Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning
The design of conventional electric vehicles (EVs) is affected by numerous limitations, such as a short travel distance and long charging time. As one of the first wireless charging systems, the Online Electric Vehicle (OLEV) was developed to overcome the limitations of the current generation of EVs...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-03-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/12/7/1229 |
id |
doaj-d98709a660284ec8b8e7ef121d8869f3 |
---|---|
record_format |
Article |
spelling |
doaj-d98709a660284ec8b8e7ef121d8869f32020-11-24T21:44:27ZengMDPI AGEnergies1996-10732019-03-01127122910.3390/en12071229en12071229Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement LearningHyukjoon Lee0Dongjin Ji1Dong-Ho Cho2KAIST (Korea Advanced Institute of Science and Technology), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, KoreaKAIST (Korea Advanced Institute of Science and Technology), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, KoreaKAIST (Korea Advanced Institute of Science and Technology), 291 Daehak-ro, Yuseong-gu, Daejeon 34141, KoreaThe design of conventional electric vehicles (EVs) is affected by numerous limitations, such as a short travel distance and long charging time. As one of the first wireless charging systems, the Online Electric Vehicle (OLEV) was developed to overcome the limitations of the current generation of EVs. Using wireless charging, an electric vehicle can be charged by power cables embedded in the road. In this paper, a model and algorithm for the optimal design of a wireless charging electric bus system is proposed. The model is built using a Markov decision process and is used to verify the optimal number of power cables, as well as optimal pickup capacity and battery capacity. Using reinforcement learning, the optimization problem of a wireless charging electric bus system in a diverse traffic environment is then solved. The numerical results show that the proposed algorithm maximizes average reward and minimizes total cost. We show the effectiveness of the proposed algorithm compared with obtaining the exact solution via mixed integer programming (MIP).https://www.mdpi.com/1996-1073/12/7/1229reinforcement learningwireless charging electric bus systemMarkov decision modeloptimizationQ-learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Hyukjoon Lee Dongjin Ji Dong-Ho Cho |
spellingShingle |
Hyukjoon Lee Dongjin Ji Dong-Ho Cho Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning Energies reinforcement learning wireless charging electric bus system Markov decision model optimization Q-learning |
author_facet |
Hyukjoon Lee Dongjin Ji Dong-Ho Cho |
author_sort |
Hyukjoon Lee |
title |
Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning |
title_short |
Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning |
title_full |
Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning |
title_fullStr |
Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning |
title_full_unstemmed |
Optimal Design of Wireless Charging Electric Bus System Based on Reinforcement Learning |
title_sort |
optimal design of wireless charging electric bus system based on reinforcement learning |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2019-03-01 |
description |
The design of conventional electric vehicles (EVs) is affected by numerous limitations, such as a short travel distance and long charging time. As one of the first wireless charging systems, the Online Electric Vehicle (OLEV) was developed to overcome the limitations of the current generation of EVs. Using wireless charging, an electric vehicle can be charged by power cables embedded in the road. In this paper, a model and algorithm for the optimal design of a wireless charging electric bus system is proposed. The model is built using a Markov decision process and is used to verify the optimal number of power cables, as well as optimal pickup capacity and battery capacity. Using reinforcement learning, the optimization problem of a wireless charging electric bus system in a diverse traffic environment is then solved. The numerical results show that the proposed algorithm maximizes average reward and minimizes total cost. We show the effectiveness of the proposed algorithm compared with obtaining the exact solution via mixed integer programming (MIP). |
topic |
reinforcement learning wireless charging electric bus system Markov decision model optimization Q-learning |
url |
https://www.mdpi.com/1996-1073/12/7/1229 |
work_keys_str_mv |
AT hyukjoonlee optimaldesignofwirelesschargingelectricbussystembasedonreinforcementlearning AT dongjinji optimaldesignofwirelesschargingelectricbussystembasedonreinforcementlearning AT donghocho optimaldesignofwirelesschargingelectricbussystembasedonreinforcementlearning |
_version_ |
1725910205337698304 |