Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach
The worldwide adoption of Electric Vehicles (EVs) has embraced promising advancements toward a sustainable transportation system. However, the effective charging scheduling of EVs is not a trivial task due to the increase in the load demand in the Charging Stations (CSs) and the fluctuation of elect...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/24/8102 |
| _version_ | 1827574925720813568 |
|---|---|
| author | Imen Azzouz Wiem Fekih Hassen |
| author_facet | Imen Azzouz Wiem Fekih Hassen |
| author_sort | Imen Azzouz |
| collection | DOAJ |
| description | The worldwide adoption of Electric Vehicles (EVs) has embraced promising advancements toward a sustainable transportation system. However, the effective charging scheduling of EVs is not a trivial task due to the increase in the load demand in the Charging Stations (CSs) and the fluctuation of electricity prices. Moreover, other issues that raise concern among EV drivers are the long waiting time and the inability to charge the battery to the desired State of Charge (SOC). In order to alleviate the range of anxiety of users, we perform a Deep Reinforcement Learning (DRL) approach that provides the optimal charging time slots for EV based on the Photovoltaic power prices, the current EV SOC, the charging connector type, and the history of load demand profiles collected in different locations. Our implemented approach maximizes the EV profit while giving a margin of liberty to the EV drivers to select the preferred CS and the best charging time (i.e., morning, afternoon, evening, or night). The results analysis proves the effectiveness of the DRL model in minimizing the charging costs of the EV up to 60%, providing a full charging experience to the EV with a lower waiting time of less than or equal to 30 min. |
| first_indexed | 2024-03-08T20:49:01Z |
| format | Article |
| id | doaj.art-9f459cb602924cef80eb2fe98e400018 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-08T20:49:01Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-9f459cb602924cef80eb2fe98e4000182023-12-22T14:06:07ZengMDPI AGEnergies1996-10732023-12-011624810210.3390/en16248102Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized ApproachImen Azzouz0Wiem Fekih Hassen1Higher School of Communication of Tunis (Sup’Com), University of Carthage, 2083 Ariana, TunisiaChair of Distributed Information Systems, University of Passau, Innstraße 41, 94032 Passau, GermanyThe worldwide adoption of Electric Vehicles (EVs) has embraced promising advancements toward a sustainable transportation system. However, the effective charging scheduling of EVs is not a trivial task due to the increase in the load demand in the Charging Stations (CSs) and the fluctuation of electricity prices. Moreover, other issues that raise concern among EV drivers are the long waiting time and the inability to charge the battery to the desired State of Charge (SOC). In order to alleviate the range of anxiety of users, we perform a Deep Reinforcement Learning (DRL) approach that provides the optimal charging time slots for EV based on the Photovoltaic power prices, the current EV SOC, the charging connector type, and the history of load demand profiles collected in different locations. Our implemented approach maximizes the EV profit while giving a margin of liberty to the EV drivers to select the preferred CS and the best charging time (i.e., morning, afternoon, evening, or night). The results analysis proves the effectiveness of the DRL model in minimizing the charging costs of the EV up to 60%, providing a full charging experience to the EV with a lower waiting time of less than or equal to 30 min.https://www.mdpi.com/1996-1073/16/24/8102smart EV chargingday-ahead planningdeep Q-Networkdata-driven approachwaiting timecost minimization |
| spellingShingle | Imen Azzouz Wiem Fekih Hassen Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach Energies smart EV charging day-ahead planning deep Q-Network data-driven approach waiting time cost minimization |
| title | Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach |
| title_full | Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach |
| title_fullStr | Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach |
| title_full_unstemmed | Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach |
| title_short | Optimization of Electric Vehicles Charging Scheduling Based on Deep Reinforcement Learning: A Decentralized Approach |
| title_sort | optimization of electric vehicles charging scheduling based on deep reinforcement learning a decentralized approach |
| topic | smart EV charging day-ahead planning deep Q-Network data-driven approach waiting time cost minimization |
| url | https://www.mdpi.com/1996-1073/16/24/8102 |
| work_keys_str_mv | AT imenazzouz optimizationofelectricvehicleschargingschedulingbasedondeepreinforcementlearningadecentralizedapproach AT wiemfekihhassen optimizationofelectricvehicleschargingschedulingbasedondeepreinforcementlearningadecentralizedapproach |