内容分发网络与机器学习融合关键技术综述Convergence of content delivery networks and machine learning
吕慧,许力澜,王瑞琨,禹忠
摘要(Abstract)：
内容分发网络在流媒体传输中广泛使用，可以解决其网络性能和服务质量存在的问题。随着流媒体市场需求越来越复杂多样，利用机器学习技术提高内容分发网络的服务质量成为一个新兴的研究热点。概括了使用机器学习融合内容分发网络并提高客户端和服务端性能的几种方法，挖掘出机器学习在内容分发网络应用中亟待解决的关键性技术问题及应对方法。提出了基于机器学习的内容分发网络的未来技术发展趋势，以期进一步提高内容分发网络的资源管理、实时分配和质量规划。
关键词(KeyWords)： 内容分发网络;机器学习;流媒体网络;自适应比特率
基金项目(Foundation): 陕西省重点产业链项目(2018ZDXL-GY-04-01)
作者(Author): 吕慧,许力澜,王瑞琨,禹忠
DOI: 10.13682/j.issn.2095-6533.2022.01.005
参考文献(References)：
- [1] ALOQAILY M,RIDHAWI I A,SALAMEH H B,et al.Data and service management in densely crowded environments:Challenges,opportunities,and recent developments[J].IEEE Communications Magazine,2019,57 (4):81-87.
- [2] OTOUM S,KANTARCI B,MOUFTAH H.Empowering reinforcement learning on big sensed data for intrusion detection[C]//Proceedings of the 2019 IEEE International Conference on Communications(ICC).Shanghai:IEEE,2019:1-7.
- [3] BALACHANDRAN A,SEKAR V,AKELLA A,et al.Developing a predictive model of quality of experience for internet video[J].ACM SIGCOMM Computer Communication Review,2013,43(4):339-350.
- [4] JIANG J,SEKAR V,MILNER H,et al.CFA:A practical prediction system for video QoE optimization[C]//Proceedings of the 13th USENIX Symposium on Networked Systems Design and Implementation(NSDI).[S.l.]:IEEE,2016:137-150.
- [5] JIANG J,SUN S,SEKAR V,et al.Pytheas:Enabling data-driven quality of experience optimization using group-based exploration-exploitation[C]//Proceedings of the 14th USENIX Symposium on Networked Systems Design and Implementation(NSDI).[S.l.]:ACM,2020:393-406.
- [6] GANJAM A,JIANG J,LIU X,et al.C3:Internet-scale control plane for video quality optimization[EB/OL].[2021-08-25].https://dl.acm.org/doi/10.5555/2789770.2789780.
- [7] SUN Y,YIN X,JIANG J,et al.CS2P:Improving video bitrate selection and adaptation with data-driven throughput prediction[C]//Proceedings of the 2020 ACM Conference on Special Interest Group on Data Communication(SIGCOMM).[S.l.]:ACM,2020:272-285.
- [8] MAO H,NETRAVALI R,ALIZADEH M.Neural adaptive video streaming with pensieve[C]//Proceedings of the 2017 Conference of the ACM Special Interest Group on Data Communication(SIGCOMM).[S.l.]:IEEE,2019:197-210.
- [9] HU H,XU Z,ZHANG X,et al.Predicting QoE of video streaming with network-context features[C]//Proceedings of the 2019 2nd International Conference on Hot Information-Centric Networking (HotICN).Chongqing:IEEE,2019:56-57.
- [10] CLAEYS M,LATRE S,FAMAEY J,et al.Design and optimisation of a (FA)Q-learning-based HTTP adaptive streaming client[J].Connection Science,2019,26 (1):25-43.
- [11] VAN D H J,PETRANGELI S,CLAEYS M,et al.A learning-based algorithm for improved bandwidth-awareness of adaptive streaming clients[C]//Proceedings of the 14th IFIP/IEEE International Symposium on Integrated Network Management(IM).Ottawa:IEEE,2019:131-138.
- [12] WANG C,LU Z,WU Z,et al.Optimizing multi-cloud CDN deployment and scheduling strategies using big data analysis[C]//Proceedings of the 14th IEEE International Conference on Services Computing(SCC).Honolulu:IEEE,2017:273-280.
- [13] NARAYANAN A,VERMA S,RAMADAN E,et al.Deepcache:A deep learning based framework for content caching[C]//Proceedings of the 2018 ACM SIGCOMM Workshop on Network Meets AI and ML(NetAI).[S.l.]:ACM,2018:48-53.
- [14] LIU Y,LU D,ZHANG G,et al.Q-learning based content placement method for dynamic cloud content delivery networks[J].IEEE Access,2019,7:66384-66394.
- [15] SHUJA J,BILAL K,ALASMARY W,et al.Applying machine learning techniques for caching in next-generation edge networks:A comprehensive survey[EB/OL].[2021-08-26].https://www.sciencedirect.com/science/article/pii/S1084804521000321 via%3Dihub.
- [16] SUN G,AL-WARD H,BOATENG G O,et al.Autonomous cache resource slicing and content placement at virtualized mobile edge network[J].IEEE Access,2019,7:84727-84743.
- [17] KIRILIN V,SUNDARRAJAN A,GORINSKY S,et al.RL-cache:Learning-based cache admission for content delivery[J].IEEE Journal on Selected Areas in Communications,2020,38 (10):2372-2385.
- [18] ZHU W,WANG Z.Data-driven multimedia edge network and content delivery[J].Scientia Sinica Informationis,2021,51(3):468-504.