Network performance trade-off in modular data centers with optical spatial division multiplexing

Modular design based on spatial division multiplexing switches is a promising way to improve the capacity and reduce the cabling complexity of data center networks. However, due to the coexistence of mice and elephant flows, in modular data center networks a trade-off between the blocking probability and total throughput arises. In fact, blocking elephant flows would lead to a relevant penalty on the throughput but a small penalty on the blocking probability. In this paper, we investigate the relation between the blocking and throughput in modular data center networks based on optical spatial division multiplexing. We combine the two metrics linearly by a weight factor that prioritizes them relatively. To solve the resource allocation problem, we propose both mixed integer linear programming formulations and close-to-optimal heuristics for three different spatial division multiplexing switching schemes. Simulation results demonstrate that a carefully chosen weight factor is necessary to achieve a proper balance between the blocking probability and throughput for all the schemes.

[1]  Dan M. Marom,et al.  Switching solutions for WDM-SDM optical networks , 2015, IEEE Communications Magazine.

[2]  Michael Galili,et al.  A roadmap for evolving towards optical intra-data-center networks , 2016 .

[3]  Amin Vahdat,et al.  Helios: a hybrid electrical/optical switch architecture for modular data centers , 2010, SIGCOMM '10.

[4]  James R. Hamilton,et al.  An Architecture for Modular Data Centers , 2006, CIDR.

[5]  Liangjia Zong,et al.  Survey of photonic switching architectures and technologies in support of spatially and spectrally flexible optical networking [invited] , 2017, IEEE/OSA Journal of Optical Communications and Networking.

[6]  Dimitra Simeonidou,et al.  Routing, spectrum and core allocation in flexgrid SDM networks with multi-core fibers , 2014, 2014 International Conference on Optical Network Design and Modeling.

[7]  David J. Ives,et al.  Physical layer transmitter and routing optimization to maximize the traffic throughput of a nonlinear optical mesh network , 2014, 2014 International Conference on Optical Network Design and Modeling.

[8]  Henk Wymeersch,et al.  Nonlinear Impairment-Aware Static Resource Allocation in Elastic Optical Networks , 2015, Journal of Lightwave Technology.

[9]  Georgios Zervas,et al.  Comparison of SDM and WDM on Direct and Indirect Optical Data Center Networks , 2016 .

[10]  Madeleine Glick,et al.  TCP flow classification and bandwidth aggregation in optically interconnected data center networks , 2016, IEEE/OSA Journal of Optical Communications and Networking.

[11]  Eiji Oki,et al.  Routing and Spectrum Allocation in Elastic Optical Networks: A Tutorial , 2015, IEEE Communications Surveys & Tutorials.

[12]  David J. Ives,et al.  Routing, modulation, spectrum and launch power assignment to maximize the traffic throughput of a nonlinear optical mesh network , 2015, Photonic Network Communications.

[13]  Alex C. Snoeren,et al.  Inside the Social Network's (Datacenter) Network , 2015, Comput. Commun. Rev..

[14]  Ioannis Tomkos,et al.  Spatial group sharing for SDM optical networks with Joint Switching , 2016, 2016 International Conference on Optical Network Design and Modeling (ONDM).

[15]  I. Tomkos,et al.  Spectral vs. spatial super-channel allocation in SDM networks under independent and joint switching paradigms , 2015, 2015 European Conference on Optical Communication (ECOC).

[16]  Biswanath Mukherjee,et al.  Spatial division multiplexing for high capacity optical interconnects in modular data centers , 2017, IEEE/OSA Journal of Optical Communications and Networking.

[17]  Hideki Tode,et al.  On-demand spectrum and core allocation for reducing crosstalk in multicore fibers in elastic optical networks , 2014, IEEE/OSA Journal of Optical Communications and Networking.

[18]  David A. Maltz,et al.  Network traffic characteristics of data centers in the wild , 2010, IMC '10.

[19]  David J. Richardson,et al.  Beam-steering all-optical switch for multi-core fibers , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[20]  Elio Salvadori,et al.  Comparison of Spectral and Spatial Super-Channel Allocation Schemes for SDM Networks , 2016, Journal of Lightwave Technology.

[21]  Masahiko Jinno,et al.  Spectrally and spatially flexible optical network planning and operations , 2015, IEEE Communications Magazine.

[22]  Biswanath Mukherjee,et al.  Optical spatial division multiplexing for ultra-high-capacity modular data centers , 2016, 2016 Optical Fiber Communications Conference and Exhibition (OFC).

[23]  David J. Ives,et al.  Adapting Transmitter Power and Modulation Format to Improve Optical Network Performance Utilizing the Gaussian Noise Model of Nonlinear Impairments , 2014, Journal of Lightwave Technology.

[24]  Toshio Morioka,et al.  Experimental Demonstration of Multidimensional Switching Nodes for All-Optical Data Center Networks , 2016, Journal of Lightwave Technology.

[25]  Ryuichi Sugizaki,et al.  Recent Progress and Outlook on Multicore Fiber for Practical Use , 2018, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[26]  Ming Zhang,et al.  Understanding data center traffic characteristics , 2010, CCRV.

[27]  Massimo Tornatore,et al.  Network performance trade-off in optical spatial division multiplexing data centers , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[28]  Ioannis Tomkos,et al.  Impact of Spatial and Spectral Granularity on the Performance of SDM Networks Based on Spatial Superchannel Switching , 2017, Journal of Lightwave Technology.

[29]  Li Yan,et al.  Nonlinear-Impairments- and Crosstalk-Aware Resource Allocation Schemes for Multicore-Fiber-based Flexgrid Networks , 2016 .