will be placed on the number of available charging stations to be allocated. Instead, a cost-minimization problem is formulated to minimize the number of facilities required to cover all demand; this formulation is referred to as the set covering [21,[27][28][29][30][31].…”