thesis

Information about thesis

Published on September 30, 2007

Author: Heather

Source: authorstream.com

Content

Slide1:  Kunal Shah Advisor: Dr. Harish Sethu SIMULATION BASED STUDY OF TCP FAIRNESS IN MULTI-HOP WIRELESS NETWORKS Computer Communications Laboratory Outline:  Outline Introduction and Motivation Background Model Description Simulation Results and Analysis Conclusion Introduction:  Introduction Ad Hoc Networks: A collection of nodes Capable of acting as a host and a router simultaneously Communicate with each other over shared, multi-hop wireless channels Required where a fixed wired or wireless infrastructure is either unavailable or destroyed Characterized by high mobility, low bandwidths, limited physical security and continuously changing network topology Once the ad hoc network is up and running using some routing protocol, next step is to evaluate performance of transport layer protocol Motivation:  Motivation As local area wireless networks based on IEEE 802.11 standard see increasing public deployment, it is important to ensure that access to network by different users remains fair No structured studies devoted to formal investigation of TCP fairness in wireless multi-hop networks Focus:  Focus Evaluate TCP Tahoe, Reno, New Reno and SACK for fairness Motivation for selecting these TCP implementations was their popularity Fairness metric based on maximal normalized distance between user’s ideal share and actual share of service delivered by network Analyze the effects of packet size, load, TCP receive buffer size and RTS/CTS on TCP fairness TCP Evolution:  TCP Evolution Dominant reliable transport protocol since its origin Consists of sliding window mechanism, which, in conjunction with ACKs and sequence numbers, guaranteed a reliable delivery and flow control No congestion control or avoidance mechanism TCP Evolution (Cont.):  TCP Evolution (Cont.) AIMD – virtually the base of all existing TCP protocols Besides maximizing link bandwidth, TCP must be fair to rest of the flows Efficient TCP is not guaranteed to be fair TCP Tahoe:  TCP Tahoe Congestion Control Algorithms: Slow Start Congestion Avoidance Fast Retransmit Problem: Transits to slow start after each packet loss TCP Reno:  TCP Reno Extension of TCP Tahoe Added Fast Recovery along with Fast Retransmit TO: Time-out TD: Threshold Duplicate TCP New Reno:  TCP New Reno TCP Reno problem: Fast Recovery algorithm rendered inefficient in the presence of multiple losses within a single transmission window TCP New Reno remains in fast recovery mode despite receiving partial acknowledgement after fast retransmission Retransmits at the rate of one packet per RTT until all the lost packets are retransmitted No retransmit timeout TCP SACK:  TCP SACK Selective Acknowledgements are used to provide the sender with sufficient information to recover from multiple packet losses within a single transmission window Sender knows exactly which packets to retransmit and so is able to quickly recover Problem: Inefficient in the case of small sender window size Fairness Criteria:  Fairness Criteria Intuitively, one can think of fairness as the closeness of achieved throughput to its fair share Max-Min Fairness (MMF):  Max-Min Fairness (MMF) When flows have equal weights, Max-Min Fair share allocation can be defined as: Resources are allocated in order of increasing demand No user gets a resource larger than its demand Users with unmet demands get an equal share of the resource MMF Example:  MMF Example Dividing a 8 slice pizza among 4 people 2 slices 1 slice 4 slices 2 slices 2 slices 2 slices 4 slices 2 slices 2 slices 2 slices desires and gets - 1 slice = 1 slice + 1 slice = 3 slices 3 slices 2 slices 2 slices + 1 slice = 3 slices Proposed Unfairness Criterion:  Proposed Unfairness Criterion where Fi = MMFi (C, d1, d2, …, dn) Sample Unfairness Calculation:  Sample Unfairness Calculation 2 Mbps 1 Mbps 3 Mbps 0.8 Mbps 0.6 Mbps i di Ai C = 1.8 Mbps MMFi U = 0.5 0.7 Mbps 0.3 Mbps 0.6 Mbps 0.6 Mbps Related work on TCP Fairness:  Related work on TCP Fairness When flows with different end-to-end propagation delays shared a link, the bandwidth allocation was far from being fair Constant rate window increase algorithm Increase-by-K policy Congestion Avoidance with Normalized Interval of Time (CANIT) Wireless links are characterized by long RTT and above schemes