- Overview
- Registration Information
- Registration Discounts
- Symposium Organizers
- At a Glance
- Calendar
- Technical Sessions
- Live Streaming
- Purchase the Box Set
- Tutorial on GENI
- Posters and Demos
- Sponsorship
- Activities
- Hotel and Travel Information
- Services
- Students
- Questions?
- Help Promote
- For Participants
- Call for Papers
- Past Proceedings
sponsors
usenix conference policies
You are here
Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks
Keith Winstein, Anirudh Sivaraman, and Hari Balakrishnan, M.I.T. Computer Science and Artificial Intelligence Laboratory
Sprout is an end-to-end transport protocol for interactive applications that desire high throughput and low delay. Sprout works well over cellular wireless networks, where link speeds change dramatically with time, and current protocols build up multi-second queues in network gateways. Sprout does not use TCP-style reactive congestion control; instead the receiver observes the packet arrival times to infer the uncertain dynamics of the network path. This inference is used to forecast how many bytes may be sent by the sender, while bounding the risk that packets will be delayed inside the network for too long.
In evaluations on traces from four commercial LTE and 3G networks, Sprout, compared with Skype, reduced self-inflicted end-to-end delay by a factor of 7.9 and achieved 2.2 the transmitted bit rate on average. Compared with Google’s Hangout, Sprout reduced delay by a factor of 7.2 while achieving 4.4 the bit rate, and compared with Apple’s Facetime, Sprout reduced delay by a factor of 8.7 with 1.9 the bit rate.
Although it is end-to-end, Sprout matched or outperformed TCP Cubic running over the CoDel active queue management algorithm, which requires changes to cellular carrier equipment to deploy. We also tested Sprout as a tunnel to carry competing interactive and bulk traffic (Skype and TCP Cubic), and found that Sprout was able to isolate client application flows from one another.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
author = {Keith Winstein and Anirudh Sivaraman and Hari Balakrishnan},
title = {Stochastic Forecasts Achieve High Throughput and Low Delay over Cellular Networks},
booktitle = {10th USENIX Symposium on Networked Systems Design and Implementation (NSDI 13)},
year = {2013},
isbn = {978-1-931971-00-3},
address = {Lombard, IL},
pages = {459--471},
url = {https://www.usenix.org/conference/nsdi13/technical-sessions/presentation/winstein},
publisher = {USENIX Association},
month = apr
}
Presentation Video
Presentation Audio
by Lakshminarayanan Subramanian
This is a highly refreshing paper among the large gamut of papers on congestion control in the research literature. The authors consider the problem of building a highly effective congestion control mechanism for cellular networks, especially to achieve the dual goals of high throughput and low delay. This paper has many interesting design surprises. One of the surprising observations in this paper is that link speeds change dramatically with time, and current transport protocols build up multi-second queues in network gateways, thereby yielding low throughputsand highly variable packet delays. This paper proposes Sprout, an end-to-end transport protocol primarily designed for interactive applications to function well over highly variable cellular network channels. The second surprising design choice in Sprout is that it does not function anything like any known TCP-style congestion control protocol;rather, it learns a stochastic model of the cellular channel based on packet arrival times, and uses the model to quickly adapt the transmission rate of a flow. Sprout specifically aims to avoid the queue buildup problem experienced by existing transport protocols. The third surprising aspect about the paper is the evaluation. Across four different cellular networks, the authors show that Sprout achieved a factor of 7-9 reduction in the end-to-end self-inflicted delay, and a factor of 2-4 enhancement in the bit rate throughput, for 3 popular interactive applications: Google Hangout, Skype and Apple FaceTime. The authors also show that Sprout matches or outperforms TCP Cubic coupled with an active queue management technique that requires changes to the cellular network. These surprises put together make this paper a very interesting read.
The key idea of Sprout is to adapt the sending rate to roughly match the current cellular network capacity while not overshooting it; by achieving this objective, Sprout can both maintain high throughput and avoid queuing delays in the network. To achieve this goal, Sprout models the cellular link using a Poisson process with an underlying rate which may change over time. Sprout models the evolution of the probability distribution on the underlying rate using Brownian motion, with which Sprout proposes a control protocol to determine the current transmission rate for an end-point. An interesting design choice made by the authors is to compute the evolution in the distribution of the underlying rate, as opposed to computing the evolution of the mean or median underlying rate. The distribution inherently captures a lot more information, and the authors can use this to compute a "safe" sending rate that has a good chance of incurring low queuing delays for the transmitted packets. They also propose Sprout-EWMA, a minor variant of Sprout that provides significant gains over Sprout as well.
There is definitely a lot more work that can be done in this space. I appreciate the authors explicitly pinpointing several limitations of their work, which leads to an array of interesting questions for future work. I will pinpoint two specific points. First, we need a much deeper understanding of the bandwidth and delay characteristics of cellular networks. Given these queuing effects, I am not sure if existing bandwidth and RTT measurement tools would be able to accurately capture these highly variable parameters. How do we distinguish between queuing based delays and non-queuing based delays? What is the impact of large or small buffers? Is there value in redesigning the queue management used in cellular networks? Second, from a Sprout design standpoint, the authors have not yet analyzed the case where Sprout cannot control delays due to competing traffic. The presence of competing traffic raises an array of questions including: (a) How do two Sprout flows compete on the same channel? (b) Does Sprout'sstochastic channel model hold in the face of competing traffic? (c) How do conventional congestion control algorithms compete with Sprout over the same cellular channel? I will end the summary with a fascinating sentence hidden in the paper: "TCP Vegas achieves lower delay than Sprout-EWMA." Are we back to the Vegas days and is this going to start a new war on congestion control?
connect with us