Atjaunināt sīkdatņu piekrišanu

End-to-End Adaptive Congestion Control in TCP/IP Networks [Hardback]

4.00/5 (2 ratings by Goodreads)
(Artistotle University of Thessaloniki, Greece), (Artistotle University of Thessaloniki, Greece)
  • Formāts: Hardback, 332 pages, height x width: 234x156 mm, weight: 589 g, 14 Tables, black and white; 105 Illustrations, black and white
  • Sērija : Automation and Control Engineering
  • Izdošanas datums: 24-Apr-2012
  • Izdevniecība: CRC Press Inc
  • ISBN-10: 1439840571
  • ISBN-13: 9781439840573
Citas grāmatas par šo tēmu:
  • Hardback
  • Cena: 269,29 €
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
End-to-End Adaptive Congestion Control in TCP/IP NetworksPalielināt
  • Formāts: Hardback, 332 pages, height x width: 234x156 mm, weight: 589 g, 14 Tables, black and white; 105 Illustrations, black and white
  • Sērija : Automation and Control Engineering
  • Izdošanas datums: 24-Apr-2012
  • Izdevniecība: CRC Press Inc
  • ISBN-10: 1439840571
  • ISBN-13: 9781439840573
Citas grāmatas par šo tēmu:
Permanent link: https://www.kriso.lv/db/9781439840573.html
Keywords:
Establishing adaptive control as an alternative framework to design and analyze Internet congestion controllers, End-to-End Adaptive Congestion Control in TCP/IP Networks employs a rigorously mathematical approach coupled with a lucid writing style to provide extensive background and introductory material on dynamic systems stability and neural network approximation; alongside future internet requests for congestion control architectures. Designed to operate under extreme heterogeneous, dynamic, and time-varying network conditions, the developed controllers must also handle network modeling structural uncertainties and uncontrolled traffic flows acting as external perturbations. The book also presents a parallel examination of specific adaptive congestion control, NNRC, using adaptive control and approximation theory, as well as extensions toward cooperation of NNRC with application QoS control.

Features:











Uses adaptive control techniques for congestion control in packet switching networks





Employs a rigorously mathematical approach with lucid writing style





Presents simulation experiments illustrating significant operational aspects of the method; including scalability, dynamic behavior, wireless networks, and fairness





Applies to networked applications in the music industry, computers, image trading, and virtual groups by techniques such as peer-to-peer, file sharing, and internet telephony





Contains working examples to highlight and clarify key attributes of the congestion control algorithms presented