react by opening up the congestion window at a much higher rate Increased probing harmful as slow 56k modem links and band-limited wireless links are themselves a bottleneck in the network Performance degradation not only due to transmission errors and losses but also due to congestion at base station → Fast TCP Flow that got head-start occupied large amount of bandwidth and starved the flows starting later on → split buffer queues Unfair packet dropping policy at Internet routers → RED policy Related work on TCP Performance:  Related work on TCP Performance Explicit Congestion Notification (ECN) Explicit Link Loss Notification M-TCP Split TCP Snoop TCP MAC Layer Fairness:  MAC Layer Fairness IEEE 802.11 uses per-node queue with per node back-off Head-of-line packet headed towards a receiver that is in high contention neighborhood can block other flow transmissions to lightly loaded neighbors Node with many flows penalizes its flow unfairly Flows that experience more contention will block more contending flows while transmitting Implementing changes made to MAC layer are impractical given the wide deployment of wireless networks using IEEE 802.11 standard Lot of research done in improving MAC layer fairness and TCP performance but no real effort made in studying TCP fairness Model Description - Node:  Model Description - Node Application Process Model:  Application Process Model TCP Process Model:  TCP Process Model AODV Background:  AODV Background Source-based routing protocol based on DSDV and DSR Utilizes sequence number of DSDV and on-demand route discovery and maintenance mechanisms of DSR Power Efficient No flooding or periodic update messages AODV Process Model:  AODV Process Model WLAN Process Model:  WLAN Process Model Simulation Scenario:  Simulation Scenario Simulation Setup:  Simulation Setup Every TCP connection is of type FTP and all flows start at the same time In each scenario, if user 1 (node 1) wants to send x Mbps, then user 2 wants to send 2x Mbps, user 3 wants to send 3x Mbps and so forth Mobility pattern is static Battery power is infinity and transmitter power is 0.25 Watts Simulation Setup (Cont.):  Simulation Setup (Cont.) Packet sizes are varied from 128 bytes to 1,024 bytes but ACKs are kept at 40 bytes long TCP receive buffer size is varied from 8,760 bytes to 131,072 bytes Load is varied from 1.5 Mbps to 7.5 Mbps to simulate low, medium and high traffic loads Load is varied from 1.5 Mbps to 7.5 Mbps but with RTS/CTS enabled for packet sizes larger than 255 packets Simulation Setup (Cont.):  Simulation Setup (Cont.) All other parameters were left unchanged as per IEEE 802.11b standard Simulation was conducted for TCP Tahoe, Reno, New Reno and SACK Simulation Results – TCP Receive Buffer Size:  Simulation Results – TCP Receive Buffer Size Simulation Results – TCP Receive Buffer Size:  Simulation Results – TCP Receive Buffer Size Simulation Results – Load with No RTS/CTS:  Simulation Results – Load with No RTS/CTS Simulation Results – Load with RTS/CTS:  Simulation Results – Load with RTS/CTS Simulation Results – Packet Size:  Simulation Results – Packet Size Conclusion:  Conclusion Using the maximal normalized distance between the actual allocation and the max-min fair share allocation as a fairness metric, TCP fairness was evaluated for TCP Tahoe, Reno, New Reno and SACK by varying TCP receive buffer size, load with and without RTS/CTS and packet size TCP Tahoe was the least unfair protocol but suffered from low throughput Tentative Conclusions:  Tentative Conclusions Fairness best when: TCP receive buffer size is large Load is high and No RTS/CTS is deployed Load is low and RTS/CTS is deployed Packet size is larger for large TCP buffer size Future Work:  Future Work Tentative conclusions need to be studied in much more depth to comprehend the complex behavior of TCP in wireless networks Analyze suggested TCP improvements like Split TCP and ECN for fairness Introduce mobility and then analyze TCP fairness Acknowledgements:  Acknowledgements I am sincerely grateful to my advisor Dr. Harish Sethu for watching, directing and guiding me throughout each stage of this work I am thankful to Dr. Constantine Katsinis and Dr. Kapil Dandekar for serving in my thesis committee I thank all the members of Computer Communications Laboratory for their support and responsiveness Questions?:  Questions?

