Affiliation:
1. TUM School of Management Technical University of Munich Munich Germany
2. TomTom Location Technology Germany GmbH Berlin Germany
3. Munich Data Science Institute Technical University of Munich Berlin Germany
Abstract
AbstractRange and charge anxiety remain essential barriers to a faster electric vehicle (EV) market diffusion. To this end, quickly and reliably finding suitable charging stations may foster an EV uptake by mitigating drivers' anxieties. Here, existing commercial services help drivers to find available stations based on real‐time availability data but struggle with data inaccuracy, for example, due to conventional vehicles blocking the access to public charging stations. In this context, recent works have studied stochastic search methods to account for availability uncertainty in order to minimize a driver's detour until reaching an available charging station. So far, both practical and theoretical approaches ignore driver coordination enabled by charging requests centralization or sharing of data, for example, sharing observations of charging stations' availability or visit intentions between drivers. Against this background, we study coordinated stochastic search algorithms, which help to reduce station visit conflicts and improve the drivers' charging experience. We model a multiagent stochastic charging station search problem as a finite‐horizon Markov decision process and introduce an online solution framework applicable to static and dynamic policies. In contrast to static policies, dynamic policies account for information updates during policy planning and execution. We present a hierarchical implementation of a single‐agent heuristic for decentralized decision making and a rollout algorithm for centralized decision making. Extensive numerical studies show that compared to an uncoordinated setting, a decentralized setting with visit intentions sharing decreases the system cost by 26%, which is nearly as good as the 28% cost decrease achieved in a centralized setting. Even in long planning horizons, our algorithm reduces the system cost by 25% while increasing each driver's search reliability.
Subject
Management of Technology and Innovation,Industrial and Manufacturing Engineering,Management Science and Operations Research
Reference26 articles.
1. Approximate dynamic programming for planning a ride-hailing system using autonomous fleets of electric vehicles
2. Arndt T. Hafner D. Kellermeier T. Krogmann S. Razmjou A. Krejca M. S. Rothenberger R. &Friedrich T.(2016).Probabilistic routing for on‐street parking search. InP.Sankowski&C.Zaroliagis(Eds.) 24th annual European symposium on algorithms (ESA 2016)(vol. 57 pp.6:1–6:13).Schloss Dagstuhl–Leibniz‐Zentrum fuer Informatik.
3. Bourgault F. Furukawa T. &Durrant‐Whyte H. F.(2003).Coordinated decentralized search for a lost target in a Bayesian world. InProceedings 2003 IEEE/RSJ international conference on intelligent robots and systems (IROS 2003) (Cat. No.03CH37453)(vol. 1 pp.48–53) Las Vegas NV USA.
4. Chung T. H. &Burdick J. W.(2008).Multi‐agent probabilistic search in a sequential decision‐theoretic framework. In2008 IEEE international conference on robotics and automation(pp.146–151).Pasadena CA USA.
5. Dai W. &Sartoretti G.(2020).Multi‐agent search based on distributed deep reinforcement learning. Tech. rep. National University of Singapore.
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献