Electric Vehicle Charging Management Based on Deep Reinforcement Learning
A time-variable time-of-use electricity price can be used to reduce the charging costs for electric vehicle (EV) owners. Considering the uncertainty of price fluctuation and the randomness of EV owner's commuting behavior, we propose a deep reinforcement learning based method for the mini...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | Journal of Modern Power Systems and Clean Energy |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9465776/ |
| _version_ | 1818212939114479616 |
|---|---|
| author | Sichen Li Weihao Hu Di Cao Tomislav Dragicevic Qi Huang Zhe Chen Frede Blaabjerg |
| author_facet | Sichen Li Weihao Hu Di Cao Tomislav Dragicevic Qi Huang Zhe Chen Frede Blaabjerg |
| author_sort | Sichen Li |
| collection | DOAJ |
| description | A time-variable time-of-use electricity price can be used to reduce the charging costs for electric vehicle (EV) owners. Considering the uncertainty of price fluctuation and the randomness of EV owner's commuting behavior, we propose a deep reinforcement learning based method for the minimization of individual EV charging cost. The charging problem is first formulated as a Markov decision process (MDP), which has unknown transition probability. A modified long short-term memory (LSTM) neural network is used as the representation layer to extract temporal features from the electricity price signal. The deep deterministic policy gradient (DDPG) algorithm, which has continuous action spaces, is used to solve the MDP. The proposed method can automatically adjust the charging strategy according to electricity price to reduce the charging cost of the EV owner. Several other methods to solve the charging problem are also implemented and quantitatively compared with the proposed method which can reduce the charging cost up to 70.2% compared with other benchmark methods. |
| first_indexed | 2024-12-12T05:56:21Z |
| format | Article |
| id | doaj.art-712570b6a06a4efabd883a5b78a201fa |
| institution | Directory Open Access Journal |
| issn | 2196-5420 |
| language | English |
| last_indexed | 2024-12-12T05:56:21Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | Journal of Modern Power Systems and Clean Energy |
| spelling | doaj.art-712570b6a06a4efabd883a5b78a201fa2022-12-22T00:35:33ZengIEEEJournal of Modern Power Systems and Clean Energy2196-54202022-01-0110371973010.35833/MPCE.2020.0004609465776Electric Vehicle Charging Management Based on Deep Reinforcement LearningSichen Li0Weihao Hu1Di Cao2Tomislav Dragicevic3Qi Huang4Zhe Chen5Frede Blaabjerg6School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,ChinaSchool of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,ChinaSchool of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,ChinaCenter for Electric Power and Energy Smart Electric Components, Technical University of Denmark,Department of Electrical Engineering,Copenhagen,DenmarkSchool of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China,Chengdu,ChinaAalborg University,Department of Energy Technology,Aalborg,DenmarkAalborg University,Department of Energy Technology,Aalborg,DenmarkA time-variable time-of-use electricity price can be used to reduce the charging costs for electric vehicle (EV) owners. Considering the uncertainty of price fluctuation and the randomness of EV owner's commuting behavior, we propose a deep reinforcement learning based method for the minimization of individual EV charging cost. The charging problem is first formulated as a Markov decision process (MDP), which has unknown transition probability. A modified long short-term memory (LSTM) neural network is used as the representation layer to extract temporal features from the electricity price signal. The deep deterministic policy gradient (DDPG) algorithm, which has continuous action spaces, is used to solve the MDP. The proposed method can automatically adjust the charging strategy according to electricity price to reduce the charging cost of the EV owner. Several other methods to solve the charging problem are also implemented and quantitatively compared with the proposed method which can reduce the charging cost up to 70.2% compared with other benchmark methods.https://ieeexplore.ieee.org/document/9465776/Deep reinforcement learningdata-driven controluncertaintyelectric vehicles (EVs) |
| spellingShingle | Sichen Li Weihao Hu Di Cao Tomislav Dragicevic Qi Huang Zhe Chen Frede Blaabjerg Electric Vehicle Charging Management Based on Deep Reinforcement Learning Journal of Modern Power Systems and Clean Energy Deep reinforcement learning data-driven control uncertainty electric vehicles (EVs) |
| title | Electric Vehicle Charging Management Based on Deep Reinforcement Learning |
| title_full | Electric Vehicle Charging Management Based on Deep Reinforcement Learning |
| title_fullStr | Electric Vehicle Charging Management Based on Deep Reinforcement Learning |
| title_full_unstemmed | Electric Vehicle Charging Management Based on Deep Reinforcement Learning |
| title_short | Electric Vehicle Charging Management Based on Deep Reinforcement Learning |
| title_sort | electric vehicle charging management based on deep reinforcement learning |
| topic | Deep reinforcement learning data-driven control uncertainty electric vehicles (EVs) |
| url | https://ieeexplore.ieee.org/document/9465776/ |
| work_keys_str_mv | AT sichenli electricvehiclechargingmanagementbasedondeepreinforcementlearning AT weihaohu electricvehiclechargingmanagementbasedondeepreinforcementlearning AT dicao electricvehiclechargingmanagementbasedondeepreinforcementlearning AT tomislavdragicevic electricvehiclechargingmanagementbasedondeepreinforcementlearning AT qihuang electricvehiclechargingmanagementbasedondeepreinforcementlearning AT zhechen electricvehiclechargingmanagementbasedondeepreinforcementlearning AT fredeblaabjerg electricvehiclechargingmanagementbasedondeepreinforcementlearning |