research-article

Public Access

Neural Network Based Wavelength Assignment in Optical Switching

Authors:

Craig L. Gutterman,

Shengxiang Zhu,

Daniel C. Kilper,

Gil ZussmanAuthors Info & Claims

Big-DAMA '17: Proceedings of the Workshop on Big Data Analytics and Machine Learning for Data Communication Networks

Pages 37 - 42

https://doi.org/10.1145/3098593.3098600

Published: 07 August 2017 Publication History

Abstract

Greater network flexibility through software defined networking and the growth of high bandwidth services are motivating faster service provisioning and capacity management in the optical layer. These functionalities require increased capacity along with rapid reconfiguration of network resources. Recent advances in optical hardware can enable a dramatic reduction in wavelength provisioning times in optical circuit switched networks. To support such operations, it is imperative to reconfigure the network without causing a drop in service quality to existing users. Therefore, we present a system that uses neural networks to predict the dynamic response of an optically circuit-switched 90-channel multi-hop Reconfigurable Optical Add-Drop Multiplexer (ROADM) network. The neural network is able to recommend wavelength assignments that contain the power excursion to less than 0.5 dB with a precision of over 99%.

Supplementary Material

WEBM File (neuralnetworkbasedwavelengthassignmentinopticalswitching.webm)

Download
68.54 MB

References

[1]

2013. Infinera and DANTE Set Guinness World Record on GÉANT Network Record set for fastest provisioning of long haul optical transmission capacity. Technical Report. Infinera.

[2]

2016. The Zettabyte Era - Trends and Analysis - Cisco. Technical Report. Cisco.

[3]

2017. openroadm. (Mar 2017). Retrieved March 10, 2017 from http://www.openroadm.org/

[4]

Martín Abadi, Ashish Agarwal, Paul Barham, Eugene Brevdo, Zhifeng Chen, Craig Citro, Greg S Corrado, Andy Davis, Jeffrey Dean, Matthieu Devin, et al. 2016. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. arXiv:1603.04467 (2016).

[5]

Pedro Amaral, Joao Dinis, Paulo Pinto, Luis Bernardo, Joao Tavares, and Henrique S Mamede. 2016. Machine learning in software defined networks: data collection and traffic classification. In Proc. IEEE ICNP'16.

[6]

Marianna Angelou, Siamak Azodolmolky, Ioannis Tomkos, Jordi Perelló, Salvatore Spadaro, Davide Careglio, Kostas Manousakis, Panagiotis Kokkinos, Emmanouel Varvarigos, Dimitri Staessens, et al. 2012. Benefits of implementing a dynamic impairment-aware optical network: results of EU project DICONET. IEEE Commun. Mag. 50, 8 (2012).

[7]

Berk Birand, Howard Wang, Keren Bergman, Dan Kilper, Thyaga Nandagopal, and Gil Zussman. 2014. Real-time power control for dynamic optical networks-Algorithms and experimentation. IEEE J. Sel. Areas Commun. 32, 8 (2014), 1615--1628.

[8]

Berk Birand, Howard Wang, Keren Bergman, and Gil Zussman. 2013. Measurements-based power control-a cross-layered framework. In Proc. OFC'13.

[9]

Peter Bodík, Rean Griffith, Charles A Sutton, Armando Fox, Michael I Jordan, and David A Patterson. 2009. Statistical machine learning makes automatic control practical for internet datacenters. In Proc. USENIX HotCloud'09.

Digital Library

[10]

Angela L Chiu, Gagan Choudhury, George Clapp, Robert Doverspike, Mark Feuer, Joel W Gannett, Janet Jackel, Gi Tae Kim, John G Klincewicz, Taek Jin Kwon, et al. 2012. Architectures and protocols for capacity efficient, highly dynamic and highly resilient core networks. IEEE J. Opt. Commun. Netw. 4, 1 (2012), 1--14.

[11]

Paulo Cortez, Miguel Rio, Miguel Rocha, and Pedro Sousa. 2006. Internet traffic forecasting using neural networks. In Proc. IEEE IJCNN'06.

[12]

Robert D Doverspike and Jennifer Yates. 2012. Optical network management and control. Proc. IEEE 100, 5 (2012), 1092--1104.

[13]

Steven Gringeri, Nabil Bitar, and Tiejun J Xia. 2013. Extending software defined network principles to include optical transport. IEEE Commun. Mag. 51, 3 (2013), 32--40.

[14]

Chi-Yao Hong, Srikanth Kandula, Ratul Mahajan, Ming Zhang, Vijay Gill, Mohan Nanduri, and Roger Wattenhofer. 2013. Achieving high utilization with software-driven WAN. In Proc. ACM SIGCOMM'13.

Digital Library

[15]

Yishen Huang, Craig L Gutterman, Payman Samadi, Patricia B Cho, Wiem Samoud, Cédric Ware, Mounia Lourdiane, Gil Zussman, and Keren Bergman. 2017. Dynamic mitigation of EDFA power excursions with machine learning. Optics Express 25, 3 (2017), 2245--2258.

