Exploiting the Path Propagation Time Differences in Multipath Transmission with FEC

Abstract

Abstract-We consider a transmission of a delay-sensitive data stream from a single source to a single destination. The reliability of this transmission may suffer from bursty packet losses -the predominant type of failures in today's Internet. An effective and well studied solution to this problem is to protect the data by a Forward Error Correction (FEC) code and send the FEC packets over multiple paths. In this paper we show that the performance of such a multipath FEC scheme can often be further improved. Our key observation is that the propagation times on the available paths often significantly differ, typically by 10-100ms. We propose to exploit these differences by appropriate packet scheduling that we call 'Spread'. We evaluate our solution with a precise, analytical formulation and tracedriven simulations. Our studies show that Spread substantially outperforms the state-of-the-art solutions. It typically achieves two-to five-fold improvement (reduction) in the effective loss rate. Or conversely, keeping the same level of effective loss rate, Spread significantly decreases the observed delays and helps fighting the delay jitter.

Goodput-Aware Load Distribution for Real-Time Traffic over Multipath Networks

“…We compare the performance of the proposed packet interleaving scheme with three representative multipath packet spreading approaches, i.e., the Smarttunnel [36], EMS [20], and Spread [55]. The evaluation results are provided in the supplementary file.…”

Online multipath convolutional coding for real-time transmission

“…In [12], Kurant showed that the propagation time differences between paths reach several tens of milliseconds by measurements. In case of FEC, the last packet (source or repair) in a FEC block arrived at the receiver must be sooner than the end-to-end (E2E) delay requirements normally specified by the path with longest propagation delay.…”

“…The simulation duration is 1000s with OLS Adapt Window of 1 second. Kurant showed in [12] that the propagation delay differences between paths reach several tens of milliseconds. Thus, we vary the propagation delay on each path from 50 to 80ms so that no path has the same delay to the others and the maximum delay difference between paths is 30ms.…”

Guest Editorial Trading Rate for Delay at the Application and Transport Layers

“…[8] studies how to allocate transmission rate resources among two users in a Gaussian multiple access channel to trade network sum rate for the delays the users experience. [9] considers the performance, deployment, and security properties of network scheduling that differentiates users on the basis of whether they would like a high rate or a Digital Object Identifier 10.1109/JSAC.2011.110501 [11], [12], [13], [14], [15] [16], [17], [18], [19] low queueing delay. Finally, [10] utilizes a network calculus approach to study the effect of classes of link scheduling algorithms on end to end delay.…”

“…Finally, [10] utilizes a network calculus approach to study the effect of classes of link scheduling algorithms on end to end delay. Moving on to approaches which allow the encoding of packet contents, but only at the source, [11] considers the effect of both traffic pacing and forward error correction maximum distance separable codes on reliable transmission rate with deadlines. [12] considers the joint optimization of a source fountain encoder and multiple path selection to provide a high rate within a bounded delay.…”