Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update
Fuel cell electric vehicles use fuel cells as their main power source; the vehicle is driven by an electric motor, and have an electric battery as a secondary power source that stores regenerative braking energy and assists driving. To reduce the hydrogen fuel consumption by using these fuel cells a...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9402260/ |
| id |
doaj-8c6b7ef91c814f189fc33c2f04df868c |
|---|---|
| record_format |
Article |
| spelling |
doaj-8c6b7ef91c814f189fc33c2f04df868c2021-04-22T23:00:24ZengIEEEIEEE Access2169-35362021-01-019592445925410.1109/ACCESS.2021.30729039402260Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model UpdateHeeyun Lee0https://orcid.org/0000-0003-1737-962XSuk Won Cha1https://orcid.org/0000-0002-4044-2079Department of Mechanical Engineering, Seoul National University, Seoul, Republic of KoreaDepartment of Mechanical Engineering, Seoul National University, Seoul, Republic of KoreaFuel cell electric vehicles use fuel cells as their main power source; the vehicle is driven by an electric motor, and have an electric battery as a secondary power source that stores regenerative braking energy and assists driving. To reduce the hydrogen fuel consumption by using these fuel cells and electric batteries efficiently, an energy management strategy is needed for the proper distribution of power among them. In this study, model-based reinforcement learning was utilized for energy management. For the optimal control of a fuel-cell electric vehicle, reinforcement learning is conducted using an internal vehicle powertrain model in the learning algorithm; initially, the model is completely unknown, but the model is learned with data from experiences as the learning process progresses. Then, reinforcement learning is conducted for the environment of the driving cycle profile to optimize the control policy. In this study, vehicle simulation was conducted using standard driving cycles, and the results showed that the learning process converged steadily and that the powertrain model was well learned. The simulated fuel consumption values show that the proposed algorithm reduces fuel consumption compared to the rule-based strategy by an average of 5.7%.https://ieeexplore.ieee.org/document/9402260/Fuel cell electric vehiclesmodel-based reinforcement learningoptimal controlpower managementreinforcement learning |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Heeyun Lee Suk Won Cha |
| spellingShingle |
Heeyun Lee Suk Won Cha Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update IEEE Access Fuel cell electric vehicles model-based reinforcement learning optimal control power management reinforcement learning |
| author_facet |
Heeyun Lee Suk Won Cha |
| author_sort |
Heeyun Lee |
| title |
Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update |
| title_short |
Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update |
| title_full |
Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update |
| title_fullStr |
Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update |
| title_full_unstemmed |
Energy Management Strategy of Fuel Cell Electric Vehicles Using Model-Based Reinforcement Learning With Data-Driven Model Update |
| title_sort |
energy management strategy of fuel cell electric vehicles using model-based reinforcement learning with data-driven model update |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2021-01-01 |
| description |
Fuel cell electric vehicles use fuel cells as their main power source; the vehicle is driven by an electric motor, and have an electric battery as a secondary power source that stores regenerative braking energy and assists driving. To reduce the hydrogen fuel consumption by using these fuel cells and electric batteries efficiently, an energy management strategy is needed for the proper distribution of power among them. In this study, model-based reinforcement learning was utilized for energy management. For the optimal control of a fuel-cell electric vehicle, reinforcement learning is conducted using an internal vehicle powertrain model in the learning algorithm; initially, the model is completely unknown, but the model is learned with data from experiences as the learning process progresses. Then, reinforcement learning is conducted for the environment of the driving cycle profile to optimize the control policy. In this study, vehicle simulation was conducted using standard driving cycles, and the results showed that the learning process converged steadily and that the powertrain model was well learned. The simulated fuel consumption values show that the proposed algorithm reduces fuel consumption compared to the rule-based strategy by an average of 5.7%. |
| topic |
Fuel cell electric vehicles model-based reinforcement learning optimal control power management reinforcement learning |
| url |
https://ieeexplore.ieee.org/document/9402260/ |
| work_keys_str_mv |
AT heeyunlee energymanagementstrategyoffuelcellelectricvehiclesusingmodelbasedreinforcementlearningwithdatadrivenmodelupdate AT sukwoncha energymanagementstrategyoffuelcellelectricvehiclesusingmodelbasedreinforcementlearningwithdatadrivenmodelupdate |
| _version_ |
1721513921330806784 |