Related presentations


Other presentations created by Heather

nanotechnology presentation
13. 10. 2007
0 views

nanotechnology presentation

MMLA group ppt 11 28 05
08. 10. 2008
0 views

MMLA group ppt 11 28 05

Sadiq
08. 05. 2008
0 views

Sadiq

Mun101806
08. 05. 2008
0 views

Mun101806

ch09r
08. 05. 2008
0 views

ch09r

louise baur
08. 05. 2008
0 views

louise baur

Obesity
07. 05. 2008
0 views

Obesity

radev
07. 05. 2008
0 views

radev

pp pres sptconfrday
06. 05. 2008
0 views

pp pres sptconfrday

pp pres sptconfrday
06. 05. 2008
0 views

pp pres sptconfrday

Communication skills notes
26. 11. 2007
0 views

Communication skills notes

L12 Superconductivity
12. 10. 2007
0 views

L12 Superconductivity

Development of behavior
11. 10. 2007
0 views

Development of behavior

Silver Sword Review
19. 10. 2007
0 views

Silver Sword Review

Notes Russia
27. 09. 2007
0 views

Notes Russia

spiritual warefare combined2
01. 10. 2007
0 views

spiritual warefare combined2

ASAPJan06 Presentation Millonig
03. 10. 2007
0 views

ASAPJan06 Presentation Millonig

symp04 pp liming e
10. 10. 2007
0 views

symp04 pp liming e

China India Web FINAL POST
10. 10. 2007
0 views

China India Web FINAL POST

reptile powerpoint
12. 10. 2007
0 views

reptile powerpoint

Heatsub
12. 10. 2007
0 views

Heatsub

Notes Europe
15. 10. 2007
0 views

Notes Europe

Funding Biomedical Research
16. 10. 2007
0 views

Funding Biomedical Research

NEW chpt 4
17. 10. 2007
0 views

NEW chpt 4

ATUG power point presentation
17. 10. 2007
0 views

ATUG power point presentation

ANT3141 20 Peru
19. 10. 2007
0 views

ANT3141 20 Peru

Implication du Personnel
24. 10. 2007
0 views

Implication du Personnel

lecture 45
02. 10. 2007
0 views

lecture 45

McK CIT 05 PC2A
15. 10. 2007
0 views

McK CIT 05 PC2A

chapter2 notes
15. 10. 2007
0 views

chapter2 notes

brun
28. 10. 2007
0 views

brun

Branson HIV and Privacy 2
29. 10. 2007
0 views

Branson HIV and Privacy 2

Oracle OTC
05. 11. 2007
0 views

Oracle OTC

Darwinismo
06. 11. 2007
0 views

Darwinismo

WRITING unit 3 summaries 95
18. 10. 2007
0 views

WRITING unit 3 summaries 95

lecture28
16. 11. 2007
0 views

lecture28

VirologyReview2005
19. 11. 2007
0 views

VirologyReview2005

Martha
20. 11. 2007
0 views

Martha

gender selection
21. 11. 2007
0 views

gender selection

ulrich 120203
30. 10. 2007
0 views

ulrich 120203

LPP600 ch5 rev
06. 11. 2007
0 views

LPP600 ch5 rev

dance
23. 11. 2007
0 views

dance

rutas de putaendo
24. 10. 2007
0 views

rutas de putaendo

Insomnia 2
28. 11. 2007
0 views

Insomnia 2

marktoberdorf
30. 10. 2007
0 views

marktoberdorf

PacketSwitching1
30. 12. 2007
0 views

PacketSwitching1

Manshadi impact
03. 01. 2008
0 views

Manshadi impact

Ionizing Radiation 2
04. 01. 2008
0 views

Ionizing Radiation 2

egov ma
23. 10. 2007
0 views

egov ma

chap15a
05. 01. 2008
0 views

chap15a

lecture hazard individual choice
04. 10. 2007
0 views

lecture hazard individual choice

Spanish presentation
22. 10. 2007
0 views

Spanish presentation

presentazione estetismo
01. 10. 2007
0 views

presentazione estetismo

BVS Panama
22. 10. 2007
0 views

BVS Panama

Hollywood
25. 10. 2007
0 views

Hollywood

astro12Summer11
13. 11. 2007
0 views

astro12Summer11

ryud
09. 10. 2007
0 views

ryud

MetaphorsWeLiveBy
24. 10. 2007
0 views

MetaphorsWeLiveBy

AMMA briefing
06. 11. 2007
0 views

AMMA briefing

west africa down
03. 01. 2008
0 views

west africa down

