Abstract

The virtual optical bus (VOB) is presented as a novel architecture for packet-based optical transport networks. The VOB is an evolutionary networking architecture based on the optical burst/packet switching (OBS/OPS) paradigm with a higher performance—in terms of packet loss rate and network throughput. The achieved gain comes at a cost of a marginal increase in the delay that packets experience at the ingress edge of the network, where we can still use inexpensive electrical buffers. In the VOB architecture, flows of traffic between nodes in the network are grouped into clusters and within each of the clusters a special form of coordination on packet transmission is introduced. This coordination ensures collision-free packet transmission within each cluster. Additionally, clustering of flows and selection of paths for clusters are done in a way that the interaction among routes of clusters in the network is minimized. This leads to a reduction of packet collisions in the network and also an increase in the network throughput. Design issues related to the VOB architecture are discussed and two design examples are presented that illustrate the high potential of this approach.

© 2010 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. Y. Chen, C. Qiao, X. Yu, “Optical burst switching: a new area in optical networking research,” IEEE Network, vol. 18, no. 3, pp. 16–23, 2004.
    [CrossRef]
  2. A. Rostami, A. Wolisz, “Impact of edge traffic aggregation on the performance of FDL-assisted optical core switching nodes,” in IEEE Int. Conf. on Communications (ICC), 2007, pp. 2275–2282.
  3. Y. Xiong, M. Vandenhoute, H. C. Cankaya, “Control architecture in optical burst-switched WDM networks,” IEEE J. Sel. Areas Commun., vol. 18, pp. 1838–1851, 2000.
    [CrossRef]
  4. H. R. van As, “Media access techniques: the evolution towards terabit/s LANs and MANs,” Comput. Networks ISDN Syst., vol. 26, nos. 6–8, pp. 603–656, 1994.
    [CrossRef]
  5. H. Akimaru, K. Kawashima, Teletraffic: Theory and Applications. Springer, 1999.
    [CrossRef]
  6. M. Pióro, D. Medhi, Routing, Flow, and Capacity Design in Communication and Computer Networks. Morgan Kaufmann, 2004.
  7. D. Eppstein, “Finding the k shortest paths,” SIAM J. Sci. Comput., vol. 28, no. 2, pp. 652–673, 1999.
    [CrossRef]
  8. A. Rostami, A. Wolisz, A. Feldmann, “Traffic analysis in optical burst switching networks: a trace-based case study,” Eur. Trans Telecommun., vol. 20, no. 7, pp. 633–649, 2009.
    [CrossRef]
  9. OMNeT++ User Manual. Available: http://omnetpp.org/documentation.
  10. H. Buchta, “Analysis of physical constraints in an optical burst switching network,” Ph.D. thesis, Technical University of Berlin, Germany, 2005.
  11. A. Rostami, “Virtual optical bus: a novel packet-based architecture for optical transport networks,” Telecommunication Networks Group (TKN), Technical University of Berlin, Tech. Rep., Feb. 2010.
  12. CPLEX 9.0 User’s Manual. ILOG, SA, 2003.
  13. B. Mukherjee, Optical WDM Networks. Springer, 2006.
  14. A. Gumaste, I. Chlamtac, “Light-trails: an optical solution for IP transport,” J. Opt. Netw., vol. 3, no. 5, pp. 261–281, 2004.
    [CrossRef]
  15. J. Li, C. Qiao, “Schedule burst proactively for optical burst switched networks,” in IEEE Global Communications Conf., 2003, pp. 2787–2791.
  16. G. Hu, C. M. Gauger, S. Junghans, “Performance of MAC layer and fairness protocol for the Dual Bus Optical Ring Network (DBORN),” in Int. Conf. on Optical Networking Design and Modeling, 2005, pp. 467–476.
  17. I. Widjaja, I. Saniee, “Simplified layering and flexible bandwidth with TWIN,” in ACM SIGCOMM Workshop on Future Directions in Network Architecture, 2004, pp. 13–20.