Drawing on the recent research efforts of the authors, the book offers numerous tables and figures to increase clarity and summarize the algorithms that implement various NNRC building blocks. Extensive simulations and comparison tests analyze its behavior and measure its performance through monitoring vital network quality metrics. Divided into three parts, the book offers a review of computer networks and congestion control, presents an adaptive congestion control framework as an alternative to optimization methods, and provides appendices related to dynamic systems through universal neural network approximators.
List of Figures
xiii
List of Tables
xix
Preface xxi
1 Introduction
1(12)
1.1 Overview
1(1)
1.2 Future Internet
2(2)
1.3 Internet Congestion Control
4(4)
1.4 Adaptive Congestion Control
8(5)
I Background on Computer Networks and Congestion Control
13(98)
2 Controlled System: The Packet-Switched Network
15(34)
2.1 Overview
15(2)
2.2 Network Connectivity
17(7)
2.2.1 Links and Nodes
17(1)
2.2.2 Sub-Networks
17(2)
2.2.3 Network Classification
19(2)
2.2.4 LAN Topologies
21(3)
2.3 Network Communication
24(16)
2.3.1 Packet Switching
24(2)
2.3.2 Protocols and Layering
26(2)
2.3.3 Internet Architecture
28(4)
2.3.4 Transfer Control Protocol (TCP)
32(5)
2.3.5 User Datagram Protocol (UDP)
37(1)
2.3.6 Internet Protocol (IP)
38(2)
2.4 Performance Characteristics
40(3)
2.4.1 Queue Size
40(1)
2.4.2 Throughput
40(1)
2.4.3 Link Utilization
41(1)
2.4.4 Packet Loss Rate
41(1)
2.4.5 Round Trip Time
41(1)
2.4.6 Fairness
42(1)
2.5 Applications
43(4)
2.5.1 E-Mail
44(1)
2.5.2 World Wide Web
44(1)
2.5.3 Remote Access
45(1)
2.5.4 File Transfer
45(1)
2.5.5 Streaming Media
46(1)
2.5.6 Internet Telephony (VOIP)
46(1)
2.6 Concluding Comments
47(2)
3 Congestion Issues and TCP
49(16)
3.1 Overview
49(1)
3.2 Core Issues in Congestion Control
50(1)
3.3 TCP: Flow Control and Congestion Control
51(6)
3.3.1 Slow Start
52(1)
3.3.2 Congestion Avoidance
53(2)
3.3.3 Fast Retransmit and Fast Recovery
55(2)
3.4 TCP Problems
57(2)
3.5 Managing Congestion
59(4)
3.5.1 TCP Friendliness
59(1)
3.5.2 Classification of Congestion Control Protocols
60(1)
3.5.2.1 Window-Based vs. Rate-Based
60(1)
3.5.2.2 Unicast vs. Multicast
61(1)
3.5.2.3 End-to-End vs. Router-Based
62(1)
3.6 Concluding Comments
63(2)
4 Measuring Network Congestion
65(14)
4.1 Overview
65(1)
4.2 Drop Tail
66(1)
4.3 Congestion Early Warning
67(10)
4.3.1 Packet Drop Schemes
68(4)
4.3.2 Packet Marking Schemes
72(5)
4.4 Concluding Comments
77(2)
5 Source-Based Congestion Control Mechanisms
79(18)
5.1 Overview
79(1)
5.2 Traditional TCP
80(1)
5.3 TCP Modifications for Networks with Large Bandwidth Delay Products
81(5)
5.3.1 Scalable TCP (STCP)
82(1)
5.3.2 HighSpeed TCP (HSTCP)
82(2)
5.3.3 BIC
84(1)
5.3.4 CUBIC
85(1)
5.4 Delay-Based Congestion Control
86(3)
5.4.1 TCP Vegas
87(1)
5.4.2 FAST TCP
88(1)
5.5 Congestion Control for Wireless Networks
89(3)
5.5.1 TCP Westwood
90(1)
5.5.2 TCP Veno
91(1)
5.6 Congestion Control for Multimedia Applications
92(3)
5.6.1 Rate Adaptation Protocol (RAP)
92(2)
5.6.2 TFRC
94(1)
5.7 Concluding Comments
95(2)
6 Fluid Flow Model Congestion Control
97(14)
6.1 Overview
97(1)
6.2 The Fluid Flow Model
98(1)
6.3 Network Representation
99(2)
6.4 Congestion Control as a Resource Allocation Problem
101(5)
6.4.1 Dual Approach
103(1)
6.4.2 Primal Approach
104(1)
6.4.3 Utility Function Selection
104(2)
6.5 Open Issues
106(3)