[16]

Kiyo Ishii, Junya Kurumida, and Shu Namiki. 2016. Experimental investigation of gain offset nehavior of feedforward-controlled WDM AGC EDFA under various dynamic wavelength allocations. IEEE Photon. J. 8, 1 (2016), 1--13.

[17]

Sushant Jain, Alok Kumar, Subhasree Mandal, Joon Ong, Leon Poutievski, Arjun Singh, Subbaiah Venkata, Jim Wanderer, Junlan Zhou, Min Zhu, Jonathan Zolla, Urs Holzle, Stephen Stuart, and Amin Vahdat. 2013. B4: Experience with a globally-deployed software defined WAN. In Proc. ACM SIGCOMM'13.

Digital Library

[18]

Xin Jin, Yiran Li, Da Wei, Siming Li, Jie Gao, Lei Xu, Guangzhi Li, Wei Xu, and Jennifer Rexford. 2016. Optimizing bulk transfers with software-defined optical WAN. In Proc. ACM SIGCOMM'16.

Digital Library

[19]

Joseph Junio, Daniel C Kilper, and Vincent WS Chan. 2012. Channel power excursions from single-step channel provisioning. IEEE J. Opt. Commun. Netw. 4, 9 (2012), A1--A7.

[20]

Daniel Kilper, Kyle Guan, Kerry Hinton, and Robert Ayre. 2012. Energy challenges in current and future optical transmission networks. Proc. IEEE 100, 5 (2012), 1168--1187.

[21]

Daniel C Kilper, M Bhopalwala, H Rastegarfar, and W Mo. 2015. Optical power dynamics in wavelength layer software defined networking. In Proc. Photonic Networks and Devices'15.

[22]

Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing atari with deep reinforcement learning. arXiv:1312.5602 (2013).

[23]

Lynn E. Nelson, Guodong Zhang, Narayan Padi, Craig Skolnick, Kathleen Benson, Troy Kaylor, Satoshi Iwamatsu, Robert Inderst, Fabio Marques, Daniel Fonseca, Mei Du, Terry Downs, Thor Scherer, Christopher Cole, Y Zhou, Paul Brooks, and Andreas Schubert. 2017. SDN-Controlled 400GbE end-to-end service using a CFP8 client over a deployed, commercial flexible ROADM system. In Proc. OFC'17.

[24]

Masaki Shiraiwa, Hideaki Furukawa, Takaya Miyazawa, Yoshinari Awaji, and Naoya Wada. 2015. Concurrently establishing and removing multi-wavelength channels reconfiguration system: Implementation for a dynamic and agile next-generation optical switching network. In Proc. IEEE PS'15.

[25]

David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. Nature 529, 7587 (2016), 484--489.

[26]

Thomas A. Strasser and Jefferson L. Wagener. 2010. Wavelength-selective switches for ROADM applications. IEEE J. Sel. Topics Quantum Electron. 16, 5 (2010), 1150--1157.

[27]

Yong Wu, Luca Chiaraviglio, Marco Mellia, and Fabio Neri. 2009. Power-aware routing and wavelength assignment in optical networks. In Proc. IEEE ECOC'09.

[28]

Tiejun J. Xia, Glenn Wellbrock, Bert Basch, Scott Kotrla, Wang Lee, Tsutomu Tajima, Kiyoshi Fukuchi, Milorad Cvijetic, Jim Sugg, Yin K. Ma, et al. 2010. End-to-end native IP data 100G single carrier real time DSP coherent detection transport over 1520-km field deployed fiber. In Proc. OFC'10.

[29]

Ying Zhang and Ake Årvidsson. 2012. Understanding the characteristics of cellular data traffic. In Proc. ACM SIGCOMM'12 workshop on Cellular networks: operations, challenges, and future design.

Digital Library

Cited By

Gao HChen XLu CLi Z(2024)On the generalization of cognitive optical networking applications using composable machine learningJournal of Optical Communications and Networking10.1364/JOCN.51498116:6(631)Online publication date: 14-May-2024
https://doi.org/10.1364/JOCN.514981
Salani MRottondi CCeré LTornatore M(2023)Dual-Stage Planning for Elastic Optical Networks Integrating Machine-Learning-Assisted QoT EstimationIEEE/ACM Transactions on Networking10.1109/TNET.2022.321397031:3(1293-1307)Online publication date: Jun-2023
https://doi.org/10.1109/TNET.2022.3213970
Chen YGao HXiao YChen XLi Z(2023)Field Trials of Communication and QoT Estimation over an SDM Optical Fiber Cable Network2023 IEEE 7th International Symposium on Electromagnetic Compatibility (ISEMC)10.1109/ISEMC58300.2023.10370483(1-4)Online publication date: 20-Oct-2023
https://doi.org/10.1109/ISEMC58300.2023.10370483
Show More Cited By

