EPCache: In-network video caching for LTE core networks

Video traffic is becoming the dominant form of traffic over mobile networks, challenging the ongoing standardization and deployment of Next generation mobile networks (4G). Currently, as the mainstream design of evolution to 4G, LTE networks provide high data-rate communication tunnels between mobile users and the Internet. However, this generic tunneling communication introduces at least 3 external hops for any request over the network, which results in high latency as well as operating expense, especially for video traffic with high bandwidth requirement. In this work, we propose EPCache, a novel in-network video caching framework for LTE core networks, which addresses the following key questions: (1)what to cache, i.e., how to select in-system video library; (2)how to cache, i.e., how to distribute the selected video library. We prove that the formulated problem is NP-hard. Together with the investigation into characteristics of online video requests, we then propose a fast algorithm for the problem. Extensive simulations are carried out to study the framework. Numerical results show that our algorithm reaches 97 - 99% of optimal. We also discuss critical issues of EPCache implementation in current LTE systems.

[1]  Pablo Rodriguez,et al.  I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system , 2007, IMC '07.

[2]  L. V. Wassenhove,et al.  A survey of algorithms for the generalized assignment problem , 1992 .

[3]  Guangyu Shi,et al.  TECC: Towards collaborative in-network caching guided by traffic engineering , 2012, 2012 Proceedings IEEE INFOCOM.

[4]  Baohua Zhao,et al.  A Collaborative Framework for In-network Video Caching in Mobile Networks , 2014, ArXiv.

[5]  Baohua Zhao,et al.  Joint request routing and video adaptation in collaborative VoD systems , 2013, 2013 IEEE Wireless Communications and Networking Conference (WCNC).

[6]  Jiangchuan Liu,et al.  Statistics and Social Network of YouTube Videos , 2008, 2008 16th Interntional Workshop on Quality of Service.

[7]  Sem C. Borst,et al.  Distributed Caching Algorithms for Content Distribution Networks , 2010, 2010 Proceedings IEEE INFOCOM.

[8]  Li Fan,et al.  Web caching and Zipf-like distributions: evidence and implications , 1999, IEEE INFOCOM '99. Conference on Computer Communications. Proceedings. Eighteenth Annual Joint Conference of the IEEE Computer and Communications Societies. The Future is Now (Cat. No.99CH36320).

[9]  Diomidis Spinellis,et al.  A survey of peer-to-peer content distribution technologies , 2004, CSUR.

[10]  Baohua Zhao,et al.  A fast, simple and near-optimal content placement scheme for a large-scale VoD system , 2012, 2012 IEEE International Conference on Communication Systems (ICCS).

[11]  Van Jacobson,et al.  Adaptive web caching: towards a new global caching architecture , 1998, Comput. Networks.

[12]  V. Srinivasan,et al.  An Algorithm for Assigning Uses to Sources in a Special Class of Transportation Problems , 1973, Oper. Res..

[13]  Sanjeev Khanna,et al.  A PTAS for the multiple knapsack problem , 2000, SODA '00.

[14]  Lada A. Adamic Zipf, Power-laws, and Pareto-a ranking tutorial , 2000 .

[15]  H. Edwin Romeijn,et al.  A class of greedy algorithms for the generalized assignment problem , 2000, Discret. Appl. Math..

[16]  Adriano O. De Maio,et al.  An all Zero-One Algorithm for a Certain Class of Transportation Problems , 1971, Oper. Res..

[17]  Pablo Rodriguez,et al.  Analysis of web caching architectures: hierarchical and distributed caching , 2001, TNET.