MicroCast: Cooperative Video Streaming on Smartphones Lorenzo KellerEPFL, Lausanne, Switzerland Anh LeUniversity of California at Irvine, Irvine, CA, USA.

Slides:



Advertisements
Similar presentations
A DISTRIBUTED CSMA ALGORITHM FOR THROUGHPUT AND UTILITY MAXIMIZATION IN WIRELESS NETWORKS.
Advertisements

February 20, Spatio-Temporal Bandwidth Reuse: A Centralized Scheduling Mechanism for Wireless Mesh Networks Mahbub Alam Prof. Choong Seon Hong.
IEEE INFOCOM 2004 MultiNet: Connecting to Multiple IEEE Networks Using a Single Wireless Card.
Roma 17/10/08 WORLD Project KO Meeting Laura Galluccio WORLD Project – KO Meeting University of Catania.
SoNIC: Classifying Interference in Sensor Networks Frederik Hermans et al. Uppsala University, Sweden IPSN 2013 Presenter: Jeffrey.
MicroCast: Cooperative Video Streaming on Smartphones Lorenzo Keller, Anh Le, Blerim Cic, Hulya Seferoglu LIDS, Christina Fragouli, Athina Markopoulou.
XORs in The Air: Practical Wireless Network Coding
VSMC MIMO: A Spectral Efficient Scheme for Cooperative Relay in Cognitive Radio Networks 1.
Maximum Battery Life Routing to Support Ubiquitous Mobile Computing in Wireless Ad Hoc Networks By C. K. Toh.
Clayton Sullivan PEER-TO-PEER NETWORKS. INTRODUCTION What is a Peer-To-Peer Network A Peer Application Overlay Network Network Architecture and System.
Lava: A Reality Check of Network Coding in Peer-to-Peer Live Streaming Mea Wang, Baochun Li Department of Electrical and Computer Engineering University.
Suphakit Awiphan, Takeshi Muto, Yu Wang, Zhou Su, Jiro Katto
An Energy Efficient Hierarchical Heterogeneous Wireless Sensor Network
Adaptive Video Streaming in Vertical Handoff: A Case Study Ling-Jyh Chen, Guang Yang, Tony Sun, M. Y. Sanadidi, Mario Gerla Computer Science Department,
A Comparison of Layering and Stream Replication Video Multicast Schemes Taehyun Kim and Mostafa H. Ammar.
Network Coding for Large Scale Content Distribution Christos Gkantsidis Georgia Institute of Technology Pablo Rodriguez Microsoft Research IEEE INFOCOM.
NCKU CSIE CIAL1 Principles and Protocols for Power Control in Wireless Ad Hoc Networks Authors: Vikas Kawadia and P. R. Kumar Publisher: IEEE JOURNAL ON.
Data Provisioning Services for mobile clients by Mustafa Ergen Authors: Mohit Agarwal and Anuj Puri Berkeley WOW Group University.
Bluenet a New Scatternet Formation Scheme * Huseyin Ozgur Tan * Zifang Wang,Robert J.Thomas, Zygmunt Haas ECE Cornell Univ*
Online Data Gathering for Maximizing Network Lifetime in Sensor Networks IEEE transactions on Mobile Computing Weifa Liang, YuZhen Liu.
Using Bluetooth on Android Devices to Implement Real-Time Multiplayer Games Brad Boone, Corey Darr, Chris Hayes, Dale Musser, Ph.D. Introduction With the.
A Transmission Control Scheme for Media Access in Sensor Networks Alec Woo, David Culler (University of California, Berkeley) Special thanks to Wei Ye.
Peer-to-peer Multimedia Streaming and Caching Service by Won J. Jeon and Klara Nahrstedt University of Illinois at Urbana-Champaign, Urbana, USA.
Power saving technique for multi-hop ad hoc wireless networks.
1 Algorithms for Bandwidth Efficient Multicast Routing in Multi-channel Multi-radio Wireless Mesh Networks Hoang Lan Nguyen and Uyen Trang Nguyen Presenter:
By: Matthew Follett. Introduction  A Wireless local area network (WLAN) links two or more devices using some wireless distribution method and usually.
A Fair Scheduling for Wireless Mesh Networks Naouel Ben Salem and Jean-Pierre Hubaux Laboratory of Computer Communications and Applications (LCA) EPFL.
Capacity of Wireless Mesh Networks: Comparing Single- Radio, Dual-Radio, and Multi- Radio Networks By: Alan Applegate.
Capacity Scaling with Multiple Radios and Multiple Channels in Wireless Mesh Networks Oguz GOKER.
Network Aware Resource Allocation in Distributed Clouds.
Incentive Based Data Sharing in Delay Tolerant Mobile Networks.
MicroPlay: A Networking Framework for Local Multiplayer Games A. Le †, L. Keller ‡, C. Fragouli ‡, A. Markopoulou † † University of California, Irvine.
Doc.: IEEE /272r0 Submission June 2001 Phil Jamieson, Philips SemiconductorsSlide 1 Project: IEEE P Working Group for Wireless Personal.
1 Insertion of ISP-owned Peer & Locality Awareness in BitTorrent Ioanna Papafili, George D. Stamoulis, Sergios Soursos AUEB EuroNF workshop, Athens October.
03/09/2003Helsinki University of Technology1 Overview of Thesis Topic Presented By: Zhao Xuetao.