zhping PHD
04. 10. 2007
0 views

zhping PHD

Ch02
15. 10. 2007
0 views

Ch02

02Coelho Review
16. 10. 2007
0 views

02Coelho Review

RUSSIA transition
26. 10. 2007
0 views

RUSSIA transition

39124236 GEOMORPHOLOGY RIVERS
19. 10. 2007
0 views

39124236 GEOMORPHOLOGY RIVERS

AFlood2005
03. 01. 2008
0 views

AFlood2005

26 Beautiful One liners 09 12 06
07. 10. 2007
0 views

26 Beautiful One liners 09 12 06

milia v10
21. 02. 2008
0 views

milia v10

BRT LA Metro
29. 10. 2007
0 views

BRT LA Metro

18531
24. 02. 2008
0 views

18531

gulf war 2 desert storm
26. 02. 2008
0 views

gulf war 2 desert storm

NDBs MSC SA Mondi
27. 02. 2008
0 views

NDBs MSC SA Mondi

t2nd edn
16. 03. 2008
0 views

t2nd edn

AsiaPacificUpdate
25. 03. 2008
0 views

AsiaPacificUpdate

Lecture23 SmallSats
15. 11. 2007
0 views

Lecture23 SmallSats

BU NSF06 kannan
31. 10. 2007
0 views

BU NSF06 kannan

Macro Chapter 4
10. 04. 2008
0 views

Macro Chapter 4

mini supercells jmm final
03. 10. 2007
0 views

mini supercells jmm final

SPS CM Seminar
14. 04. 2008
0 views

SPS CM Seminar

lecture13 Online Games
22. 04. 2008
0 views

lecture13 Online Games

IDN Gold WebEx BSE
22. 04. 2008
0 views

IDN Gold WebEx BSE

NIV oncall
01. 05. 2008
0 views

NIV oncall

history stuff
14. 12. 2007
0 views

history stuff

abadinsky08 ppt ch03
07. 01. 2008
0 views

abadinsky08 ppt ch03

The BioArtificial Liver2
02. 05. 2008
0 views

The BioArtificial Liver2

Katrina RRC
02. 05. 2008
0 views

Katrina RRC

angusallyouneed tcm4 123635
02. 10. 2007
0 views

angusallyouneed tcm4 123635

ladeau
21. 10. 2007
0 views

ladeau

Presentation10
09. 04. 2008
0 views

Presentation10

Food web of the Arctic
10. 10. 2007
0 views

Food web of the Arctic

Barbara 01
26. 09. 2007
0 views

Barbara 01

Befmod Dog Pony Big
17. 04. 2008
0 views

Befmod Dog Pony Big

TC
09. 10. 2007
0 views

TC

EHaro Presentacion Casablanca
24. 10. 2007
0 views

EHaro Presentacion Casablanca

Turner Powerpoint
31. 12. 2007
0 views

Turner Powerpoint

Feb27
07. 10. 2007
0 views

Feb27

2005 Kobe
09. 10. 2007
0 views

2005 Kobe

liberal jun2000 tapia
15. 10. 2007
0 views

liberal jun2000 tapia

hiv and smoking
29. 10. 2007
0 views

hiv and smoking

157 4s1 10p35 voloshin
26. 10. 2007
0 views

157 4s1 10p35 voloshin

cicognani
11. 10. 2007
0 views

cicognani

paper55
29. 10. 2007
0 views

paper55

Mission and Vision
07. 01. 2008
0 views

Mission and Vision

2004 07 01 rochoa
15. 11. 2007
0 views

2004 07 01 rochoa

Seva activities at Bridgewater
10. 12. 2007
0 views

Seva activities at Bridgewater

African lag
05. 10. 2007
0 views

African lag

8 Barbra Morgante RFI
15. 10. 2007
0 views

8 Barbra Morgante RFI

Vajente GWDAW11 StatusOfVirgo
01. 12. 2007
0 views

Vajente GWDAW11 StatusOfVirgo

papineni
15. 10. 2007
0 views

papineni

housemtg 20040907
16. 10. 2007
0 views

housemtg 20040907

ClevelandStateF2005
02. 11. 2007
0 views

ClevelandStateF2005

IDC prezentace LinuxWorld
24. 10. 2007
0 views

IDC prezentace LinuxWorld

stassun
01. 01. 2008
0 views

stassun

Models User Guide
05. 10. 2007
0 views

Models User Guide

Suite Sensation General
07. 12. 2007
0 views

Suite Sensation General

Suchman Virology 2005
16. 10. 2007
0 views

Suchman Virology 2005

jd graz
18. 03. 2008
0 views

jd graz

veronarda
03. 10. 2007
0 views

veronarda

RHIC spin talk
15. 11. 2007
0 views

RHIC spin talk

Nian Cai Liu presentation
15. 10. 2007
0 views

Nian Cai Liu presentation