Stochastic forecasts achieve high throughput and low delay over cellular networks

  • Authors:
  • Keith Winstein;Anirudh Sivaraman;Hari Balakrishnan

  • Affiliations:
  • MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Mass;MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Mass;MIT Computer Science and Artificial Intelligence Laboratory, Cambridge, Mass

  • Venue:
  • nsdi'13 Proceedings of the 10th USENIX conference on Networked Systems Design and Implementation
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

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.