FlyCache: Recommendation-driven edge caching architecture for full life cycle of video streaming^✩

Abstract

With the rapid development of 5G technology, the proportion of video traffic on the Internet is increasing, bringing pressure on the network infrastructure. Edge computing technology provides a feasible solution for optimizing video content distribution. However, the limited edge node cache capacity and dynamic user requests make edge caching more complex. Therefore, we propose a recommendation-driven edge Caching network architecture for the Full life cycle of video streaming (FlyCache) designed to improve users’ Quality of Experience (QoE) and reduce backhaul traffic consumption. FlyCache implements intelligent caching management across three key stages: before-playback, during-playback, and after-playback. Specifically, we introduce a cache placement policy for the before-playback stage, a dynamic prefetching and cache admission policy for the during-playback stage, and a progressive cache eviction policy for the after-playback stage. To validate the effectiveness of FlyCache, we developed a user behavior-driven edge caching simulation framework incorporating recommendation mechanisms. Experiments conducted on the MovieLens and synthetic datasets demonstrate that FlyCache outperforms other caching strategies in terms of byte hit rate, backhaul traffic, and delayed startup rate.

Keywords

Edge caching / Cache architecture / Cache placement / Cache admission / Caching eviction

References

[1] P. Chen, W. He, W. Ma, X. Huang, C. Wang, Iotdq: an industrial iot data analysis library for apache iotdb, Big Data Min. Anal. 7 (1) (2024) 29-41.

[2] Ericsson, Ericsson mobility report November 2024, https://www.ericsson.com/en/reports-and-papers/mobility-report/reports/november-2024. (Accessed 29 Novem-ber 2024).

[3] A.-J. Su, D.R. Choffnes, A. Kuzmanovic, F.E. Bustamante, Drafting behind akamai: in-ferring network conditions based on cdn redirections, IEEE/ACM Trans. Netw. 17 (6)(2009) 1752-1765.

[4] S. Shao, W. Gong, H. Yang, S. Guo, L. Chen, A. Xiong, Data trusted sharing delivery: a blockchain-assisted software-defined content delivery network, IEEE Internet Things J. 10 (14) (2021) 11949-11959.

[5] P. Casas, A. D’Alconzo, P. Fiadino, A. Bär, A. Finamore, On the analysis of qoe-based performance degradation in youtube traffic, in: Proceedings of the 10th International Conference on Network and Service Management (CNSM) and Workshop, IEEE, 2014, pp. 1-9.

[6] W. Shi, J. Cao, Q. Zhang, Y. Li, L. Xu, Edge computing: vision and challenges, IEEE Internet Things J. 3 (5) (2016) 637-646.

[7] K. Kumaran, E. Sasikala, Learning based latency minimization techniques in mobile edge computing (mec) systems: a comprehensive survey,in:Proceedings of the 2021 International Conference on System, Computation, Automation and Networking (IC-SCAN), IEEE, 2021, pp. 1-6.

[8] H. Ahlehagh, S. Dey, Video-aware scheduling and caching in the radio access net-work, IEEE/ACM Trans. Netw. 22 (5) (2014) 1444-1462.

[9] D. Liu, B. Chen, C. Yang, A.F. Molisch, Caching at the wireless edge: design aspects, challenges, and future directions, IEEE Commun. Mag. 54 (9) (2016) 22-28.

[10] S. Sen, J. Rexford, D. Towsley,Proxy prefix caching for multimedia streams, in:Proceedings of the IEEE INFOCOM’99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Com-munications Societies. The Future Is Now (Cat. No.99CH36320), vol. 3, IEEE, 1999, pp. 1310-1319.

[11] K.-L. Wu, P.S. Yu, J.L. Wolf, Segmentation of multimedia streams for proxy caching, IEEE Trans. Multimed. 6 (5) (2004) 770-780.

[12] L. Maggi, L. Gkatzikis, G. Paschos, J. Leguay, Adapting caching to audience retention rate, Comput.commun. 116 (2018) 159-171.

[13] X. Huang, L. He, L. Wang, F. Li, Towards 5 g: joint optimization of video seg-ment caching, transcoding and resource allocation for adaptive video streaming in a multi-access edge computing network, IEEE Trans. Veh. Technol. 70 (10) (2021) 10909-10924.

