Neural Network Based Wavelength Assignment in Optical Switching

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%.

[1]  Michael I. Jordan,et al.  Statistical Machine Learning Makes Automatic Control Practical for Internet Datacenters , 2009, HotCloud.

[2]  M. Mellia,et al.  Power-Aware Routing and Wavelength Assignment in optical networks , 2009, 2009 35th European Conference on Optical Communication.

[3]  Shu Namiki,et al.  Experimental Investigation of Gain Offset Behavior of Feedforward-Controlled WDM AGC EDFA Under Various Dynamic Wavelength Allocations , 2016, IEEE Photonics Journal.

[4]  Srikanth Kandula,et al.  Achieving high utilization with software-driven WAN , 2013, SIGCOMM.

[5]  Wei Xu,et al.  Optimizing Bulk Transfers with Software-Defined Optical WAN , 2016, SIGCOMM.

[6]  L. E. Nelson,et al.  SDN-controlled 400GbE end-to-end service using a CFP8 client over a deployed, commercial flexible ROADM system , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[7]  J. Junio,et al.  Channel power excursions from single-step channel provisioning , 2012, IEEE/OSA Journal of Optical Communications and Networking.

[8]  Alex Graves,et al.  Playing Atari with Deep Reinforcement Learning , 2013, ArXiv.

[9]  Naoya Wada,et al.  Concurrently establishing and removing multi-wavelength channels reconfiguration system: Implementation for a dynamic and agile next-generation optical switching network , 2015, 2015 International Conference on Photonics in Switching (PS).

[10]  Gil Zussman,et al.  Dynamic mitigation of EDFA power excursions with machine learning. , 2017, Optics express.

[11]  Ying Zhang,et al.  Understanding the characteristics of cellular data traffic , 2012, CCRV.

[12]  Dahai Xu,et al.  Architectures and Protocols for Capacity Efficient, Highly Dynamic and Highly Resilient Core Networks [Invited] , 2012, IEEE/OSA Journal of Optical Communications and Networking.

[13]  Jennifer Yates,et al.  Optical Network Management and Control , 2012, Proceedings of the IEEE.

[14]  Nabil Bitar,et al.  Extending software defined network principles to include optical transport , 2013, IEEE Communications Magazine.

[15]  Daniel C. Kilper,et al.  Energy Challenges in Current and Future Optical Transmission Networks , 2012, Proceedings of the IEEE.

[16]  Miguel Rio,et al.  Internet Traffic Forecasting using Neural Networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[17]  Didier Colle,et al.  Benefits of implementing a dynamic impairment-aware optical network: results of EU Project DICONET , 2012, IEEE Communications Magazine.

[18]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[19]  Howard Wang,et al.  Measurements-based power control - A cross-layered framework , 2013, 2013 Optical Fiber Communication Conference and Exposition and the National Fiber Optic Engineers Conference (OFC/NFOEC).

[20]  Daniel C. Kilper,et al.  Real-Time Power Control for Dynamic Optical Networks—Algorithms and Experimentation , 2013, IEEE Journal on Selected Areas in Communications.

[21]  T J Xia,et al.  End-to-end native IP data 100G single carrier real time DSP coherent detection transport over 1520-km field deployed fiber , 2010, 2010 Conference on Optical Fiber Communication (OFC/NFOEC), collocated National Fiber Optic Engineers Conference.

[22]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[23]  Min Zhu,et al.  B4: experience with a globally-deployed software defined wan , 2013, SIGCOMM.

[24]  Luís Bernardo,et al.  Machine Learning in Software Defined Networks: Data collection and traffic classification , 2016, 2016 IEEE 24th International Conference on Network Protocols (ICNP).

[25]  T. Strasser,et al.  Wavelength-Selective Switches for ROADM Applications , 2010, IEEE Journal of Selected Topics in Quantum Electronics.

[26]  Houman Rastegarfar,et al.  Optical Power Dynamics in Wavelength Layer Software Defined Networking , 2015 .