DOC PREVIEW
UCLA COMSCI 218 - Analysis of TCP Performance

This preview shows page 1-2-3-4 out of 12 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
View full document
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 12 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

Analysis of TCP Performance over Mobile Ad Hoc Networks* Gavin Holland and Nitin Vaidya Department of Computer Science Texas A&M University, College Station, TX 77843-3112 {gholland,vaidya}@cs.tamu.edu Abstract Mobile ad hoc networks have gained a lot of attention lately as a means of providing continuous network connectivity to mobile computing devices regardless of physical location. Recently, a large amount of re- search has focused on the routing protocols needed in such an environment. In this paper, we investi- gate the effects that link breakage due to mobility has on TCP performance. Through simulation, we show that TCP throughput drops significantly when nodes move, due to TCP’s inability to recognize the difference between link failure and congestion. We also analyze specific examples, such as a situation where throughput is zero for a particular connec- tion. We introduce a new metric, expected throughput, for the comparison of throughput in multi-hop net- - - works, and then use this metric to show how the use of explicit link failure notification (ELFN) techniques can significantly improve TCP performance. 1 Introduction With the proliferation of mobile computing devices, the demand for continuous network connectivity regardless of physical location has spurred interest in the use of mobile ad hoc networks. A mobile ad hoc network is a network in which a group of mobile computing devices communicate among themselves using wireless radios, without the aid of a fixed networking infras- tructure. Their use is being proposed as an exten- sion to the Internet, but they can be used anywhere that a fixed infrastructure does not exist, or is not de- sirable. A lot of research of mobile ad hoc networks has focused on the development of routing protocols (e.g. [19, 10, 11, 16, 18, 20, 21, 22, 231. ‘This work was supported in part by the Department of Ed- ucation under Award No. P200A80305, the National Science Foundation under Grant No. CDA-9529442, and the Texas Ad- vanced Technology Program under Grant No. 010115-248. Permission lo make digital or hard copies of all or part of this work for personal or classroom USC is granted without fee provided that copies are not made or distributed for protit or commercial advantage and that copies bear this notice and the full citation on the tirst page. To copy otherwise, to republish, to post on servers or to redistribute to lists. requires prior spccitic permission and/or a fee. Mobicom ‘99 Seattle Washington USA Copyright ACM 1999 l-581 13-142-9/99/08...$5.00 Our research is focused on the performance of TCP over mobile ad hoc networks. Since TCP/IP is the standard network protocol stack on the Internet, its use over mobile ad hoc networks is a certainty. Not only does it leverage a large number of applications, but its use also allows seamless integration with the Internet, where available. However, earlier research on cellular wireless sys- tems showed that TCP suffers poor performance in wire- less networks because of packet losses and corruption caused by wireless induced errors. Thus, a lot of re- search has since focused on mechanisms to improve TCP performance in cellular wireless systems (e.g. [2, 31). Further studies have addressed other network problems that negatively affect TCP performance, such as band- width asymmetry and large round-trip times, which are prevalent in satellite networks (e.g. [12, 41). In this paper, we address another network character- istic that impacts TCP performance, which is common in mobile ad hoc networks: link failures due to mobil- ity. We first present a performance analysis of standard TCP over mobile ad hoc networks, and then present an analysis of the use of explicit notification techniques to counter the affects of link failures. 2 Simulation Environment and Methodology The results in this paper are based on simulations using the ns network simulator from Lawrence Berkeley Na- tional Laboratory (LBNL) [13], with extensions from the MONARCH project at Carnegie Mellon [5]. The extensions include a set of mobile ad hoc network rout- ing protocols and an implementation of BSD’s ARP protocol, as well as an 802.11 MAC layer and a radio propagation model. Also included are mechanisms to model node mobility using pre-computed mobility pat- terns that are fed to the simulation at run-time. For more information about the extensions, we refer the reader to [5]. Unless otherwise noted, no modifications were made to the simulator described in [5], beyond mi- nor bug fixes that were necessary to complete the study. All results are based on a network configuration con- sisting of TCP-Reno over IP on an 802.11 wireless net- work, with routing provided by the Dynamic Source 219Routing (DSR) protocol and BSD’s ARP protocol (used to resolve IP addresses to MAC addresses). The choice of DSR as the routing protocol was based on the availability of the ns extensions at the time when this study was initiated. Our goal was only to’ observe TCP’s performance in the presence of mobility induced failures in a plausible network environment, for which any of the proposed mobile wireless ad hoc routing pro- tocols would have sufficed. However, since we frequently refer to the routing protocol in this paper, the next para- graph is a brief primer on DSR to familiarize the reader with its terminology and characteristics. The Dynamic Source Routing (DSR) protocol was developed by researchers at CMU for use in mobile ad hoc networks [6]. In DSR, each packet injected into the network contains a routing header that specifies the complete sequence of nodes on which the packet should be forwarded. This route is obtained through route dis- covery. When a node


View Full Document

UCLA COMSCI 218 - Analysis of TCP Performance

Documents in this Course
GSM

GSM

59 pages

Chord

Chord

30 pages

10_2

10_2

9 pages

13_4

13_4

10 pages

RAP

RAP

17 pages

46_4

46_4

9 pages

32_4

32_4

10 pages

umts

umts

39 pages

AdHoc-MAC

AdHoc-MAC

29 pages

rma

rma

8 pages

Lecture

Lecture

29 pages

Load more
Download Analysis of TCP Performance
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Analysis of TCP Performance and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Analysis of TCP Performance 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?