[14] B. Chen, C. Yang, Caching policy for cache-enabled d2d communications by learning user preference, IEEE Trans. Commun. 66 (12) (2018) 6586-6601.

[15] L.E. Chatzieleftheriou, M. Karaliopoulos, I. Koutsopoulos, Jointly optimizing content caching and recommendations in small cell networks, IEEE Trans. Mob.comput. 18 (1) (2018) 125-138.

[16] A.C.B. Monção, S.L. Correa, A.C. Viana, K.V. Cardoso, Combining resource-aware recommendation and caching in the era of mec for improving the experience of video streaming users, IEEE Trans. Serv.comput. 16 (3) (2023) 1698-1712.

[17] W. Liu, H. Zhang, H. Ding, Z. Yu, D. Yuan, Recommendation based video caching and transcoding in mobile edge networks, IEEE Trans. Veh. Technol. 73 (5) (2024) 6572-6583.

[18] P. Sermpezis, T. Giannakas, T. Spyropoulos, L. Vigneri, Soft cache hits: improving performance through recommendation and delivery of related content, IEEE J. Sel. Areas Commun. 36 (6) (2018) 1300-1313.

[19] X. Wang, C. Wang, X. Li, V.C. Leung, T. Taleb, Federated deep reinforcement learning for Internet of things with decentralized cooperative edge caching, IEEE Internet Things J. 7 (10) (2020) 9441-9455.

[20] P. Lin, Z. Ning, Z. Zhang, Y. Liu, F.R. Yu, V.C. Leung, Joint optimization of preference-aware caching and content migration in cost-efficient mobile edge net-works, IEEE Trans. Wirel.commun. 23 (5) (2024) 4918-4931.

[21] D.S. Berger, R.K. Sitaraman, M. Harchol-Balter, AdaptSize: orchestrating the hot ob-ject memory cache in a content delivery network,in:Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17), USENIX Association, 2017, pp. 483-498.

[22] V. Kirilin, A. Sundarrajan, S. Gorinsky, R.K. Sitaraman, Rl-cache: learning-based cache admission for content delivery,in:Proceedings of the 2019 Workshop on Net-work Meets AI & ML, ACM, 2019, pp. 57-63.

[23] Y. Guan, X. Zhang, Z. Guo, Prefcache: edge cache admission with user preference learning for video content distribution, IEEE Trans. Circuits Syst. Video Technol. 31 (4) (2020) 1618-1631.

[24] N. Megiddo, D.S. Modha, ARC: a self-tuning, low overhead replacement cache,in:Proceedings of the 2nd USENIX Conference on File and Storage Technologies, USENIX Association, 2003, pp. 115-130.

[25] J. Yang, Y. Zhang, Z. Qiu, Y. Yue, R. Vinayak, FIFO queues are all you need for cache eviction, in: Proceedings of the 29th Symposium on Operating Systems Principles, ACM, 2023, pp. 130-149.

[26] P. Li, Y. Zhang, H. Zhang, W. Wang, K. Xu, Z. Zhang, A delayed eviction caching replacement strategy with unified standard for edge servers, Comput. Netw. 230 (2023) 109794.

[27] S.S. Krishnan, R.K. Sitaraman, Video stream quality impacts viewer behavior: in-ferring causality using quasi-experimental designs, IEEE/ACM Trans. Netw. 21 (6)(2013) 2001-2014.

[28] T. Joachims, L. Granka, B. Pan, H. Hembrooke, G. Gay, Accurately interpreting click-through data as implicit feedback, SIGIR Forum 51 (1) (2017) 4-11.

[29] S. Wu, M.-A. Rizoiu, L. Xie, Beyond views: measuring and predicting engagement in online videos,in: Proceedings of the International AAAI Conference on Web and Social Media, vol. 12, AAAI Press, 2018, pp. 434-443.

[30] R. Zhan, C. Pei, Q. Su, J. Wen, X. Wang, G. Mu, D. Zheng, P. Jiang, K. Gai, De-confounding duration bias in watch-time prediction for video recommendation, in: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ACM, 2022, pp. 4472-4481.

[31] Y. Zhang, Y. Bai, J. Chang, X. Zang, S. Lu, J. Lu, F. Feng, Y. Niu, Y. Song, Leveraging watch-time feedback for short-video recommendations: a causal labeling frame-work,in:Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, ACM, 2023, pp. 4952-4959.