The design of an IPTV multicast system for the Internet backbone network is presented and explored through extensive simulations. In the proposed system, a resource reservation algorithm such as RSVP, IntServ, or DiffServ is used to reserve resources (i.e., bandwidth and buffer space) in each router in an IP multicast tree. Each router uses an Input-Queued, Output-Queued, or Crosspoint-Queued switch architecture with unity speedup. A recently proposed Recursive Fair Stochastic Matrix Decomposition algorithm used to compute near-perfect transmission schedules for each IP router. The IPTV traffic is shaped at the sources using Application-Specific Token Bucker Traffic Shapers, to limit the burstiness of incoming network traffic. The IPTV traffic is shaped at the destinations using Application-Specific Playback Queues, to remove residual network jitter and reconstruct the original bursty IPTV video streams at each destination. All IPTV traffic flows are regenerated at the destinations with essentially zero delay jitter and essentially-perfect QoS. The destination nodes deliver the IPTV streams to the ultimate end users using the same IPTV multicast system over a regional Metropolitan Area Network. It is shown that all IPTV traffic is delivered with essentially-perfect end-to-end QoS, with deterministic bounds on the maximum delay and jitter on each video frame. Detailed simulations of an IPTV distribution system, multicasting several hundred high-definition IPTV video streams over several essentially saturated IP backbone networks are presented. 1. Introduction Multimedia traffic such as IPTV and video-on-demand represent a rapidly growing segment of the total Internet traffic. According to Cisco [1, 2], global Internet traffic is nearly doubling every 2 years, and global capacity will have to increase 75 times over the decade 2002–2012 to keep up with the demand. Furthermore, video-based traffic such as IPTV [3] will represent 90% of global network loads in 2012. The US Federal Communication Commission (FCC) has required that all TV broadcasts occur in digital format in 2009, and the growing fraction of multimedia traffic threatens to overwhelm the current Internet infrastructure. According to [4], “The United States will not be the first country to complete the transition to digital television… Luxembourg, the Netherlands, Finland, Andorra, Sweden, and Switzerland have all completed their transitions, utilizing the Digital Video Broadcasting—Terrestrial (DVB-T) standard. Transitions are now under way in more than 35 other countries." According to Cisco
References
[1]
Cisco Systems White Paper, “Approaching the Zettabyte Era,” 2008, http://www.cisco.com.
[2]
R. Lawler, “Cisco Sees a Zettaflood of IP Traffic-Driven by Video,” Contentinople—Networking the Digital Media Industry, 2008, http://www.contentinople.com.
[3]
Y. Xiao, X. Du, J. Zhang, F. Hu, and S. Guizani, “Internet protocol television (IPTV): the killer application for the next-generation internet,” IEEE Communications Magazine, vol. 45, no. 11, pp. 126–134, 2007.
[4]
J. M. Boyce, “The US digital television broadcasting transition,” IEEE Signal Processing Magazine, vol. 26, no. 3, pp. 110–112, 2009.
[5]
Cisco Systems White Paper, “Optimizing Video Transport in your IP Triple Play Network,” 2006, http://www.cisco.com.
[6]
L. Hardesty, “Internet gridlock: video is clogging the internet. How we choose to unclog it will have far-reaching implications,” MIT Technology Review, 2008.
[7]
M. Baard, “NSF Preps New Improved Internet,” Wired, August 2005.
[8]
BBN Technologies—GENI Project Office, “Global Environment for Network Innovations—GENI System Overview,” December 2007.
[9]
T. H. Szymanski and D. Gilbert, “Internet multicasting of IPTV with essentially-zero delay jitter,” IEEE Transactions on Broadcasting, vol. 55, no. 1, pp. 20–30, 2009.
[10]
T. H. Szymanski, “A low-jitter guaranteed-rate scheduling algorithm for packet-switched IP routers,” IEEE Transactions on Communications, vol. 57, no. 11, 2009.
[11]
T. H. Szymanski, “Bounds on end-to-end delay and jitter in input-buffered and internally-buffered IP/MPLS networks,” in Proceedings of the IEEE Sarnoff Symposium (SARNOFF '09), Princeton, NJ, USA, 2009.
[12]
S. Orlowski, R. Wessaly, M. Pioro, and A. Tomaszewski, “SNDlib1.0-survivable network design library,” ZIB report ZR-07-15, Networks, October 2009, http://sndlib.zib.de/home.action.
[13]
L. Tassiulas and A. Ephremides, “Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks,” IEEE Transactions on Automatic Control, vol. 27, pp. 1936–1948, 1992.
[14]
V. Anantharam, N. McKeown, A. Mekkittikul, and J. Walrand, “Achieving 100% throughput in an input-queued switch,” IEEE Transactions on Communications, vol. 47, no. 8, pp. 1260–1267, 1999.