Mohamed Hefeeda 1 School of Computing Science Simon Fraser University, Canada Video Streaming over Cooperative Wireless Networks Mohamed Hefeeda (Joint.
IEEE Globecom 2010 Tan Le Yong Liu Department of Electrical and Computer Engineering Polytechnic Institute of NYU Opportunistic Overlay Multicast in Wireless.
A novel approach of gateway selection and placement in cellular Wi-Fi system Presented By Rajesh Prasad.
User Cooperation via Rateless Coding Mahyar Shirvanimoghaddam, Yonghui Li, and Branka Vucetic The University of Sydney, Australia IEEE GLOBECOM 2012 &
A Smart Decision Model for Vertical Handoff Ling-Jyh Chen *, Tony Sun *, Benny Chen *, Venkatesh Rajendran †, Mario Gerla * * Department of Computer Science,
Opportunistic Use of Client Repeaters to Improve Performance of WLANs Victor Bahl 1, Ranveer Chandra 1, Patrick P. C. Lee 2, Vishal Misra 2, Jitendra Padhye.
Load-Balancing Routing in Multichannel Hybrid Wireless Networks With Single Network Interface So, J.; Vaidya, N. H.; Vehicular Technology, IEEE Transactions.
Paper # – 2009 A Comparison of Heterogeneous Video Multicast schemes: Layered encoding or Stream Replication Authors: Taehyun Kim and Mostafa H.
IEEE MEDIA INDEPENDENT HANDOVER DCN: Title: Data Offload Service through Wireless P2P Networks based on IEEE Framework.
Downlink Scheduling With Economic Considerations to Future Wireless Networks Bader Al-Manthari, Nidal Nasser, and Hossam Hassanein IEEE Transactions on.
Vertical Optimization Of Data Transmission For Mobile Wireless Terminals MICHAEL METHFESSEL, KAI F. DOMBROWSKI, PETER LANGENDORFER, HORST FRANKENFELDT,
SocialTube: P2P-assisted Video Sharing in Online Social Networks
End-to-End Efficiency (E 3 ) Integrating Project of the EC 7 th Framework Programme General View of the E3 Prototyping Environment for Cognitive and Self-x.
Copyright © 2011, Scalable and Energy-Efficient Broadcasting in Multi-hop Cluster-Based Wireless Sensor Networks Long Cheng ∗ †, Sajal K. Das†,
An Energy Efficient MAC Protocol for Wireless LANs, E.-S. Jung and N.H. Vaidya, INFOCOM 2002, June 2002 吳豐州.
Stretchable Architectures for Next Generation Cellular Networks Presented By Shashidhar Lakkavalli, Ansuya Negi and Dr. Suresh Singh Portland State University.
1 DozyAP: Power-Efficient Wi-Fi Tethering Speaker Hao Han College of William & Mary 3/22/2013 W&M Graduate Research Symposium 2013.
Doc.: IEEE /0542r0 SubmissionSimone Merlin, QualcommSlide 1 HEW Scenarios and Goals Date: Authors: May 2013.
Tufts Wireless Laboratory School Of Engineering Tufts University Paper Review “An Energy Efficient Multipath Routing Protocol for Wireless Sensor Networks”,
Cooperative MIMO Paradigms for Cognitive Radio Networks
Proposal of OmniRAN architecture for Data Offload Service through Wireless P2P Networks Document Number: omniran Date Submitted:
RM-MAC: A Routing-Enhanced Multi-Channel MAC Protocol in Duty-Cycle Sensor Networks Ye Liu, Hao Liu, Qing Yang, and Shaoen Wu In Proceedings of the IEEE.
Heterogeneous Wireless Access in Large Mesh Networks Haiping Liu, Xin Liu, Chen-Nee Chuah, Prasant Mohapatra University of California, Davis IEEE MASS.
2012 1/6 NSDI’08 Harnessing Exposed Terminals in Wireless Networks Mythili Vutukuru, Kyle Jamieson, and Hari Balakrishnan MIT Computer Science and Artificial.
Doc.: IEEE /00144r0 Submission 3/01 Nada Golmie, NISTSlide 1 IEEE P Working Group for Wireless Personal Area Networks Dialog with FCC Nada.
1 Low Latency Multimedia Broadcast in Multi-Rate Wireless Meshes Chun Tung Chou, Archan Misra Proc. 1st IEEE Workshop on Wireless Mesh Networks (WIMESH),
Multimedia Retrieval Architecture Electrical Communication Engineering, Indian Institute of Science, Bangalore – , India Multimedia Retrieval Architecture.
THE EMERGING TECHNOLOGY IN WIRELESS COMMUNICATION.
LA-MAC: A Load Adaptive MAC Protocol for MANETs IEEE Global Telecommunications Conference(GLOBECOM )2009. Presented by Qiang YE Smart Grid Subgroup Meeting.
Optimization-based Cross-Layer Design in Networked Control Systems Jia Bai, Emeka P. Eyisi Yuan Xue and Xenofon D. Koutsoukos.
Efficient Opportunistic Sensing using Mobile Collaborative Platform MOSDEN.
-1/16- Maximum Battery Life Routing to Support Ubiquitous Mobile Computing in Wireless Ad Hoc Networks C.-K. Toh, Georgia Institute of Technology IEEE.
Network Topologies for Scalable Multi-User Virtual Environments Lingrui Liang.
MicroCast: Cooperative Video Streaming on Smartphones
Golrezaei, N. ; Molisch, A.F. ; Dimakis, A.G.
Presentation transcript:

