EUVIMEDEUVIMED entdecken
Crossref

Recommendation-Enabled Caching Strategy With Age of Information in Edge–Cloud Networks

Xiaoyan Zhao, Fengxian Hou, Peiyan Yuan, Chenyang Wang, Junna Zhang, Hu Jin

IEEE Transactions on Network Science and Engineering · 2026 · 13 · 1538-1553

DOI: 10.1109/tnse.2025.3597136 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Network Science and Engineering, 2026. Verfasst von Xiaoyan Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 80 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Science and Technology Research Project of Henan province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The recommendation of local content in edge servers is a crucial strategy to alleviate cloud pressure and enhance resource utilization in edge-cloud networks. However, the dynamic complexities of user request behavior and the diminishing value of cached content have not been adequately accounted for in time-varying recommendation-enabled caching systems. In this study, an edge caching problem integrating content recommendation and Age of Information (AoI) based on user requests and content value is proposed to maximize system revenue in time-varying scenarios. Firstly, a personalized user request model is proposed to capture dynamic influences from content recommendation and user historical requests. Then, the optimization problem is decomposed into two subproblems: the content recommendation problem and the cache replacement problem. Moreover, the content recommendation problem is proved to exhibit monotone submodularity, and a greedy algorithm with $(1 - \frac{1}{e})$-approximate solution is proposed to determine the recommendation set for each user. Furthermore, the cache replacement problem is formulated as a Markov decision process, and an iterative optimization algorithm combining Recommendation and AoI based on Double Deep Q-Network (RA-DDQN) is proposed to maximize the long-term system revenue. Finally, extensive experiments conducted on a real dataset validate the superiority of the proposed algorithm compared to other algorithms.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Research Project of Henan province

Zitieren

APA

Zhao, X., Hou, F., Yuan, P., Wang, C., Zhang, J., & Jin, H. (2026). Recommendation-Enabled Caching Strategy With Age of Information in Edge–Cloud Networks. IEEE Transactions on Network Science and Engineering, 13, 1538-1553. https://doi.org/10.1109/tnse.2025.3597136

Vancouver

Zhao X, Hou F, Yuan P, Wang C, Zhang J, Jin H. Recommendation-Enabled Caching Strategy With Age of Information in Edge–Cloud Networks. IEEE Transactions on Network Science and Engineering. 2026;13:1538-1553. doi:10.1109/tnse.2025.3597136

BibTeX
@article{Zhao2026,
  author = {Zhao, Xiaoyan and Hou, Fengxian and Yuan, Peiyan and Wang, Chenyang and Zhang, Junna and Jin, Hu},
  title = {Recommendation-Enabled Caching Strategy With Age of Information in Edge–Cloud Networks},
  journal = {IEEE Transactions on Network Science and Engineering},
  year = {2026},
  volume = {13},
  pages = {1538--1553},
  doi = {10.1109/tnse.2025.3597136}
}
Kostenlos starten →