Federated learning for smart charging of connected electric vehicles
Fuente:
Zenodo
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Recurso digital |
| Publié: |
Zenodo
2021
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866902155424694272 |
|---|---|
| author | Al-Zuhairi, Yaqoob kannan, prashanth Aguilar Igartua, Mónica |
| author_facet | Al-Zuhairi, Yaqoob kannan, prashanth Aguilar Igartua, Mónica |
| contents | <p>Due to rising concerns over climate change, air<br>pollution and clean energy awareness, the demand<br>for electric vehicles (EVs) and renewable energy<br>generation has increased in recent years. The main<br>objective of this research is to design a decentralized<br>smart charging coordination framework for<br>EVs based on federated learning (FL) algorithms<br>in order to provide an acceptable collaboratively<br>learning model with privacy preservation of EVs,<br>improve charging scenarios, contribute to smart<br>grid stabilization, meet EVs energy requirements<br>wherever and whenever they request, and gain<br>welfare for EV owners. Moreover, FL is introduced<br>with the goal of bringing machine learning (ML)<br>down to the edge level in vehicular networks.<br>Ultimately, a multimetric routing protocol is also<br>used to predict the best route for transmitting<br>messages among EVs, infrastructures, charging<br>stations (CSs), and central servers.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_17315738 |
| institution | Zenodo |
| language | |
| publishDate | 2021 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Federated learning for smart charging of connected electric vehicles Al-Zuhairi, Yaqoob kannan, prashanth Aguilar Igartua, Mónica SCITEL JITEL2021 Telecommunications <p>Due to rising concerns over climate change, air<br>pollution and clean energy awareness, the demand<br>for electric vehicles (EVs) and renewable energy<br>generation has increased in recent years. The main<br>objective of this research is to design a decentralized<br>smart charging coordination framework for<br>EVs based on federated learning (FL) algorithms<br>in order to provide an acceptable collaboratively<br>learning model with privacy preservation of EVs,<br>improve charging scenarios, contribute to smart<br>grid stabilization, meet EVs energy requirements<br>wherever and whenever they request, and gain<br>welfare for EV owners. Moreover, FL is introduced<br>with the goal of bringing machine learning (ML)<br>down to the edge level in vehicular networks.<br>Ultimately, a multimetric routing protocol is also<br>used to predict the best route for transmitting<br>messages among EVs, infrastructures, charging<br>stations (CSs), and central servers.</p> |
| title | Federated learning for smart charging of connected electric vehicles |
| topic | SCITEL JITEL2021 Telecommunications |
| url | https://doi.org/10.5281/zenodo.17315738 |