Index Terms

Neural Network Based Wavelength Assignment in Optical Switching

Recommendations

Wavelength assignment algorithm in optical multicast networks with multi-wavelength conversion
APCC'09: Proceedings of the 15th Asia-Pacific conference on Communications

Multi-wavelength conversion is a feasible technique to realize optical signal replication. However, there are little work to study the wavelength assignment and network performance in the optical network employing multi-wavelength conversion. In this ...
Routing and wavelength assignment for hypercube in array-based WDM optical networks

Hypercube is one of the most versatile and efficient communication patterns shared by a large number of computational problems. As the number of edges in hypercube grows logarithmically with the size of networks, the complexity of network topologies can ...
Performance Evaluation of Heuristic Algorithms for Wavelength Assignment in WDM Optical Networks
ICPPW '04: Proceedings of the 2004 International Conference on Parallel Processing Workshops

Given a set of connection requests in a WDM optical network and a designated lightpath for each connection request, the wavelength assignment problem is to assign a wavelength to each lightpath in such a way that light-paths sharing common links are ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

Big-DAMA '17: Proceedings of the Workshop on Big Data Analytics and Machine Learning for Data Communication Networks

August 2017

58 pages

ISBN:9781450350549

DOI:10.1145/3098593

Copyright © 2017 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

SIGCOMM: ACM Special Interest Group on Data Communication

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 August 2017

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

NSF

Conference

SIGCOMM '17

Sponsor:

SIGCOMM

SIGCOMM '17: ACM SIGCOMM 2017 Conference

August 21, 2017

CA, Los Angeles, USA

Acceptance Rates

Overall Acceptance Rate 7 of 11 submissions, 64%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

14
Total Citations
View Citations
666
Total Downloads

Downloads (Last 12 months)58
Downloads (Last 6 weeks)8

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

Cited By

Gao HChen XLu CLi Z(2024)On the generalization of cognitive optical networking applications using composable machine learningJournal of Optical Communications and Networking10.1364/JOCN.51498116:6(631)Online publication date: 14-May-2024
https://doi.org/10.1364/JOCN.514981
Salani MRottondi CCeré LTornatore M(2023)Dual-Stage Planning for Elastic Optical Networks Integrating Machine-Learning-Assisted QoT EstimationIEEE/ACM Transactions on Networking10.1109/TNET.2022.321397031:3(1293-1307)Online publication date: Jun-2023
https://doi.org/10.1109/TNET.2022.3213970
Chen YGao HXiao YChen XLi Z(2023)Field Trials of Communication and QoT Estimation over an SDM Optical Fiber Cable Network2023 IEEE 7th International Symposium on Electromagnetic Compatibility (ISEMC)10.1109/ISEMC58300.2023.10370483(1-4)Online publication date: 20-Oct-2023
https://doi.org/10.1109/ISEMC58300.2023.10370483
Freire MSengupta DLavignotte ATremblay CLepers C(2021)Reinforcement Learning for Compensating Power Excursions in Amplified WDM SystemsJournal of Lightwave Technology10.1109/JLT.2021.3107774(1-1)Online publication date: 2021
https://doi.org/10.1109/JLT.2021.3107774
Rai SGarg A(2021)Analysis of RWA in WDM optical networks using machine learning for traffic prediction and pattern extractionJournal of Optics10.1007/s12596-021-00735-652:2(900-907)Online publication date: 13-Jul-2021
https://doi.org/10.1007/s12596-021-00735-6
Zhu SGutterman CMontiel AYu JRuffini MZussman GKilper D(2020)Hybrid Machine Learning EDFA ModelOptical Fiber Communication Conference (OFC) 202010.1364/OFC.2020.T4B.4(T4B.4)Online publication date: 2020
https://doi.org/10.1364/OFC.2020.T4B.4
D’Amico AStraullu SNespola AKhan ILondon EVirgillito EPiciaccia STanzi AGalimberti GCurri V(2020)Using machine learning in an open optical line system controllerJournal of Optical Communications and Networking10.1364/JOCN.38255712:6(C1)Online publication date: 14-Feb-2020
https://doi.org/10.1364/JOCN.382557
Zhang YXin JLi XHuang S(2020)Overview on routing and resource allocation based machine learning in optical networksOptical Fiber Technology10.1016/j.yofte.2020.10235560(102355)Online publication date: Dec-2020
https://doi.org/10.1016/j.yofte.2020.102355
Gao RLiu LLiu XLun HYi LHu WZhuge Q(2020)An overview of ML-based applications for next generation optical networksScience China Information Sciences10.1007/s11432-020-2874-y63:6Online publication date: 12-May-2020
https://doi.org/10.1007/s11432-020-2874-y
Ravi Prakash Rao TMalleswara Rao V(2018)Load and Link Aware Protection Switching Technique for WDM NetworksJournal of Optical Communications10.1515/joc-2018-0090Online publication date: 19-Oct-2018
https://doi.org/10.1515/joc-2018-0090
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten