Towards mobility aware knowledge sharing in vehicular knowledge networks

Salah Ud Din, Muhammad; Härri, Jérôme
CSCN 2025, IEEE Conference on Standards for Communications and Networking, 15-17 September 2025, Bologna, Italy

Modern artificial intelligence (AI) techniques, combined with powerful far-edge computing capabilities, enable vehicles to cooperate, generate, and share knowledge with other vehicles over ad-hoc wireless technologies. In such decentralized vehicular knowledge networks, Named Data Networking (NDN) offers a promising paradigm to link knowledge consumers and producers without reliance on centralized infrastructure. One challenge in sharing knowledge over NDN lies in its redundancybased multi-hop dissemination mechanism, which can introduce inefficiencies and delays. Given the size and time sensitivity of knowledge, this necessitates fast and reliable dissemination strategies. This paper presents Mobility-Aware Knowledge Sharing
(MAKS), a scheme that considers vehicular dynamics and trajectory information to develop a mobility-aware forwarding information base (MaFIB), ensuring reliable knowledge sharing and reverse path stability in continuously varying network conditions.
Simulation results show that MAKS achieves a knowledge delivery ratio above 90%, reduces the path partition rate by over 40%, and lowers the number of retransmissions by more than threefold compared to other approaches.

HAL
Type:
Conférence
City:
Bologna
Date:
2025-09-15
Department:
Systèmes de Communication
Eurecom Ref:
8321
Copyright:
© 2025 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PERMALINK : https://www.eurecom.fr/publication/8321