[15]
N. McKeown, “The iSLIP scheduling algorithm for input-queued switches,” IEEE/ACM Transactions on Networking, vol. 7, no. 2, pp. 188–201, 1999.
[16]
C. E. Koksal, R. G. Gallager, and C. E. Rohrs, “Rate quantization and service quality over single crossbar switches,” in Proceedings of the IEEE Conference on Computer Communications (INFOCOM '04), pp. 1962–1973, 2004.
[17]
C.-S. Chang, W. J. Chen, and H.-Y. Huang, “On service guarantees for input buffered crossbar switches: a capacity decomposition approach by birkhoff and von neuman,” in Proceedings of the IEEE International Workshop on Quality of Service (iWQoS '99), pp. 79–86, 1999.
[18]
C.-S. Chang, W.-J. Chen, and H.-Y. Huang, “Birkhoff-von neumann input-buffered crossbar switches for guaranteed-rate services,” IEEE Transactions on Communications, vol. 49, no. 7, pp. 1145–1147, 2001.
[19]
I. Keslassy, M. Kodialam, T. V. Lakshman, and D. Stiliadis, “On guaranteed smooth scheduling for input-queued switches,” IEEE/ACM Transactions on Networking, vol. 13, no. 6, pp. 1364–1375, 2005.
[20]
M. S. Kodialam, T. V. Lakshman, and D. Stilladis, “Scheduling of Guaranteed-bandwidth low-jitter traffic in input-buffered switches,” US patent application no. #20030227901, 2003.
[21]
S. R. Mohanty and L. N. Bhuyan, “Guaranteed smooth switch scheduling with low complexity,” in Proceedings of the IEEE Global Telecommunications Conference (GLOBECOM '05), pp. 626–630, 2005.
[22]
N. McKeown and B. Prabhakar, “Scheduling multicast cells in an input-queued switch,” in Proceedings of the 15th Annual Joint Conference of the IEEE Computer and Communications Societies (INFOCOM '96), vol. 1, pp. 271–278, March 1996.
[23]
M. Marsan, A. Bianco, P. Giaccone, E. Leonardi, and F. Neri, “Multicast traffic in input-queued switches: optimal scheduling and maximum throughput,” IEEE/ACM Transactions on Networking, vol. 11, no. 3, pp. 465–477, 2003.
[24]
J. F. Hayes, R. Breault, and M. K. Mehmet-Ali, “Performance analysis of a multicast switch,” IEEE Transactions on Communications, vol. 39, no. 4, pp. 581–587, 1991.
[25]
J. Y. Hui and T. Renner, “Queueing analysis for multicast packet switching,” IEEE Transactions on Communications, vol. 42, no. 2, pp. 723–731, 1994.
[26]
B. Prabhakar, N. McKeown, and R. Ahuja, “Multicast scheduling for input-queued switches,” IEEE Journal on Selected Areas in Communications, vol. 15, no. 5, pp. 855–866, 1997.
[27]
M. Song, W. Zhu, A. Francini, and M. Alam, “Performance analysis of large multicast switches with multicast virtual output queues,” Computer Communications, vol. 28, no. 2, pp. 189–198, 2005.
[28]
S. R. Gulliver and G. Ghinea, “The perceptual and attentive impact of delay and jitter in multimedia delivery,” IEEE Transactions on Broadcasting, vol. 53, no. 2, pp. 449–458, 2007.
[29]
S. Chand and H. Om, “Modeling of buffer storage in video transmission,” IEEE Transactions on Broadcasting, vol. 53, no. 4, pp. 774–779, 2007.
[30]
Y. Bai and M. R. Ito, “Application-aware buffer management: new metrics and techniques,” IEEE Transactions on Broadcasting, vol. 51, no. 1, pp. 114–121, 2005.
[31]
Y. Ganjali and N. McKeown, “Update on buffer sizing in internet routers,” ACM SIGCOMM Computer Communication Review, vol. 36, no. 5, pp. 67–70, 2006.
[32]
G. Vu-Brugier, R. S. Stanojevic, D. J. Leith, and R. N. Shorten, “A Critique of recently proposed buffer sizing strategies,” ACM/SIGCOMM Computer Communication Review, vol. 37, no. 1, pp. 43–47, 2007.
[33]
M. Enachescu, Y. Ganjali, A. Goel, N. McKeown, and T. Roughgarden, “Routers with very small buffers,” in Proceedings of the 25th IEEE International Conference on Computer Communications (INFOCOM '06), Barcelona, Spain, April 2006.
[34]
A. Dhamdhere and C. Dovrolis, “Open issues in router buffer sizing,” vol. 36, no. 1, pp. 87–92.
[35]
T. H. Szymanski and D. Gilbert, “Provisioning mission-critical telerobotic control systems in internet backbone networks with essentially-perfect QoS,” IEEE Journal on Selected Areas in Communications, vol. 28, no. 5, pp. 630–643, 2010.
