Dynamic stochastic electric vehicle routing with safe reinforcement learning

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 p...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Transportation research. Part E, Logistics and transportation review Ročník 157; číslo 157; s. 102496
Hlavní autori: Basso, Rafael, Kulcsár, Balázs, Sanchez-Diaz, Ivan, Qu, Xiaobo
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier Ltd 01.01.2022
Predmet:
Approximate Dynamic Programming
Electric Vehicles
Energy Consumption
Green Logistics
Reinforcement Learning
Vehicle Routing
Energy consumption
Approximate dynamic programming
Electric vehicles
Vehicle routing
Green logistics
Reinforcement learning
ISSN:1366-5545, 1878-5794
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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 offline 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 traffic model for the city of Luxembourg and a high-fidelity 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 benefits. •The Dynamic Stochastic Electric Vehicle Routing Problem (DS-EVRP) is introduced.•A Safe Reinforcement Learning solution method is presented.•A tailored Value Function Approximation, safe policy and a training strategy are proposed.•Realistic computational experiments are performed.•Results indicate energy savings and increased reliability.
ISSN:1366-5545
1878-5794
DOI:10.1016/j.tre.2021.102496