Content deleted Content added
Synchrodyne (talk | contribs) No edit summary |
Synchrodyne (talk | contribs) No edit summary |
||
Line 17:
| year = 2004 }}
</ref>
leverages on [[Time-driven switching]] ([[Time-Driven Switching|TDS]]) to realize sub-lambda switching in highly scalable dynamic [[optical switching|optical networking]
<ref>
[http://www.mario-baldi.net M. Baldi], [http://dit.unitn.it/ofek/ Y. Ofek], "[http://staff.polito.it/mario.baldi/publications/ONM2003.pdf Realizing Dynamic Optical Networking]," [http://optical-networks.com/ Optical Networks Magazine], [http://www.springerlink.com/content/t87443j2276n0w26/?p=ee76836c03234578b4a3e08418d41461&pi=0 Special Issue "Dynamic Optical Networking: around the Corner or Light Years Away?"], Vol. 4, No. 5, Sep./Oct. 2003, pp. 100-111.
</ref>
, which requires minimum (possibly optical) buffers. In this context, TDS has the same general objectives as [[optical burst switching]] and [[optical packet switching]]: realizing all-optical networks with high wavelength utilization. TDS operation is based on time frames (TFs) that can be viewed as virtual containers for multiple [[internet protocol|IP]] packets that are switched at every TDS switch based on and coordinated by the [[UTC]] ([[coordinated universal time]]) signal implementing [[pipeline forwarding]]. In the context of optical networks,
In TDS all packets in the same TF are switched in the same way. Consequently, header processing is not required, which results in low complexity (hence high scalability) and enables optical implementation. The TF is the basic SVP capacity allocation unit; hence, the allocation granularity depends on the number of TFs per time cycle. For example, with a 10 Gb/s optical channel and 1000 TFs in each time cycle, the minimum FλP capacity (obtained by allocating one TF in every time cycle) is 10 Mb/s.▼
Scheduling through a switching fabric is based on a pre-defined schedule, which enables the implementation of a simple controller. Moreover, low-complexity switching fabric architectures, such as Banyan, can be deployed notwithstanding their blocking features, thus further enhancing scalability. In fact, blocking can be avoided during schedule computation by avoiding conflicting input/output connections during the same TF. Previous results [4] show that (especially if multiple wavelength division multiplexing channels are deployed on optical links between fractional λ switches) high link utilization can be achieved with negligible blocking using a Banyan network without speedup.▼
In FλS, likewise in TDS, all packets in the same time frame are switched in the same way. Consequently, header processing is not required, which results in low complexity (hence high scalability) and enables [http://dit.unitn.it/ip-flow/prototypeswitch.html optical implementation]
<ref>
D. Agrawal, M. Baldi, M. Corrà, G. Fontana, T. H. Truong, G. Marchetto, V. T. Nguyen, [http://dit.unitn.it/ofek/ Y. Ofek], D. Severina, O. Zadedyurina, "[http://staff.polito.it/mario.baldi/publications/2007ISCC_PF_testbed.pdf A Scalable Approach for Supporting Streaming Media: Design, Implementation and Experiments]," IEEE Symposium on Computers and Communications (ISCC 07), Aveiro (Portugal), July 2007.
</ref>
<ref>
D. Agrawal, [http://www.mario-baldi.net M. Baldi], M. Corrà, G. Fontana, T. H. Truong, G. Marchetto, V. T. Nguyen, [http://dit.unitn.it/ofek/ Y. Ofek], D. Severina, O. Zadedyurina, "[http://staff.polito.it/mario.baldi/publications/2007ICC_TDS_Prototype.pdf Scalable Switching Testbed not 'Stopping' the Serial Bit Stream]," IEEE International Conference on Communications (ICC 2007), Optical Networks and Systems Symposium, Glasgow (Scottland, UK), June 2007. Recipient of the Best Paper Award.
▲
▲Scheduling through a switching fabric is based on a pre-defined schedule, which enables the implementation of a simple controller. Moreover, low-complexity switching fabric architectures, such as Banyan, can be deployed notwithstanding their blocking features, thus further enhancing scalability. In fact, blocking can be avoided during schedule computation by avoiding conflicting input/output connections during the same TF.
<ref>
Donato Grieco, Achille Pattavina and Yoram Ofek, "Fractional Lambda Switching for Flexible Bandwidth Provisioning in WDM Networks: Principles and Performance", Photonic Network Communications, Issue: Volume 9, Number 3, Date: May 2005, Pages: 281 - 296
</ref>
<ref>
{{Citation
| last1 = Baldi | first1 = M.
| authorlink1 = http://www.mario-baldi.net
| last2 = Ofek | first2 = Y.
| authorlink2 = http://dit.unitn.it/ofek
| title = Fractional Lambda Switching - Principles of Operation and Performance Issues
| journal = SIMULATION: Transactions of The Society for Modeling and Simulation International
| volume = 80
| issue = 10
| url = http://staff.polito.it/mario.baldi/publications/TSMS2004_FLS.pdf
| format = [[Portable Document Format|PDF]]
| year = 2004 }}
</ref>
<ref>
V.T. Nguyen, R. Lo Cigno, Y. Ofek, “Tunable laser-based design and analysis for fractional lambda switches,” IEEE Transactions on communication, vol.56, no.6, pp. 957-967, June 2008.
</ref>
<ref>
V.T. Nguyen, R. Lo Cigno, Y. Ofek, M. Telek, “Time Blocking Analysis in Time-Driven Switching Networks,” in the proceedings of INFOCOM 2008, pp. 1804-1812, 2008.
</ref>
== References ==
| |||