MicroCast: Cooperative Video Streaming on Smartphones Lorenzo KellerEPFL, Lausanne, Switzerland Anh LeUniversity of California at Irvine, Irvine, CA, USA Blerim CiciUniversity of California at Irvine, Irvine, CA, USA Hulya SeferogluMassachusettes Institute of Tachnology, Boston, MA, USA Christina FragouliEPFL, Lausanne, Switzerland Athina MarkopoulouUniversity of California at Irvine, Irivine, CA, USA MobiSys’12, June 25–29, 2012, Low Wood Bay, Lake District, UK

Outline Introduction MicroCast Architecture Performance Evaluation Limitations and Extensions Conclusion 2

Introduction In this paper, we are interested in the scenario where a group of smartphone users, within proximity of each other, are interested in watching the same video at the same time. Some or all of the users may have poor or intermittent cellular connectivity, depending on the coverage of their providers, or may face congestion in the local network. 3

Introduction Fortunately, because the users engage in a group activity, this scenario naturally lends itself to cooperation. Furthermore, when every phone has multiple parallel connections (e.g., 3G, WiFi, and Bluetooth), there are even more available resources that, if properly used, can further improve the user experience. 4

Introduction We propose a novel cooperative scheme, called MicroCast, for video streaming to a group of smartphones within proximity of each other. Each phone utilizes simultaneously two network interfaces: one (cellular) to connect to the video server and download parts of the video; and the other (WiFi) to connect to the rest of the group and exchange downloaded parts. 5

Introduction Our scheme optimizes the usage of the cellular links to ensure that all the available bandwidth is used when channel conditions are good so as to compensate for potential long periods of bad channel conditions. It also optimizes the dissemination in the local area so as to ensure that even in presence of heavy interference from other networks, the phones can still collaborate. 6

Introduction In our scheme, each phone downloads the video much faster than it is played out when the conditions are good, in order to reduce the likelihood of buffering during the playback when the radio conditions significantly deteriorate. 7

Introduction Our system consists of three key components, namely: ◦ MicroDownload: determines which parts of the video each phone should download from the server; ◦ MicroNC-P2: exploits overhearing and network coding over WiFi; ◦ MicroBroadcast: provides high-rate broadcast over WiFi on Android phones. 8

Introduction An attractive feature of our architecture is that it is modular: one can change each component (e.g., the link layer, the algorithms for local distribution or download, the streaming protocol, etc.) independently of the others. 9

MicroCast Architecture 10

MicroCast Architecture Assumptions ◦ There is a small number of users (up to 6-7). ◦ These users know and trust each other. ◦ All users are within proximity of each other and all local links have similar rates on average. ◦ In every phone, we use the cellular connection for the downlink, and WiFi to establish local, device-to-device links. 11

MicroCast Architecture 12

MicroDownload Runs only on one of the phones (in a group) that initiates the download. It instructs the requesters of all phones which segments to download from the server. Its main idea is that the next segment to be downloaded is assigned to a phone which has the smallest backlog (i.e., the set of segments a phone has to download from its cellular connection). 13

MicroDownload Algorithm 14

MicroBroadcast It implements a comprehensive networking stack, which currently operates on wireless technologies including WiFi and RFCOMM Bluetooth. The most important functionality that MicroBroadcast provides is the ability to pseudo-broadcast over WiFi. 15

