Dynamic Stochastic Electric Vehicle Routing with Safe Reinforcement Learning  
Artikel i vetenskaplig tidskrift, 2021

Dynamic routing of electric commercial vehicles can be a challenging problem since besides the uncertainty of
energy consumption there are also random customer requests. This paper introduces the Dynamic Stochastic
Electric Vehicle Routing Problem (DS-EVRP). A Safe Reinforcement Learning method is proposed for
solving the problem. The objective is to minimize expected energy consumption in a safe way, which means
also minimizing the risk of battery depletion while en route by planning charging whenever necessary. The
key idea is to learn o ine about the stochastic customer requests and energy consumption using Monte
Carlo simulations, to be able to plan the route predictively and safely online. The method is evaluated using
simulations based on energy consumption data from a realistic tra c model for the city of Luxembourg
and a high- delity vehicle model. The results indicate that it is possible to save energy at the same time
maintaining reliability by planning the routes and charging in an anticipative way. The proposed method
has the potential to improve transport operations with electric commercial vehicles capitalizing on their
environmental bene ts.

Reinforcement Learning

Energy Consumption

Green Logistics

Electric Vehicles

Vehicle Routing

Approximate Dynamic Programming


Rafael Basso

Chalmers, Elektroteknik, System- och reglerteknik, Reglerteknik

Balázs Adam Kulcsár

Chalmers, Elektroteknik, System- och reglerteknik, Reglerteknik

Ivan Sanchez-Diaz

Chalmers, Teknikens ekonomi och organisation, Service Management and Logistics

Xiaobo Qu

Chalmers, Arkitektur och samhällsbyggnadsteknik, Geologi och geoteknik

Transportation Research Part E: Logistics and Transportation Review

1366-5545 (ISSN)

EL FORT - Optimering av elfordonsflotta i Real-Tid - (Fas 2)

VINNOVA (2017-05512), 2018-03-01 -- 2019-12-31.

IRIS: Inverse förstärkning-lärande och intelligenta svarmalgoritmer för elastiska transportnät

Chalmers, 2020-01-01 -- 2021-12-31.

EL FORT - El Flottor Optimering i Real-Tid

VINNOVA (2014-01381), 2014-07-01 -- 2017-06-30.




Transportteknik och logistik




Mer information

Senast uppdaterat