A comparison of mechanisms for improving TCP performance over wireless links (1997)
Cached
Download Links
- [www.cs.cmu.edu]
- [www.cs.cmu.edu]
- [www-2.cs.cmu.edu]
- [www.cs.uccs.edu]
- [cs.uccs.edu]
- [www.cs.umass.edu]
- [www.cs.ucsb.edu]
- [www.cs.cmu.edu]
- [www.cs.ucsd.edu]
- [www-cse.ucsd.edu]
- [www.sds.lcs.mit.edu]
- [daedalus.cs.berkeley.edu]
- [csl.ee.iastate.edu]
- [www.cs.cmu.edu]
- [cs.wisc.edu]
- [cs.wisc.edu]
- [www.cs.rutgers.edu]
- [www.cs.cmu.edu]
- [pdos.lcs.mit.edu]
- [daedalus.cs.berkeley.edu]
- [wind.lcs.mit.edu]
- [wind.lcs.mit.edu]
- [si.di.fc.ul.pt]
- [www.research.microsoft.com]
- [www-2.cs.cmu.edu]
- [www.research.microsoft.com]
- [www.utdallas.edu]
- DBLP
Other Repositories/Bibliography
| Venue: | IEEE/ACM TRANSACTIONS ON NETWORKING |
| Citations: | 698 - 10 self |
BibTeX
@ARTICLE{Balakrishnan97acomparison,
author = {Hari Balakrishnan and Venkata N. Padmanabhan and Srinivasan Seshan and Randy H. Katz},
title = {A comparison of mechanisms for improving TCP performance over wireless links},
journal = {IEEE/ACM TRANSACTIONS ON NETWORKING},
year = {1997},
volume = {5},
pages = {756--769}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Reliable transport protocols such as TCP are tuned to perform well in traditional networks where packet losses occur mostly because of congestion. However, networks with wireless and other lossy links also suffer from significant losses due to bit errors and handoffs. TCP responds to all losses by invoking congestion control and avoidance algorithms, resulting in degraded end-to-end performance in wireless and lossy systems. In this paper, we compare several schemes designed to improve the performance of TCP in such networks. We classify these schemes into three broad categories: end-to-end protocols, where loss recovery is performed by the sender; link-layer protocols, that provide local reliability; and split-connection protocols, that break the end-to-end connection into two parts at the base station. We present the results of several experiments performed in both LAN and WAN environments, using throughput and goodput as the metrics for comparison. Our results show that a reliable link-layer protocol that is TCP-aware provides very good performance. Furthermore, it is possible to achieve good performance without splitting the end-to-end connection at the base station. We also demonstrate that selective acknowledgments and explicit loss notifications result in significant performance improvements.
