doi:10.1016/j.comcom.2007.02.017
Copyright © 2007 Elsevier B.V. All rights reserved.
Improving performance of transport protocols in multipath transferring schemes
References and further reading may be available for this article. To view references and further reading you must
purchase this article.
Maysam Yabandeh
, a, 
, Sajjad Zarifzadeha, and Nasser Yazdania,
aRouter Laboratories, ECE Department, Faculty of Engineering, University of Tehran, Iran
Available online 5 March 2007.
Abstract
One major drawback of multipath transferring schemes inspired by usage of different paths with diverse delays is the emergence of reordering among packets of the same flow. In this paper, we present two separate approaches to resolve this problem for UDP and TCP connections. By properly scheduling the packets among multiple paths, our UDP-based approach tries to deliver data to the receiver in-order, while imposing a minimum possible delay and small buffer space on the receiver’s application. We theoretically prove the optimality of the proposed method and then present its analytical results. Unfortunately, in the case of TCP, the reordering intensifies the problem by bringing more timeouts and many unnecessary fast-retransmits which eventually degrades the throughput of TCP connections considerably. To address these issues, we first present the general conditions that should be held to avoid timeouts in multipath schemes. Then, we enhance our approach by preventing nonessential fast-retransmit/recovery events in TCP. Moreover, we introduce an analytical model to estimate the probability of triggering 3rd duplicate ACK in our method. Finally, through simulation experiments we show that the performance of our multipath methods is comparable with the optimal one-path transmissions (with aggregated bandwidth); especially, in terms of throughput and fast-retransmit ratio parameters.
Keywords: Multipath transferring; Transport protocols; Reordering; Multimedia communication; Delay
Fig. 1. Timeline of sequential transmission steps in the presented model. The transmission time of bulk j lasts tj seconds and the delay of path k is dk.
Fig. 2. Schematic view of the proposed idea for UDP connections. The method schedules packets at the source to arrive in-order at the destination.
Fig. 3. Axis of receiving times from paths 1 and 2. The zero point of the axis represents the start of transmission by the sender.
Fig. 4. The additional delay imposed by the proposed method on the receiver’s application (i.e., BPT-d1) with respect to the delay difference (i.e., Δd) and bandwidth ratio of the slower path (i.e., C2/C).
Fig. 5. Maximum tolerable value of f1 (C1/C) under different values of K (the constant factor in TCP’s timeout formula).
Fig. 6. Interleaving reception of packets through two paths. With the assumption that each packet contains just one byte of data, the number above each packet represents the sequence number of that packet and the one below it stands for the last successful received sequence number.
Fig. 7. All possible overlapping cases for the reception of bulk i and i + 1.
Fig. 8. Schematic view for computing the minimum tolerable transmission time for bulk i + 1.
Fig. 9. Relative order between sending times of packets belonging to two consecutive bulk k and k + 1.
Fig. 10. The area in the (
,
) plane that satisfies 
. The Case A depicts this area when α > 0 and Case B shows the mentioned area when α < 0.
Fig. 11. BPT achieved by UDP methods for transferring a file of size 100 KB.
Fig. 12. Throughput achieved by TCP methods for transferring a file of size 100 KB (a) simple multipath method, (b) our enhanced multipath method and (c) one-path method.
Fig. 13. Throughput achieved by TCP methods for transferring a file of size 1000 KB (a) simple multipath method, (b) our enhanced multipath method and (c) one-path method.
Fig. 14. Number of drops in TCP methods for transferring a file of size 1000 KB (a) simple multipath method, (b) our enhanced multipath method and (c) one-path method.
Fig. 15. Dropped throughput in our approach with respect to the one-path method. These results are measured by transferring a file of size 1000 KB.
Fig. 16. Analytical results for the probability of triggering 3rd duplicate ACK computed through (55).
Fig. 17. Number of timeout events in our method for transferring a file of size 1000 KB.
Table 1.
Number of fast retransmission events for transferring a file of size 900 KB; The numbers in each cell belong to the number of fast retransmissions obtained respectively by simple multipath (SM) approach, enhanced multipath (EM) approach, and one-path (OP) method. The rows and columns represent the ratio of bandwidth and delay of path 2 to path 1, respectively
Corresponding author. Tel.: +98 21 61114352; fax: +98 21 88778690.
Abstract
Purchase PDF (638 K)
E-mail Article
Add to my Quick Links
Cited By in Scopus (0)
Purchase PDF (5492 K)
