AoI-Aware Agentic Federated Mixture-of-Digital-Twin Experts for 6G Vehicular Edge Intelligence
Document Type
Article
Source of Publication
IEEE Open Journal of the Communications Society
Publication Date
1-1-2026
Abstract
Digital twin-enabled vehicular edge intelligence is expected to become a fundamental service paradigm for sixth-generation (6G) intelligent transportation systems. However, the performance of such systems depends not only on model accuracy, but also on the freshness of digital twin states, timeliness of inference, privacy-preserving model training, and efficient use of heterogeneous edge resources. Existing DT-assisted federated learning and edge mixture-of-experts solutions optimize digital twin synchronization, distributed learning, and sparse inference largely independently, without allowing digital twin states to actively govern expert specialization, expert refreshing, and distributed orchestration. Nevertheless, the joint problem of how digital twins should guide federated expert specialization, expert routing, expert refreshing, and expert migration remains largely unexplored. In this paper, we propose an AoI-aware agentic federated mixture-of-digital-twin experts framework (AA-FedMoDTE) for 6G vehicular edge intelligence. The proposed framework treats digital twins as active control states for federated MoE training and deployment. We introduce a digital-twin-driven client–expert alignment mechanism, an AoI and Age-of-Knowledge-aware expert routing and refreshing strategy, and a dual-timescale multi-agent orchestration framework for expert placement, migration, federated aggregation, and real-time inference. The proposed methodology provides a unified theoretical and algorithmic foundation for freshness-aware, privacy-preserving, and resource-efficient edge intelligence in highly dynamic vehicular networks. Simulation results show that AA-FedMoDTE consistently reduces AoI, AoK, end-to-end latency and communication overhead while improving task accuracy. The gains come from twin-guided client-expert alignment, sparse expert routing and freshness-aware refreshing under dynamic vehicular edge conditions.
DOI Link
ISSN
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Disciplines
Computer Sciences
Keywords
6G, Age of Information, Digital twin, federated learning, mixture-of-experts, multi-agent learning, vehicular edge computing
Scopus ID
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Recommended Citation
Tariq, Asadullah; Serhani, Mohamed Adel; Taleb, Ikbal; Alkobaisi, Shayma; Qayyum, Tariq; and Ud Din, Irfan, "AoI-Aware Agentic Federated Mixture-of-Digital-Twin Experts for 6G Vehicular Edge Intelligence" (2026). All Works. 8347.
https://zuscholars.zu.ac.ae/works/8347
Indexed in Scopus
yes
Open Access
yes
Open Access Type
Gold: This publication is openly available in an open access journal/series