Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems
While electric vehicles (EVs) continue to draw more attention as an alternative to traditional fossil fuel vehicles, the relatively short driving range of EVs is often pointed out as their biggest drawback. In terms of energy consumption, one of the most energy-intensive systems in EVs is the heatin...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9973292/ |
| _version_ | 1797902209120206848 |
|---|---|
| author | Sungho Joo Dongmin Lee Minseop Kim Taeho Lee Sanghyeok Choi Seungju Kim Jeyeol Lee Joongjae Kim Yongsub Lim Jeonghoon Lee |
| author_facet | Sungho Joo Dongmin Lee Minseop Kim Taeho Lee Sanghyeok Choi Seungju Kim Jeyeol Lee Joongjae Kim Yongsub Lim Jeonghoon Lee |
| author_sort | Sungho Joo |
| collection | DOAJ |
| description | While electric vehicles (EVs) continue to draw more attention as an alternative to traditional fossil fuel vehicles, the relatively short driving range of EVs is often pointed out as their biggest drawback. In terms of energy consumption, one of the most energy-intensive systems in EVs is the heating, ventilation, and air conditioning (HVAC) system. Most HVAC systems use On/Off or PID control for the actuators, but these control methods have low efficiency and are difficult to apply in multiple-input multiple-output systems. In this paper, we propose a novel multi-agent deep reinforcement learning (MADRL) method to efficiently control the low-level actuators of the EV HAVC systems. Through this method, multiple objectivs such as setpoint temperature, subcooling and efficiency can be considered simultaneously by giving independent rewards for each actuator agent. The proposed method is evaluated via a actual vehicle simulator, and experimental results show that the MADRL-based method consumes only 53% of the energy consumption of PID control on average in a transient phase. |
| first_indexed | 2024-04-10T09:14:05Z |
| format | Article |
| id | doaj.art-3a26f8e55b41422197c2a54293656311 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-10T09:14:05Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-3a26f8e55b41422197c2a542936563112023-02-21T00:01:05ZengIEEEIEEE Access2169-35362023-01-01117574758710.1109/ACCESS.2022.32274509973292Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC SystemsSungho Joo0Dongmin Lee1Minseop Kim2Taeho Lee3https://orcid.org/0000-0002-1288-5104Sanghyeok Choi4Seungju Kim5Jeyeol Lee6Joongjae Kim7https://orcid.org/0000-0001-9028-8199Yongsub Lim8Jeonghoon Lee9https://orcid.org/0000-0002-5059-1684MakinaRocks, Seoul, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaHanon Systems, Deajeon, Republic of KoreaMakinaRocks, Seoul, Republic of KoreaHanon Systems, Deajeon, Republic of KoreaWhile electric vehicles (EVs) continue to draw more attention as an alternative to traditional fossil fuel vehicles, the relatively short driving range of EVs is often pointed out as their biggest drawback. In terms of energy consumption, one of the most energy-intensive systems in EVs is the heating, ventilation, and air conditioning (HVAC) system. Most HVAC systems use On/Off or PID control for the actuators, but these control methods have low efficiency and are difficult to apply in multiple-input multiple-output systems. In this paper, we propose a novel multi-agent deep reinforcement learning (MADRL) method to efficiently control the low-level actuators of the EV HAVC systems. Through this method, multiple objectivs such as setpoint temperature, subcooling and efficiency can be considered simultaneously by giving independent rewards for each actuator agent. The proposed method is evaluated via a actual vehicle simulator, and experimental results show that the MADRL-based method consumes only 53% of the energy consumption of PID control on average in a transient phase.https://ieeexplore.ieee.org/document/9973292/Multi-agent reinforcement learningenergy consumption efficiencyHVACEVRL |
| spellingShingle | Sungho Joo Dongmin Lee Minseop Kim Taeho Lee Sanghyeok Choi Seungju Kim Jeyeol Lee Joongjae Kim Yongsub Lim Jeonghoon Lee Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems IEEE Access Multi-agent reinforcement learning energy consumption efficiency HVAC EV RL |
| title | Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems |
| title_full | Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems |
| title_fullStr | Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems |
| title_full_unstemmed | Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems |
| title_short | Multi-Agent Reinforcement Learning Based Actuator Control for EV HVAC Systems |
| title_sort | multi agent reinforcement learning based actuator control for ev hvac systems |
| topic | Multi-agent reinforcement learning energy consumption efficiency HVAC EV RL |
| url | https://ieeexplore.ieee.org/document/9973292/ |
| work_keys_str_mv | AT sunghojoo multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT dongminlee multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT minseopkim multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT taeholee multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT sanghyeokchoi multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT seungjukim multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT jeyeollee multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT joongjaekim multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT yongsublim multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems AT jeonghoonlee multiagentreinforcementlearningbasedactuatorcontrolforevhvacsystems |