EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Edge and Fog Computing in Vehicular Networks: State‐of‐the‐Art, Challenges, and Future Directions

Yazeed Yasin Ghadi, Sunawar Khan, Tehseen Mazhar, Muhammad Usman Tariq, Tariq Shahzad, Wasim Ahmad, Habib Hamam

IET Intelligent Transport Systems · 2026-01 · 20 (1)

DOI: 10.1049/itr2.70371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Intelligent Transport Systems, online erschienen am 16.11.2026. Verfasst von Yazeed Yasin Ghadi und 6 weiteren Autor:innen. Die Arbeit nennt 145 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Problem: Intelligent Transportation Systems (ITS) and Internet of Vehicles (IoV) applications increasingly require low‐latency, reliable, and mobility‐aware computation for safety‐critical and data‐intensive services. However, existing reviews of Vehicular Edge Computing (VEC) and Vehicular Fog Computing (VFC) often remain architecture‐specific, provide limited synthesis of recent AI‐ and 6G‐enabled developments, and do not sufficiently examine the gap between simulation‐based performance gains and real‐world deployment constraints.

Aim

This paper presents a systematic, taxonomy‐driven, and deployment‐aware survey of edge and fog computing in vehicular networks.

Methods

Following PRISMA‐based guidelines, 680 records from major scholarly databases were screened, 95 duplicates were removed, 275 full‐text articles were assessed, and 145 studies published between 2016 and 2026 were selected for detailed synthesis.

Results

The review organises the literature around VEC, VFC, hybrid edge‐fog architectures, AI‐enabled resource orchestration, computation offloading, caching, mobility management, security, and 6G‐oriented communication. Reported literature values indicate that AI‐based offloading, caching, and cooperative fog mechanisms can substantially reduce latency and backhaul demand under study‐specific assumptions; however, these gains are not directly comparable across all studies because they depend on simulator settings, mobility models, channel conditions, baseline methods, and traffic density. The analysis further reveals persistent sim‐to‐real barriers, including handover delay, channel variability, resource heterogeneity, security overhead, scalability limitations, and lack of standardised benchmarks.

Conclusion

The survey contributes a dynamic taxonomy, a critical comparison of VEC/VFC/hybrid paradigms, a clarified performance‐metric taxonomy, and a concrete roadmap for AI‐native, secure, sustainable, and 6G‐enabled vehicular edge‐fog computing.

Zitieren

APA

Ghadi, Y. Y., Khan, S., Mazhar, T., Tariq, M. U., Shahzad, T., Ahmad, W., & Hamam, H. (2026). Edge and Fog Computing in Vehicular Networks: State‐of‐the‐Art, Challenges, and Future Directions. IET Intelligent Transport Systems, 20(1). https://doi.org/10.1049/itr2.70371

Vancouver

Ghadi YY, Khan S, Mazhar T, Tariq MU, Shahzad T, Ahmad W, et al. Edge and Fog Computing in Vehicular Networks: State‐of‐the‐Art, Challenges, and Future Directions. IET Intelligent Transport Systems. 2026;20(1). doi:10.1049/itr2.70371

BibTeX
@article{Ghadi2026,
  author = {Ghadi, Yazeed Yasin and Khan, Sunawar and Mazhar, Tehseen and Tariq, Muhammad Usman and Shahzad, Tariq and Ahmad, Wasim and Hamam, Habib},
  title = {Edge and Fog Computing in Vehicular Networks: State‐of‐the‐Art, Challenges, and Future Directions},
  journal = {IET Intelligent Transport Systems},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/itr2.70371}
}
Kostenlos starten →