Learning congestion over millimeter-wave channels

This paper studies how learning techniques can be used by the congestion control algorithms employed by transport protocols over 5G wireless channels, in particular millimeter waves. We show how metrics measured at the transport layer might be valuable to ascertain the congestion level. In situations characterized by a high correlation between such parameters and the actual congestion, it is observed that the performance of unsupervised learning methods is comparable to supervised learning approaches. Exploiting the ns-3 platform to perform an in-depth, realistic assessment, allows us to study the impact of various layers of the protocol stack. We also consider different scheduling policies to discriminate whether the allocation of radio resources impacts the performance of the proposed scheme.

[1]  Theodore S. Rappaport,et al.  Investigation and Comparison of 3GPP and NYUSIM Channel Models for 5G Wireless Communications , 2017, 2017 IEEE 86th Vehicular Technology Conference (VTC-Fall).

[2]  Theodore S. Rappaport,et al.  3-D Millimeter-Wave Statistical Channel Model for 5G Wireless System Design , 2016, IEEE Transactions on Microwave Theory and Techniques.

[3]  George F. Riley,et al.  The ns-3 Network Simulator , 2010, Modeling and Tools for Network Simulation.

[4]  S. Dutta,et al.  5G MmWave Module for the ns-3 Network Simulator , 2015, MSWiM.

[5]  Mo Dong,et al.  PCC Vivace: Online-Learning Congestion Control , 2018, NSDI.

[6]  Athanasios V. Vasilakos,et al.  A survey of millimeter wave communications (mmWave) for 5G: opportunities and challenges , 2015, Wireless Networks.

[7]  Hari Balakrishnan,et al.  An experimental study of the learnability of congestion control , 2014, SIGCOMM.

[8]  Sundeep Rangan,et al.  Transport layer performance in 5G mmWave cellular , 2016, 2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS).

[9]  Hari Balakrishnan,et al.  Mahimahi: Accurate Record-and-Replay for HTTP , 2015, USENIX Annual Technical Conference.

[10]  Gorry Fairhurst,et al.  Enabling Internet-Wide Deployment of Explicit Congestion Notification , 2015, PAM.

[11]  Anh T. Pham,et al.  On the Throughput Performance of TCP Cubic in Millimeter-Wave Cellular Networks , 2019, IEEE Access.

[12]  Lakshminarayanan Subramanian,et al.  Adaptive Congestion Control for Unpredictable Cellular Networks , 2015, Comput. Commun. Rev..

[13]  Ramón Agüero,et al.  Learning Congestion State For mmWave Channels , 2019, mmNets@MobiCom.

[14]  Mark Handley,et al.  Congestion control for high bandwidth-delay product networks , 2002, SIGCOMM '02.

[15]  Albert G. Greenberg,et al.  Data center TCP (DCTCP) , 2010, SIGCOMM '10.

[16]  Jing Zhu,et al.  Will TCP Work in mmWave 5G Cellular Networks? , 2018, IEEE Communications Magazine.

[17]  Jeffrey G. Andrews,et al.  What Will 5G Be? , 2014, IEEE Journal on Selected Areas in Communications.

[18]  Van Jacobson,et al.  BBR: Congestion-Based Congestion Control , 2016, ACM Queue.

[19]  Sundeep Rangan,et al.  A Framework for End-to-End Evaluation of 5G mmWave Cellular Networks in ns-3 , 2016, WNS3 '16.

[20]  Hari Balakrishnan,et al.  Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks , 2013, NSDI.

[21]  Shin-Lin Shieh,et al.  5G New Radio: Waveform, Frame Structure, Multiple Access, and Initial Access , 2017, IEEE Communications Magazine.

[22]  Nick Feamster,et al.  Design and implementation of a routing control platform , 2005, NSDI.

[23]  Leandros Tassiulas,et al.  Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks , 1992 .

[24]  Pierre Geurts,et al.  A machine learning approach to improve congestion control over wireless computer networks , 2004, Fourth IEEE International Conference on Data Mining (ICDM'04).