Legacy congestion control protocols including TCP and its variants, are known to perform poorly over cellular networks due to highly variable capacities over short time scales, self-inflicted packet delays, and packet losses unrelated to congestion. Three specific characteristics directly impact the unpredictability of cellular channels.
First, the state of a cellular channel between a mobile device and a base station undergoes several complex state transitions that affect channel availability in short time scales; this introduces variability in the underlying channel.
Second, the frame scheduling algorithms used in cellular networks cause burstiness in the cellular channel. Based on real-world cellular measurements, we observe that the typical traffic characteristics at a receiver are bursty (even for smooth source transmission patterns), with variable burst sizes and burst inter-arrival periods.
Third, while prior work has considered only self-inflicted queuing delay as a cause for high delays, we find that competing traffic does affect end-to-end delay characteristics, especially under high contention or when the cellular channel is near saturation.
Finally, device mobility has a substantial impact on channel characteristics that further compounds these challenges. The lack of channel predictability has important implications on the design of new congestion control protocols. The large bandwidth coupled with connectivity impairments associated with mmWave channels will qualitatively change the nature of congestion control.
Improved Network Performance Over 5G mmWave Cellular
In this project we aim at designing a transport layer protocol optimized for the mmWave access network, and for the new class of applications that it will enable, aiming to work seamlessly across a connection consisting of both wireline and wireless segments.In our recent ICC paper submission “The Bufferbloat Problem over Intermittent Multi-Gbps mmWave Links”, we have proposed a simple approach to solve some of the major issues related to TCP over mmWave that we observed in our previous publication: “Transport layer performance in 5G mmWave cellular”. Our solution, namely Dynamic RW, delivers high throughput while guaranteeing low latency.
|R. Kumary, R.S. Margolies, R. Jana, Y. Liuyand, S. Panwar, "WiLiTV: A Low-Cost Wireless Framework for Live TV Services,"2017 IEEE Conference on Computer Communications Workshops, May 2017||Distributed Core||2017/04/11|
|R. Ford, A. Sridharan, R. Margolies, R. Jana, S. Rangan “Provisioning Low Latency, Resilient Mobile Edge Clouds for 5G” arXiv:1703.10915 [cs.NI]||Distributed Core||2017/03/31|
|M. Zhang, M. Mezzavilla, J. Zhu, S. Rangan, S. Panwar "The Bufferbloat Problem over Intermittent Multi-Gbps mmWave Links" arXiv:1611.02117 [cs.NI]||Congestion Control, Future Congestion Control, High-speed, networking, mmwave, Networking||2016/12/22|
|E. Kurdoglu, Y. Liu, Y. Wang, Y. Shi, C. Gu, J. Lyu, "Real-time Bandwidth Prediction and Rate Estimation for Video Calls over Cellular Networks," in Proceedings of the 7th International Conference on Multimedia Systems, ACM, 2016 / Klagenfurt, Austria||Congestion Control, Future Congestion Control, High-speed, networking||2016/12/21|
|R. Ford, M. Zhang, S. Dutta M. Mezzavilla, S. Rangan, M. Zorzi "A Framework for End-to-End Evaluation of 5G mmWaveCellular Networks in ns-3" Proceedings of the Workshop on ns-3, Pages 85-92, June 15 - 16, 2016, Seattle, WA, USA||5G Channel Models, High-speed, networking, mmwave, mmWave Channel Models, ns3||2016/06/15|
|M. Zhang, M. Mezzavilla, R. Ford, S. Rangan, S. Panwar, E. Mellios, D. Kong, A. Nix, M. Zorzi, "Transport layer performance in 5G mmWave cellular", Computer Communications Workshops (INFOCOM WKSHPS) 2016 IEEE Conference on, pp. 730-735, 2016.||Congestion Control, Dynamic Channel Models, ns3||2016/04/14|
|M. Zhang, M. Mezzavilla, R. Ford, S. Rangan, S. Panwar, E. Mellios, D. Kong, A.. Nix, M. Zorzi, Transport Layer Performance in 5G mmWave Cellular, IEEE Infocom Millimeter Wave Networking Workshop, San Francisco, April 2016.||Congestion Control, Millimeter Wave 5G Prototype, mmWave MAC, ns3||2016/03/08|
|R. Ford, M. Zhang, M. Mezzavilla, S. Dutta, S. Rangan, M. Zorzi, Achieving Ultra-Low Latency in 5G Millimeter Wave Cellular Networks, IEEE Communications Magazine 55.3 (2017): 196-203.||Congestion Control, high speed mmwave mac, High-speed, networking, Millimeter Wave 5G Prototype, mmWave MAC, ns3||2016/02/23|
|R. Ford, M. Zhang, M. Mezzavilla, S. Dutta, S. Rangan, M. Zorzi "A Framework for End-to-End Evaluation of 5G mmWaveCellular Networks in ns-3" Proceedings of the Workshop on ns-3, Pages 85-92, June 15 - 16, 2016, Seattle, WA, USA||High-speed, networking, Millimeter Wave 5G Prototype, mmWave MAC||2016/02/23|
|Y. Zaki, T. Pötsch, J. Chen, L. Subramanian, C. Görg,“Adaptive Congestion Control for Unpredictable Cellular Networks” ACM Special Interest Group on Data Communication (SIGCOMM) London, UK, August 2015.||Congestion Control, Future Congestion Control||2015/08/01|
|M. Mezzavilla, S. Dutta, M. Zhang, M. R. Akdeniz, S. Rangan, “5G mmWave Module for the ns-3 Network Simulator,” Proceedings of the 18th ACM International Conference on Modeling, Analysis and Simulation of Wireless and Mobile Systems. ACM, 2015.||High-speed, networking, Millimeter Wave 5G Prototype, ns3||2015/06/29|
|R. Gupta, B. Bachmann, R. Ford, S. Rangan, N. Kundargi, A. Ekbal, K. Rathi, M.I. Sanchez, A. Oliva, A. Morelli, “ns-3-based real-time emulation of LTE testbed using LabVIEW platform for software defined networking (SDN) in CROWD project. “ Proc. Workshop on ns-3 (WNS3 ’15)., Barcelona, Spain, May 2015.||High-speed, networking, Millimeter Wave 5G Prototype, Wireless Comm||2015/05/13|
|Z. Cao, S. Panwar, M. Kodialam, T. Lakshman, "Enhancing Mobile Networks With Software Defined Networking and Cloud Computing," in IEEE/ACM Transactions on Networking , vol.PP, no.99, pp.1-14||Distributed Core||2017/04/11|
|R. Ford, M. Zhang, M. Mezzavilla, S. Dutta, S. Rangan and M. Zorzi, "Achieving Ultra-Low Latency in 5G Millimeter Wave Cellular Networks," in IEEE Communications Magazine, vol. 55, no. 3, pp. 196-203, March 2017.||Distributed Core, high speed mmwave mac, mmWave MAC||2017/03/03|
|S. Dutta, M. Zhang, M. Mezzavilla, M.R. Akdeniz, S. Rangan, Millimeter wave module for ns-3 network simulator||High-speed, networking, Wireless Comm||2015/06/29|