NC-CELL: Network Coding-based Content Distribution in Cellular Networks for Cloud Applications
18
0
0
Texte intégral
(2) Agenda. 1. Introduction. 2. Network coding in cellular networks (NC-CELL). 3. Evaluation. 4. Conclusion. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 1 of 10.
(3) Outline. 1. Introduction. 2. Network coding in cellular networks (NC-CELL). 3. Evaluation. 4. Conclusion. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 1 of 10.
(4) Motivation I. Mobile data traffic will rise up to 15 EB per month by 2018. I. By 2017 4.4 billion people will use mobile cloud applications. I. $ 45 billion market Mobile cloud applications will account for 90% of all mobile data traffic by 2018. I. 100%. 50%. 0. 18 %. 17 %. 15 %. 14 %. 12 %. 10 %. 82 %. 83 %. 85 %. 86 %. 88 %. 90 %. 2013. 2014. 2015. 2016. 2017. 2018. Non-Cloud Cloud. Source: Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, 2013-2018. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 2 of 10.
(5) The key idea. Optimizing information delivery of flows in mobile networks with overlapping or partially overlapping content through network coding. I I. Geographically co-located users Mobile cloud applications content I I I I. Advertisement Maps Meteo Google Now. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 3 of 10.
(6) Outline. 1. Introduction. 2. Network coding in cellular networks (NC-CELL). 3. Evaluation. 4. Conclusion. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 3 of 10.
(7) The scenario. Buffers. Network Coding. S-GW. P-GW. Internet. Cloud. MME UE. E-UTRAN. Evolved Packet Core LTE Network. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 4 of 10.
(8) An example UE1. UE2. Request A. eNodeB. Cloud Application. Packet request Packet AUE1 Packet AUE1. Send content A. Cache and forward AUE1. Process and store AUE1. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 5 of 10.
(9) An example UE1. UE2. eNodeB. Request A. Cloud Application. Packet request Packet AUE1 Packet AUE1. Process and store AUE1. Send content A. Cache and forward AUE1. Request B. Packet request Packet BUE2. Packet BUE2. Send content BUE2. Cache and forward BUE2. Process and store BUE2. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 5 of 10.
(10) An example UE1. UE2. eNodeB. Request A. Cloud Application. Packet request Packet AUE1 Packet AUE1. Process and store AUE1. Request B. Packet request Packet BUE2. Packet BUE2 Request B. Send content A. Cache and forward AUE1. Send content BUE2. Cache and forward BUE2. Process and store BUE2 Packet request Packet BUE1. Send content BUE1. Check if B is in buffer Packet (A ⊕ B)UE1,UE2 Decode B using AUE1. Coding (A ⊕ B)UE1,UE2. Decode A using BUE2. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 5 of 10.
(11) The key aspects. I. Monitor and cache in transit traffic. I. Identify coding opportunities. Coding Opportunities eNodeBs can deliver information needed by two or more users with a single coded transmission. I. XOR to combine packets. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 6 of 10.
(12) Content distribution. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. cn−k,1. cn−k+1,2. ⋮ ⋮. ⋮ cn−1,k−1 ⊕ cn,k. cn−k,1 ⊕ cn−k+1,2. cn,k. Individual Transmission -. ⋱. ⋮ c2k−1,k−1 ⊕ c2k,k. ck+1,1 ⊕ ck+2,2. ck+2,2. ck+1,1. ⋱. ⋮ ck−1,k−1 ⊕ ck,k. ck,k c1,1. c2,2. u2 u1. c1,1 ⊕ c2,2. ⋮. ⋱. Users. uk. c2k,k. Optimal allocation for content distribution. Encoded Transmission. t. 7 of 10.
(13) Outline. 1. Introduction. 2. Network coding in cellular networks (NC-CELL). 3. Evaluation. 4. Conclusion. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 7 of 10.
(14) Throughput improvement I. Number of transmissions at eNodeB ( n · (k + ϑ), if r = 0 σ = k n k · (k + ϑ) + k + (r − 1), otherwise I I I. ·104 NC-CELL Disabled. 1 Num. Transmissions. I. n: common chunks k : users ϑ: encoded transmissions r : remainder of n/k. 0.8 0.6 0.4 NC-CELL Enabled. 0.2 0 2. 4 k. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 6. 8. 10. 200. 400. 600. 800 1 000. n 8 of 10.
(15) Evaluation. I. Coding gain η= I. γ σ. 7. γ: total number of chunks. 6. Coding gain η. k = 10. 5 k=8. 4 k=6. 3 k=4. 2. k=2. 1 0. 10. 100. 200. 300. 400. 500. Num. common chunks n. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 9 of 10.
(16) Outline. 1. Introduction. 2. Network coding in cellular networks (NC-CELL). 3. Evaluation. 4. Conclusion. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 9 of 10.
(17) Conclusion. I. Efficient content distribution for cloud applications in mobile cellular networks. I. Network coding and caching performed at eNodeB. I. Considerable throughput improvement. Claudio Fiandrino | IEEE GLOBECOM 2014 | NC-CELL. 10 of 10.
(18) Thank You!.
(19)
Documents relatifs
To efficiently transmit multimedia contents through a wire- less networks in a cross-layer design paradigm, the following points relating the source and the network must be taken
Index Terms—cloud storage, private cloud, content caching, distributed storage, Small Cell networks, open cloud
The problem complexity coupled with the need for self-organizing solutions in small cells mandate distributed approaches in which the SBSs can autonomously decide on in-network
T HE M OBILE C LOUD O FFLOADING H ELPER Mobile Cloud Offloading Helper (MCOH) is a software module, which resides in mobile operator network and uses feedback from the
Our previous work [12] proposes a novel network coding based technique, called NC-CELL (Network Coding in CELLu- lar networks) to improve efficiency of content distribution for
In this paper we propose a network coding based technique, called NC-CELL (Network Coding in CELLular networks), which improves efficiency of content distribution for cloud
In an idealized model, multi-hop wireless networks can be modeled as unit disk graphs of the plane, where two nodes are neighbors if their distance is lower than a fixed radio range
Since then, a rich literature has flourished for both theoretical and practical aspects, and several results have established network coding as an efficient method to broadcast data
