Fleet Management and Charging Scheduling for Shared Mobility-on-Demand System: A Systematic Review

Abstract

Challenged by urbanization and increasing travel needs, existing transportation systems call for new mobility paradigms. In this article, we present the fleet management and charging scheduling of a shared mobility-ondemand system, whereby electric vehicle fleets are operated by a centralized platform to provide customers with mobility service. We provide a comprehensive review of system operation based on the operational objectives. The fleet scheduling strategies are categorized into four types: ⅰ) order dispatching, ⅱ) order-dispatching and rebalancing, ⅲ) orderdispatching, rebalancing and charging, and ⅳ) extended. Specifically, we first identify mathematical modeling techniques implemented in the transportation network, then analyze and summarize the solution approaches including mathematical programming, reinforcement learning, and hybrid methods. The advantages and disadvantages of different models and solution approaches are compared. Finally, we present research outlook in various directions. INDEX TERMS shared mobility-on-demand, electric vehicles, fleet management, operational objective, deep reinforcement learning.W

Coordinated Planning of Electric Vehicle Charging Infrastructure and Renewables in Power Grids

“…It is worth noting that the proposed MPC learning method allows for accurate representation of individual EV charging constraints during each iteration. It is different from machine learning methods which learn customer charging and driving decisions [31] and face difficulties at incorporating complex EV physical constraints [32]. Besides, MPC learning applies the adaptive control to high-level objectives to identify a smart grid of the future with some unknown parameters, while most existing adaptive control methods are limited to lower-level control applications such as the one in [33].…”