Abstract
Hopfield networks have been suggested as a tool for the optimization of traffic grooming. However, this method of optimization based on neural networks normally requires a considerable delay to find an optimal solution. This limited their practicability in optical data transport. This paper proposes a solution to reduce this delay. That is a learning model in which arriving service patterns are clustered into groups corresponding to separate optimal grooming solutions. When a new service pattern arrives, it is checked to see if it belongs to an existing optimized group: if one is found, the corresponding optimal grooming solution is returned immediately. If not, an optimization process is required to determine its optimal grooming solution. This paper discusses the practicability of the proposed learning model and the clustering strategies.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Zhu, K., et al.: A Review of Traffic Grooming in WDM Optical Networks: Architectures and Challenges, Computer Science Department, University of California, Davis, CA 95616, USA
Hu, J.Q.: Traffic grooming in WDM ring networks: A linear programming solution. Journal of Opt. Networks 1 (2002)
Zhao, C.M., et al.: Traffic Grooming for WDM Rings with Dynamic Traffic (2003) (manuscript)
Vo, V.M.N., et al.: Traffic Switching Optimization on Optical Routing by Using Hopfield Network. In: RIVF 2004, Hanoi, Vietnam, February 02-05 (2004)
Vo, V.M.N., et al.: Optimization of Services-into-Burst Multiplexing based on Hopfield Network. In: ICHSN 2005, Montreal (August 2005)
Lagoudakis, M.G.: Neural Networks and Optimization Problems - A Case Study: The Minimum Cost Spare Allocation Problem, University of Southwestern Louisian
Lillo, W., et al.: On Solving Constrained Optimization Problems with Neural Networks: A Penalty Method Approach. IEEE Trans. on Neural Networks 4(6) (1993)
Zhang, X., et al.: An effective and comprehensive approach to traffic grooming and wavelength assignment in SONET/WDM rings. In: SPIE Proc. Conf. All-Opt. Networking, Boston, MA, September 1998, vol. 3531 (1998)
Wang, J., et al.: Improved approaches for cost-effective traffic grooming in WDM ring networks: ILP formulations and single-hop and multihop connections. IEEE Journal of Lightwave Technology 19(11) (2001)
Simmons, J., et al.: Quantifying the benefit of wavelength add-drop in WDM rings with distance-independent and dependent traffic. IEEE Journal of Lightwave Technology 17 (January 1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vo, V.M.N. (2010). Learning Model for Reducing the Delay in Traffic Grooming Optimization. In: Nguyen, N.T., Le, M.T., Świątek, J. (eds) Intelligent Information and Database Systems. ACIIDS 2010. Lecture Notes in Computer Science(), vol 5990. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-12145-6_32
Download citation
DOI: https://doi.org/10.1007/978-3-642-12145-6_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-12144-9
Online ISBN: 978-3-642-12145-6
eBook Packages: Computer ScienceComputer Science (R0)