Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management
This paper presents a high-fidelity multi-physics dynamic model for electric vehicles, serving as a fundamental building block for intelligent vehicle-to-grid (V2G) integration systems. The model accurately captures complex vehicle dynamics of the powertrain, battery, and regenerative braking, enabl...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/15/8214 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849405877560279040 |
|---|---|
| author | Michela Costa Gianluca Del Papa |
| author_facet | Michela Costa Gianluca Del Papa |
| author_sort | Michela Costa |
| collection | DOAJ |
| description | This paper presents a high-fidelity multi-physics dynamic model for electric vehicles, serving as a fundamental building block for intelligent vehicle-to-grid (V2G) integration systems. The model accurately captures complex vehicle dynamics of the powertrain, battery, and regenerative braking, enabling precise energy consumption evaluation, including in AI-driven V2G scenarios. Validated using real-world data from a Citroën Ami operating on urban routes in Naples, Italy, it achieved exceptional accuracy with a root mean square error (RMSE) of 1.28% for dynamic state of charge prediction. This robust framework provides an essential foundation for AI-driven digital twin technologies in V2G applications, significantly advancing sustainable transportation and smart grid integration through predictive simulation. Its versatility supports diverse fleet applications, from residential energy management and coordinated charging optimization to commercial car sharing operations, leveraging backup power during peak demand or grid outages, so to maximize distributed battery storage utilization. |
| format | Article |
| id | doaj-art-20e1a29378494b9ba63bd3e50a460bbf |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-20e1a29378494b9ba63bd3e50a460bbf2025-08-20T03:36:33ZengMDPI AGApplied Sciences2076-34172025-07-011515821410.3390/app15158214Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy ManagementMichela Costa0Gianluca Del Papa1National Research Council, Institute of Science and Technology for Sustainable Energy and Mobility, Via Guglielmo Marconi, 4, 80125 Naples, ItalyNational Research Council, Institute of Science and Technology for Sustainable Energy and Mobility, Via Guglielmo Marconi, 4, 80125 Naples, ItalyThis paper presents a high-fidelity multi-physics dynamic model for electric vehicles, serving as a fundamental building block for intelligent vehicle-to-grid (V2G) integration systems. The model accurately captures complex vehicle dynamics of the powertrain, battery, and regenerative braking, enabling precise energy consumption evaluation, including in AI-driven V2G scenarios. Validated using real-world data from a Citroën Ami operating on urban routes in Naples, Italy, it achieved exceptional accuracy with a root mean square error (RMSE) of 1.28% for dynamic state of charge prediction. This robust framework provides an essential foundation for AI-driven digital twin technologies in V2G applications, significantly advancing sustainable transportation and smart grid integration through predictive simulation. Its versatility supports diverse fleet applications, from residential energy management and coordinated charging optimization to commercial car sharing operations, leveraging backup power during peak demand or grid outages, so to maximize distributed battery storage utilization.https://www.mdpi.com/2076-3417/15/15/8214digital twinselectric vehiclesvehicle-to-gridmulti-physics modellingartificial intelligenceenergy flow optimization |
| spellingShingle | Michela Costa Gianluca Del Papa Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management Applied Sciences digital twins electric vehicles vehicle-to-grid multi-physics modelling artificial intelligence energy flow optimization |
| title | Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management |
| title_full | Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management |
| title_fullStr | Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management |
| title_full_unstemmed | Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management |
| title_short | Digital Twins for Intelligent Vehicle-to-Grid Systems: A Multi-Physics EV Model for AI-Based Energy Management |
| title_sort | digital twins for intelligent vehicle to grid systems a multi physics ev model for ai based energy management |
| topic | digital twins electric vehicles vehicle-to-grid multi-physics modelling artificial intelligence energy flow optimization |
| url | https://www.mdpi.com/2076-3417/15/15/8214 |
| work_keys_str_mv | AT michelacosta digitaltwinsforintelligentvehicletogridsystemsamultiphysicsevmodelforaibasedenergymanagement AT gianlucadelpapa digitaltwinsforintelligentvehicletogridsystemsamultiphysicsevmodelforaibasedenergymanagement |