Indra Widjaja
ABSTRACT
This paper describes a novel network architecture with simplified layering, called Time-domain Wavelength Interleaved Networking (TWIN), that scales end-to-end bandwidth granularity exibly up to the wavelength capacity. In TWIN, all packet and complex processing functions are pushed to the network edge such that the network core only has to deal with an optical forwarding layer. Furthermore, by avoiding fast optical switching and optical buffering in the core through scheduling fast-tunable lasers and buffering packets at the edge, TWIN effectively makes the network act like a switch. We examine distributed network scheduling for this architecture and show its performance via analysis and simulation. We also explore other research issues that are unique in TWIN.
- A. Odlyzko, "Pricing and architecture of the Internet: historical perspectives from telecommunications and transportation," available at http://www.dtc.umn.edu/~odlyzko.Google Scholar
- L. Martini et al., "Encapsulation methods for transport of Ethernet frames over IP/MPLS networks," IETF work in progress, Apr. 2003.Google Scholar
- L. Martini et al., "Encapsulation methods for transport of ATM over IP and MPLS networks," IETF work in progress, Apr. 2004.Google Scholar
- C. Kawa et al., "Frame relay over pseudo-wires," IETF work in progress, Feb. 2004.Google Scholar
- ATM Forum, "Circuit emulation service - interoperability specification," AF-SAA-0032.000, Sep. 1995.Google Scholar
- A. Malis et al., "SONET/SDH circuit emulation over packet (CEP)," IETF work in progress, Apr. 2004.Google Scholar
- N. Spring, R. Mahajan, D. Wetherhall and T. Anderson, "Measuring ISP topologies with rocketfuel," in Proc. SIGCOMM 2002, Pittsburgh, Aug. 2002. Google ScholarDigital Library
- C. Fraleigh et al., "Packet-level traffic measurements from the Sprint IP backbone," IEEE Network Magazine, pp. 6--16, Nov. 2003. Google ScholarDigital Library
- S. Sudipta, V. Kumar and D. Saha, "Switched optical backbone for cost-effective scalable core IP networks," IEEE Comm. Magazine, pp. 60--70, Jun. 2003. Google ScholarDigital Library
- P. Molinero-Fernandez, N. McKeown and H. Zhang, "Is IP going to take the world (of communications)?," HotNets-I, Princeton, Oct. 2002.Google Scholar
- I. Widjaja, I. Saniee, R. Giles and D. Mitra, "Light-core and intelligent edge for a exible, thin-layered, and cost-effective optical transport network," IEEE Comm. Magazine, pp. S30--S36, May 2003. Google ScholarDigital Library
- C. Chang, W. Chen and H. Huang, "Birkho-von Neumann input buffered crossbar switches," in Proc. IEEE INFOCOM 2000, Aprl. 2000.Google Scholar
- S. Yao, S. Dixit and B. Mukherjee, "Advances in photonic packet switching: an overview," IEEE Comm. Magazine, pp. 84--94, Feb. 2000. Google ScholarDigital Library
- T. S. El-Bawab and J. Shin, "Optical packet switching in core networks: between vision and reality," IEEE Comm. Magazine, pp. 60--65, Sep. 2002. Google ScholarDigital Library
- J. Turner, "Terabit burst switching," J. High Speed Networks, vol. 8, no. 1, pp. 3--16, Jan. 1999. Google ScholarDigital Library
- C. Qiao and M. Yoo, "Optical burst switching (OBS) - a new paradigm for an optical Internet," J. High Speed Networks, vol. 8, no. 1, pp. 69--84, Jan. 1999. Google ScholarDigital Library
- D. M. Marom et al., "Wavelength-selective 1x4 switch for 128 WDM channels at 50 GHz spacing," in Proc. OFC 2002, postdeadline paper FB7, Los Angeles, 2002.Google Scholar
- D. M. Marom, "Wavelength selective 1 x K switches for transparent optical networks," in Proc. SPIE 2002, Vol. 4907, Oct. 2002.Google Scholar
- M. Kauer et al., "16-channel digitally tunable packet switching transmitter with sub-nanosecond switching time," in Proc. ECOC 2002, paper 3.3.3, 2002.Google Scholar
- A. Mekkittikul and N. McKeown, "A practical scheduling algorithm to achieve 100% throughput in input-queued switches," in Proc. IEEE INFOCOM 1998, Mar. 1998.Google ScholarCross Ref
- N. McKeown, "The iSLIP scheduling algorithm for input-queue switches," IEEE Trans. on Networking, vol. 7, pp. 188--201, Apr. 1999. Google ScholarDigital Library
- J. G. Dai and B. Prabhakar, "The throughput of data switches with and without speedup," in Proc. IEEE INFOCOM 2000, Apr. 2000.Google ScholarCross Ref
- http://www.symmetricom.comGoogle Scholar
- K. Ross, N. Bambos, K. Kumaran, I. Saniee, I. Widjaja, "Scheduling bursts in time-domain wavelength interleaved networks," IEEE J. Selected Areas in Communications, vol. 21, no. 9, pp. 1441--1451, Nov. 2003. Google ScholarDigital Library
- CableLabs, "Data-over-cable service interface specifications - radio frequency interface specification," SP-RFIv2.0-I01-011231, Dec. 2001.Google Scholar