2009 (1)

A. Rostami, A. Wolisz, A. Feldmann, “Traffic analysis in optical burst switching networks: a trace-based case study,” Eur. Trans Telecommun., vol. 20, no. 7, pp. 633–649, 2009.
[CrossRef]

2004 (2)

A. Gumaste, I. Chlamtac, “Light-trails: an optical solution for IP transport,” J. Opt. Netw., vol. 3, no. 5, pp. 261–281, 2004.
[CrossRef]

Y. Chen, C. Qiao, X. Yu, “Optical burst switching: a new area in optical networking research,” IEEE Network, vol. 18, no. 3, pp. 16–23, 2004.
[CrossRef]

2000 (1)

Y. Xiong, M. Vandenhoute, H. C. Cankaya, “Control architecture in optical burst-switched WDM networks,” IEEE J. Sel. Areas Commun., vol. 18, pp. 1838–1851, 2000.
[CrossRef]

1999 (1)

D. Eppstein, “Finding the k shortest paths,” SIAM J. Sci. Comput., vol. 28, no. 2, pp. 652–673, 1999.
[CrossRef]

1994 (1)

H. R. van As, “Media access techniques: the evolution towards terabit/s LANs and MANs,” Comput. Networks ISDN Syst., vol. 26, nos. 6–8, pp. 603–656, 1994.
[CrossRef]

Akimaru, H.

H. Akimaru, K. Kawashima, Teletraffic: Theory and Applications. Springer, 1999.
[CrossRef]

Buchta, H.

H. Buchta, “Analysis of physical constraints in an optical burst switching network,” Ph.D. thesis, Technical University of Berlin, Germany, 2005.

Cankaya, H. C.

Y. Xiong, M. Vandenhoute, H. C. Cankaya, “Control architecture in optical burst-switched WDM networks,” IEEE J. Sel. Areas Commun., vol. 18, pp. 1838–1851, 2000.
[CrossRef]

Chen, Y.

Y. Chen, C. Qiao, X. Yu, “Optical burst switching: a new area in optical networking research,” IEEE Network, vol. 18, no. 3, pp. 16–23, 2004.
[CrossRef]

Chlamtac, I.

Eppstein, D.

D. Eppstein, “Finding the k shortest paths,” SIAM J. Sci. Comput., vol. 28, no. 2, pp. 652–673, 1999.
[CrossRef]

Feldmann, A.

A. Rostami, A. Wolisz, A. Feldmann, “Traffic analysis in optical burst switching networks: a trace-based case study,” Eur. Trans Telecommun., vol. 20, no. 7, pp. 633–649, 2009.
[CrossRef]

Gauger, C. M.

G. Hu, C. M. Gauger, S. Junghans, “Performance of MAC layer and fairness protocol for the Dual Bus Optical Ring Network (DBORN),” in Int. Conf. on Optical Networking Design and Modeling, 2005, pp. 467–476.

Gumaste, A.

Hu, G.

G. Hu, C. M. Gauger, S. Junghans, “Performance of MAC layer and fairness protocol for the Dual Bus Optical Ring Network (DBORN),” in Int. Conf. on Optical Networking Design and Modeling, 2005, pp. 467–476.

Junghans, S.

G. Hu, C. M. Gauger, S. Junghans, “Performance of MAC layer and fairness protocol for the Dual Bus Optical Ring Network (DBORN),” in Int. Conf. on Optical Networking Design and Modeling, 2005, pp. 467–476.

Kawashima, K.

H. Akimaru, K. Kawashima, Teletraffic: Theory and Applications. Springer, 1999.
[CrossRef]

Li, J.

J. Li, C. Qiao, “Schedule burst proactively for optical burst switched networks,” in IEEE Global Communications Conf., 2003, pp. 2787–2791.

Medhi, D.

M. Pióro, D. Medhi, Routing, Flow, and Capacity Design in Communication and Computer Networks. Morgan Kaufmann, 2004.

Mukherjee, B.

B. Mukherjee, Optical WDM Networks. Springer, 2006.

Pióro, M.

M. Pióro, D. Medhi, Routing, Flow, and Capacity Design in Communication and Computer Networks. Morgan Kaufmann, 2004.

Qiao, C.

Y. Chen, C. Qiao, X. Yu, “Optical burst switching: a new area in optical networking research,” IEEE Network, vol. 18, no. 3, pp. 16–23, 2004.
[CrossRef]

J. Li, C. Qiao, “Schedule burst proactively for optical burst switched networks,” in IEEE Global Communications Conf., 2003, pp. 2787–2791.

Rostami, A.

A. Rostami, A. Wolisz, A. Feldmann, “Traffic analysis in optical burst switching networks: a trace-based case study,” Eur. Trans Telecommun., vol. 20, no. 7, pp. 633–649, 2009.
[CrossRef]

A. Rostami, “Virtual optical bus: a novel packet-based architecture for optical transport networks,” Telecommunication Networks Group (TKN), Technical University of Berlin, Tech. Rep., Feb. 2010.

