Idle Vehicle Relocation Strategy through Deep Learning for Shared Autonomous Electric Vehicle System Optimization

Corresponding authors Abstract In optimization of a shared autonomous electric vehicle (SAEV) system, idle vehicle relocation strategies are important to reduce operation costs and customers' wait time. However, for an on-demand service, continuous optimization for idle vehicle relocation is computationally expensive, and thus, not effective. This study proposes a deep learning-based algorithm that can instantly predict the optimal solution to idle vehicle relocation problems under various traffic conditions. The proposed relocation process comprises three steps. First, a deep learningbased passenger demand prediction model using taxi big data is built. Second, idle vehicle relocation problems are solved based on predicted demands, and optimal solution data are collected. Finally, a deep learning model using the optimal solution data is built to estimate the optimal strategy without solving relocation. In addition, the proposed idle vehicle relocation model is validated by applying it to optimize the SAEV system. We present an optimal service system including the design of SAEV vehicles and charging stations. Further, we demonstrate that the proposed strategy can drastically reduce operation costs and wait times for on-demand services. Keywords: Idle vehicle relocation, deep learning, shared autonomous electric vehicle (SAEV), demand prediction, system optimization 1. Introduction Shared autonomous electric vehicles (SAEVs) that combine car sharing services, autonomous driving technology, and electric vehicles (EVs) are expected to revolutionize transportation systems in the near future [1,2]. An SAEV autonomously goes to the location requested by a customer and rides that customer to a prescribed destination, thus providing a low-stress and safe transportation service [3,4], promoting transportation accessibility [5], and reducing mobility costs [6]. In addition, EVs help reduce fuel consumption and produce less environmental pollutants and greenhouse gas emissions [7-10].