2021
DOI: 10.1109/tits.2020.3002271
|View full text |Cite
|
Sign up to set email alerts
|

Effective Charging Planning Based on Deep Reinforcement Learning for Electric Vehicles

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
29
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 96 publications
(29 citation statements)
references
References 40 publications
0
29
0
Order By: Relevance
“…Moreover, compared to previous RL works, the prior was neglected in ( Zhang Q. et al, 2020 ). The latter was considered in ( Zhang C. et al, 2020 ) through estimating energy consumption from rarely available historical data. Second, a trained RL agent requires less computing effort and less memory space than model-based techniques and mixed integer non-linear programming formulations ( Mocanu et al, 2018 ) of the EV routing problem such as ( Pourazarm et al, 2014 ).…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Moreover, compared to previous RL works, the prior was neglected in ( Zhang Q. et al, 2020 ). The latter was considered in ( Zhang C. et al, 2020 ) through estimating energy consumption from rarely available historical data. Second, a trained RL agent requires less computing effort and less memory space than model-based techniques and mixed integer non-linear programming formulations ( Mocanu et al, 2018 ) of the EV routing problem such as ( Pourazarm et al, 2014 ).…”
Section: Discussionmentioning
confidence: 99%
“…Additionally, researchers in ( Zhang Q. et al, 2020 ) used actor-critic RL to minimize the route’s energy consumption without recharging opportunities. In ( Zhang C. et al, 2020 ), a deep RL approach was proposed to reduce both travel time and distance while different charging modes and occupation of charging spots were considered. In this research, we formulate the EV-specific routing problem in a graph-theoretical setting as a Markov decision process (MDP) and suggest a possible model-free RL algorithm to solve it by generating energy feasible paths for EV from source to target.…”
Section: Introductionmentioning
confidence: 99%
“…Its core idea is to achieve the maximum return or achieve specific goals through learning strategies during the interaction between the agent and the environment, so that the agent has the ability to make optimal decisions. Considering that the transformation process of reinforcement learning between environments is very complicated, in order to simplify the reinforcement learning modeling problem, the Markov decision process (MDP) is proposed to describe and model the reinforcement learning process [39]. The principle of reinforcement learning is shown in Figure 2.…”
Section: Reinforcement Learningmentioning
confidence: 99%
“…The principle of reinforcement learning is shown in Figure 2. The specific description is as follows cated, in order to simplify the reinforcement learning modeling problem, the Markov decision process (MDP) is proposed to describe and model the reinforcement learning process [39]. The principle of reinforcement learning is shown in Figure 2.…”
Section: Reinforcement Learningmentioning
confidence: 99%
“…A distributed architecture to suggest a set of the nearest charging stations for EV recharging using a distributed ant system algorithm [11]. Zhang, et al [12], authors propose a formalization of the EV charging scheduling problem as a markov decision process and deep reinforcement learning algorithms to reduce the EVs total charging time. To minimize the total elapsed time by considering the traffic condition, the remaining energy in the battery, and the CS queuing length, the EV charging scheduling method is proposed in [13].…”
Section: Introductionmentioning
confidence: 99%