A. Rostami, A. Wolisz, “Impact of edge traffic aggregation on the performance of FDL-assisted optical core switching nodes,” in IEEE Int. Conf. on Communications (ICC), 2007, pp. 2275–2282.

Saniee, I.

I. Widjaja, I. Saniee, “Simplified layering and flexible bandwidth with TWIN,” in ACM SIGCOMM Workshop on Future Directions in Network Architecture, 2004, pp. 13–20.

van As, H. R.

H. R. van As, “Media access techniques: the evolution towards terabit/s LANs and MANs,” Comput. Networks ISDN Syst., vol. 26, nos. 6–8, pp. 603–656, 1994.
[CrossRef]

Vandenhoute, M.

Y. Xiong, M. Vandenhoute, H. C. Cankaya, “Control architecture in optical burst-switched WDM networks,” IEEE J. Sel. Areas Commun., vol. 18, pp. 1838–1851, 2000.
[CrossRef]

Widjaja, I.

I. Widjaja, I. Saniee, “Simplified layering and flexible bandwidth with TWIN,” in ACM SIGCOMM Workshop on Future Directions in Network Architecture, 2004, pp. 13–20.

Wolisz, A.

A. Rostami, A. Wolisz, A. Feldmann, “Traffic analysis in optical burst switching networks: a trace-based case study,” Eur. Trans Telecommun., vol. 20, no. 7, pp. 633–649, 2009.
[CrossRef]

A. Rostami, A. Wolisz, “Impact of edge traffic aggregation on the performance of FDL-assisted optical core switching nodes,” in IEEE Int. Conf. on Communications (ICC), 2007, pp. 2275–2282.

Xiong, Y.

Y. Xiong, M. Vandenhoute, H. C. Cankaya, “Control architecture in optical burst-switched WDM networks,” IEEE J. Sel. Areas Commun., vol. 18, pp. 1838–1851, 2000.
[CrossRef]

Yu, X.

Y. Chen, C. Qiao, X. Yu, “Optical burst switching: a new area in optical networking research,” IEEE Network, vol. 18, no. 3, pp. 16–23, 2004.
[CrossRef]

Comput. Networks ISDN Syst. (1)

H. R. van As, “Media access techniques: the evolution towards terabit/s LANs and MANs,” Comput. Networks ISDN Syst., vol. 26, nos. 6–8, pp. 603–656, 1994.
[CrossRef]

Eur. Trans Telecommun. (1)

A. Rostami, A. Wolisz, A. Feldmann, “Traffic analysis in optical burst switching networks: a trace-based case study,” Eur. Trans Telecommun., vol. 20, no. 7, pp. 633–649, 2009.
[CrossRef]

IEEE J. Sel. Areas Commun. (1)

Y. Xiong, M. Vandenhoute, H. C. Cankaya, “Control architecture in optical burst-switched WDM networks,” IEEE J. Sel. Areas Commun., vol. 18, pp. 1838–1851, 2000.
[CrossRef]

IEEE Network (1)

Y. Chen, C. Qiao, X. Yu, “Optical burst switching: a new area in optical networking research,” IEEE Network, vol. 18, no. 3, pp. 16–23, 2004.
[CrossRef]

J. Opt. Netw. (1)

SIAM J. Sci. Comput. (1)

D. Eppstein, “Finding the k shortest paths,” SIAM J. Sci. Comput., vol. 28, no. 2, pp. 652–673, 1999.
[CrossRef]

Other (11)

J. Li, C. Qiao, “Schedule burst proactively for optical burst switched networks,” in IEEE Global Communications Conf., 2003, pp. 2787–2791.

G. Hu, C. M. Gauger, S. Junghans, “Performance of MAC layer and fairness protocol for the Dual Bus Optical Ring Network (DBORN),” in Int. Conf. on Optical Networking Design and Modeling, 2005, pp. 467–476.

I. Widjaja, I. Saniee, “Simplified layering and flexible bandwidth with TWIN,” in ACM SIGCOMM Workshop on Future Directions in Network Architecture, 2004, pp. 13–20.

A. Rostami, A. Wolisz, “Impact of edge traffic aggregation on the performance of FDL-assisted optical core switching nodes,” in IEEE Int. Conf. on Communications (ICC), 2007, pp. 2275–2282.