- IEEE, "Draft amendment to carrier sense multiple access with collision detection (CSMA/CD) access method and physical layer specifications," IEEE Draft P802.3ah/D3.1, Feb. 2004.Google Scholar
- C. Fraleigh, F. Tobagi and C. Diot, "Provisioning IP backbone networks to support latency sensitive traffic," in Proc. IEEE INFOCOM 2003, Apr. 2003.Google ScholarCross Ref
- T. E. Anderson, S. S. Owicki, J. B. Saxe and C. P. Thacker, "High-speed switch scheduling for local-area networks," ACM Transactions on Computer Systems, vol. 11, no. 4, pp. 319--352, Nov. 1993. Google ScholarDigital Library
- M. W. Goudreau, S. G. Kolliopoulos and S. B. Rao, "Scheduling algorithms for input-queued switches: randomized techniques and experimental evaluation," in Proc. IEEE INFOCOM 2000, Apr. 2000.Google ScholarCross Ref
- D. Katabi, M. Handley and C. Rohrs, "Congestion control for high bandwidth-delay product networks," in Proc. SIGCOMM 2002, Pittsburgh, 2002. Google ScholarDigital Library
- B. Zhu et al., "6.4-Tb/s (160x42.7 Gb/s) transmission with 0.8 bits/s/Hz spectral efficiency over 32x100 km of fiber using CSRZ-DPSK format," in Proc. OFC 2003, postdeadline paper PD19, Georgia, 2003.Google Scholar
- P.P. Mitra and J.B. Stark, "Nonlinear limits to the information capacity of optical fiber communications," Nature, vol. 411, pp. 1027--1030, Jun. 2001.Google ScholarCross Ref
- A. Odlyzko, "Internet traffic growth: sources and implications," Proceedings of SPIE 2003, vol. 5247, 2003.Google Scholar
- M. Médard, S. G. Finn, R. A. Barry and R. G. Gallager, "Redundant trees for preplanned recovery in arbitrary vertex-redundant or edge-redundant graphs," IEEE/ACM Trans. on Networking, vol.7, no. 5, Oct. 1999. Google ScholarDigital Library
- N.G. Duffield, A. Greenberg, P. Mishra, K.K. Ramakrishnan and J.E. van der Merwe, "A flexible model for resource management in virtual private networks," in Proc. SIGCOMM 1999, Boston, Oct. 1999. Google ScholarDigital Library
Index Terms
- Simplified layering and flexible bandwidth with TWIN
Recommendations
Cost-effectiveness of bandwidth granularities in optical networks
With exponential growth of users traffic demands, the efficient and cost-effective usage of bandwidth and spectrum plays an important role to improve service provisioning. This study first reviews different bandwidth granularities in optical networks. ...
Generalized Coincident Pulse Technique and New Addressing Schemes for Time-Division Multiplexing Optical Buses
Time-division multiplexing (TDM) optical buses have applications in computer networks, high-performance routers and switches, and interprocessor communication subsystems of parallel computers. Three waveguides are used to implement the previously ...
A framework for fiber delay-line buffers in packet-based asynchronous multifiber optical networks (PAMFONET)
A major challenge in packet-based optical networks is packet contention, which occurs when two or more packets are heading to the same output at the same time. To resolve contention in the optical domain, a fundamental approach is fiber delay-line (FDL) ...
Reviews
Wei Yen
Networking has become increasingly cumbersome, as new technologies integrate with old. Excessive interworking, necessitated by an inadequate migration strategy, can negate the benefits of new technologies. To grapple with this issue, many researchers have sought to increase the capacity of the core nodes in the backbone. This paper, on the other hand, presents an interesting alternative; it proposes a new network architecture, called time domain wavelength interleaved networking (TWIN). The main idea is to adopt a passive core network, and push interworking to the edge nodes. More specifically, the network is modeled as a nonblocking crossbar. The edge nodes are considered input/output, and the core nodes switch fabric. Each destination is addressed with a unique wavelength. Fast tunable lasers, burst buffering, and scheduling are key components, enabling many-to-one communications. This paper is well written. The significance of the contributions could easily be overshadowed by the plain, yet concise, title and writing style. The paper describes the architecture and scheduling scheme in detail. However, the paper discusses several critical issues-such as management, scalability, and reliability-only briefly, presumably because of the page limitation. As all pioneer works do, the paper raises many questions. For example, it is hard to believe the switched virtual circuit becomes a nonissue in TWIN. Also, the per node wavelength assignment can be stringent in some cases and wasteful in others. Overall, I believe new studies will be inspired by this work, and recommend it to anybody interested in network architecture. Online Computing Reviews Service
Access critical reviews of Computing literature here
Become a reviewer for Computing Reviews.
Comments