MicroBroadcast 16

MicroNC-P2 Responsible for distributing segments using the local wireless network. It takes advantage of pseudo-broadcast, i.e., unicast and overhearing, to reduce the number of transmissions. Instead of disseminating regular packets, our scheme disseminates random linear combinations of packets of the same segment to maximize the usefulness of overheard packets. 17

MicroNC-P2 Algorithm 18

MicroNC-P2 Algorithm 19

MicroNC-P2 Algorithm 20

MicroNC-P2 Algorithm 21

MicroNC-P2 22

MicroCast Architecture Reception Rate ◦ Assume for simplicity that each phone can receive rate R c from the cellular network and rate R l from the local network. ◦ If we have N phones, this implies that we need to maintain R l ≥ (N − 1)R c, since each phone is expected to receive through the local network the segments that the other N − 1 phones have downloaded. 23

Performance Evaluation In our evaluation, we perform experiments on an Android testbed consisting of seven smartphones: four Samsung Captivate and three Nexus S. All smartphones have a 1 Ghz Cortex-A8 CPU and 512 MB RAM. Six of them use Android Gingerbread (2.3) and one (Nexus S) uses Android Ice Scream Sandwich (4.0) as their operating systems. 24

Evaluation of MicroDownload We used three Nexus S connected to the same cellular network provider, and placed them within proximity of each other (the distances among them are approximately 2 cm) in an indoor environment. In our experiment, we disabled MicroNC- P2 and we measured the download rates of the smartphones over 100 seconds. 25

Evaluation of MicroDownload Phone 1, 2: 3G Phone 3: EDGE This shows the importance of the adaptive request mechanism of MicroDownload. 26

Evaluation of MicroNC-P2 We compare the performance of MicroNC-P2 to a BitTorrent-based distributor [8] and an R2-based distributor [41]. We consider a clique and a star overlay topologies for local connectivity. 27 [8] B. Cohen. Incentives build robustness in BitTorrent. In Proceedings of the First Workshop on Economics of Peer-to-Peer Systems, Berkeley, CA, USA, [41] M. Wang and B. Li. R2: Random push with random network coding in live Peer-to-Peer streaming. IEEE Journal on Selected Areas in Communications, 25(9):1655–1666, Dec

Evaluation of MicroNC-P2 28

29

Evaluation of MicroNC-P2 The set of experimental results clearly show that by exploiting the broadcast nature of the wireless medium, MicroNC- P2 manages to introduce less amount of traffic into the local network as compared to BitTorrent-Pull and R2-Push. 30

Evaluation of the MicroCast System We compare the average download rates of MicroCast to two other schemes: no cooperation and the combination of MicroDownload and BitTorrent-Pull. We used up to seven phones, the first four of which had 3G rates varying from 480 Kbps to 670 Kbps, while the rest of the phones did not have 3G connections. The local network can support up to 20 Mbps UDP traffic, and we use the star topology. 31

Evaluation of the MicroCast System 32

Evaluation of the MicroCast System 33

Evaluation of the MicroCast System 34 Average download rate as a function of number of phones when the local network bandwidth is 4 Mbps.

Evaluation of Energy Consumption 35

Limitations and Extensions We have already implemented and successfully tested a version of the system that uses Bluetooth in the local area, instead of WiFi. An attractive feature of Bluetooth is that it can be used without rooting the phone. Furthermore, it supports both single-hop and multi-hop transmission via piconets and scatternets respectively. On the downside, Bluetooth does not support broadcast, which was a necessary ingredient for achieving MicroCast’s benefits. 36

Limitations and Extensions One could use WiFi (instead of cellular) for downloading the content from the server. However, in that case, the downlink and the local transmissions are no longer independent as they both use WiFi. 37

Limitations and Extensions Our implementation of MicroDownload currently does not take into account the local link quality between the nodes and does not try to download in parallel blocks on multiple devices when spare capacity is available. It also cannot exploit broadcast capabilities of the WAN link. This is typically not available on cellular networks but could be used if, for instance, the phones are connected to an AP. 38

Limitations and Extensions Finally, the current implementation cannot support more than 7 concurrent devices (when an Android 4.0 device acts as the AP) or 6 devices (when an Android 2.3 device acts as the AP). In order to further increase the number of users, one could use more than one phones as softAPs, but this requires modification of the system. In particular, promiscuous mode does not allow for overhearing of packets associated with a different softAP. 39

Conclusion MicroCast cooperatively uses the resources on all smartphones of the group, such as cellular links and WiFi connections, to improve the streaming experience. Experimental results demonstrate significant performance benefits in terms of per-user video download rate without battery penalty. 40