H. Akimaru, K. Kawashima, Teletraffic: Theory and Applications. Springer, 1999.
[CrossRef]

M. Pióro, D. Medhi, Routing, Flow, and Capacity Design in Communication and Computer Networks. Morgan Kaufmann, 2004.

OMNeT++ User Manual. Available: http://omnetpp.org/documentation.

H. Buchta, “Analysis of physical constraints in an optical burst switching network,” Ph.D. thesis, Technical University of Berlin, Germany, 2005.

A. Rostami, “Virtual optical bus: a novel packet-based architecture for optical transport networks,” Telecommunication Networks Group (TKN), Technical University of Berlin, Tech. Rep., Feb. 2010.

CPLEX 9.0 User’s Manual. ILOG, SA, 2003.

B. Mukherjee, Optical WDM Networks. Springer, 2006.

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (12)

Fig. 1
Fig. 1

A generic architecture of the switch assumed in the VOB.

Fig. 2
Fig. 2

Abstract model of a single ingress node equipped with a FDL insertion buffer on the transit path. There are two possibilities for incorporating the insertion buffers into the architecture of the switch depicted in Fig. 1: at the input or output of the switch (see points marked as A, B, and C). In the former case, the insertion buffers are placed between the delay lines and the switch fabric, which necessitates additional 1 × 2 switching elements before the insertion buffers to allow for bypassing the insertion buffers if required. In the latter case, the insertion buffers could be incorporated into the FDL buffering unit. In either case, additional ports on the main switch would be needed.

Fig. 3
Fig. 3

Example of applying the VOB: (a) a simple network with four O-D flows, (b) the same network after applying the VOB.

Fig. 4
Fig. 4

Single-bottleneck scenario used for MAC protocol evaluation.

Fig. 5
Fig. 5

Loss rate on the bottleneck link against the offered load at B = 3 , (a) OBS, W = 3 . The loss rate for the VOB network is zero, (b) W = 2 . The error bars represent 90% confidence intervals.

Fig. 6
Fig. 6

Throughput of the network against the offered load to the bottleneck link at B = 3 , (a) W = 3 , (b) W = 2 . 90% confidence intervals are not shown since they are too small.

Fig. 7
Fig. 7

Access delay experienced by node S 1 , 1 in accessing VOB 1 at B = 3 and W = 3 . 90% confidence intervals are not shown since they are too small.

Fig. 8
Fig. 8

NSFNET topology.

Fig. 9
Fig. 9

Number of VOBs per link resulting from solving the ILP for the ring network for different traffic matrices (random and uniform) and for different values of A max . The results are compared with the classical OBS network for which the number of independent flows per link are shown.

Fig. 10
Fig. 10

Load per link resultng from solving the ILP for the ring network for different traffic matrices (random and uniform) and for different values of A max . The results are compared with the classical OBS network. Load values are normalized to the capacity of a single wavelength channel.

Fig. 11
Fig. 11

Number of VOBs per link resulting from solving the ILP for the NSFNET topology at A max = 0.7 and for different values of k. The results are compared with the classical OBS network for which the number of independent flows per link are shown.

Fig. 12
Fig. 12

Load per link resulting from solving the ILP for the NSFNET topology at A max = 0.7 and at different values of k. The results are compared with the classical OBS network. Load values are normalized to the capacity of a single wavelength channel.

Tables (5)

Tables Icon

Table 1 Throughput Gain of the VOB Network Over the OBS Network at 70% Link Load in Percent

Tables Icon

Table 2 Random Traffic Matrix for the Ring Network Used in the Design Example

Tables Icon

Table 3 Traffic Matrix of the NSFNET

Tables Icon

Table 4 Performance Evaluation Results for the Ring Network a

Tables Icon

Table 5 Performance Evaluation Results for the NSFNET a

Equations (7)

Equations on this page are rendered with MathJax. Learn more.

θ ( p , l ) { 1 if link l P is used in path p P 0 otherwise } .
γ ( p , l , f ) { 1 if O - D flow f F could be supported by path p P on link l L 0 otherwise } .
x p { 1 if p P is selected as a VOB 0 otherwise } .
y p f { 1 if flow f F is supported by path p P 0 otherwise } .
Min max l L p P θ ( p , l ) x p .
p P y p f = 1 f F .
f F y p f λ f γ ( p , l , f ) x p A max l L , p P .