6.5.1 Stability and Convergence
106(1)
6.5.2 Implementation Constraints
107(1)
6.5.3 Robustness
107(1)
6.5.4 Fairness
108(1)
6.6 Concluding Comments
109(2)
II Adaptive Congestion Control Framework
111(104)
7 NNRC: An Adaptive Congestion Control Framework
113(12)
7.1 Overview
113(1)
7.2 Packet Switching Network System
114(3)
7.3 Problem Statement
117(1)
7.4 Throughput Improvement
118(2)
7.5 NNRC Framework Description
120(3)
7.5.1 Future Path Congestion Level Estimator
121(1)
7.5.2 Feasible Desired Round Trip Time Estimator
122(1)
7.5.3 Rate Control
122(1)
7.5.4 Throughput Control
123(1)
7.6 Concluding Comments
123(2)
8 NNRC: Rate Control Design
125(26)
8.1 Overview
125(1)
8.2 Feasible Desired Round Trip Time Estimator Design
125(7)
8.2.1 Proof of Lemma 8.1
129(1)
8.2.2 Proof of Lemma 8.2
130(2)
8.3 Rate Control Design
132(8)
8.3.1 Guaranteeing Boundness of Transmission Rate
137(1)
8.3.2 Reducing Rate in Congestion
138(2)
8.4 Illustrative Example
140(8)
8.4.1 Implementation Details
141(1)
8.4.2 Network Topology
142(1)
8.4.3 Normal Scenario
142(1)
8.4.4 Congestion Avoidance Scenario
143(5)
8.5 Concluding Comments
148(3)
9 NNRC: Throughput and Fairness Guarantees
151(20)
9.1 Overview
151(1)
9.2 Necessity for Throughput Control
151(2)
9.3 Problem Definition
153(1)
9.4 Throughput Control Design
154(4)
9.4.1 Guaranteeing Specific Bounds on the Number of Channels
156(1)
9.4.2 Reducing Channels in Congestion
157(1)
9.5 Illustrative Example
158(11)
9.5.1 Implementation Details
159(1)
9.5.2 Normal Scenario
160(3)
9.5.3 Congestion Avoidance Scenario
163(1)
9.5.4 Throughput Improvement
163(6)
9.6 Concluding Comments
169(2)
10 NNRC: Performance Evaluation
171(32)
10.1 Overview
171(1)
10.2 Network Topology
172(2)
10.3 Scalability
174(6)
10.3.1 Effect of Maximum Queue Length
174(2)
10.3.2 Effect of Propagation Delays
176(2)
10.3.3 Effect of Bandwidth
178(2)
10.4 Dynamic Response of NNRC and FAST TCP
180(8)
10.4.1 Bursty Traffic
182(1)
10.4.2 Re-Routing
183(3)
10.4.3 Non-Constant Number of Sources
186(2)
10.5 NNRC and FAST TCP Interfairness
188(11)
10.6 Synopsis of Results
199(1)
10.7 Concluding Comments
200(3)
11 User QoS Adaptive Control
203(12)
11.1 Overview
203(1)
11.2 Application Adaptation Architecture
204(3)
11.2.1 QoS Mapping
204(1)
11.2.2 Application QoS Control Design
205(2)
11.3 NNRC Source Enhanced with Application Adaptation
207(1)
11.4 Illustrative Example
208(2)
11.4.1 Application Adaptation Implementation Details
209(1)
11.4.2 Simulation Study
210(1)
11.5 Concluding Comments
210(5)
III Appendices
215(58)
A Dynamic Systems and Stability
217(30)
A.1 Vectors and Matrices
217(2)
A.1.1 Positive Definite Matrices
219(2)
A.2 Signals
221(2)
A.3 Functions
223(1)
A.3.1 Continuity
223(1)
A.3.2 Differentiation
224(1)
A.3.3 Convergence
225(1)
A.3.4 Function Properties
226(1)
A.4 Dynamic Systems
227(2)
A.4.1 Stability Definitions
229(2)
A.4.2 Boundedness Definitions
231(1)
A.4.3 Stability Tools
232(15)
B Neural Networks for Function Approximation
247(26)
B.1 General
247(2)
B.2 Neural Networks Architectures
249(1)
B.2.1 Multilayer Perceptron (MLP)
250(2)
B.2.2 Radial Basis Function Networks (RBF)
252(1)
B.2.3 High-Order Neural Networks (HONN)
253(2)
B.3 Off-Line Training
255(2)
B.3.1 Algorithms
257(1)
B.3.1.1 Gradient Algorithms
257(4)
B.3.1.2 Least Squares
261(1)
B.3.1.3 Backpropagation
262(1)
B.4 On-Line Training
263(1)
B.4.1 Filtering Schemes
263(1)
B.4.1.1 Filtered Error
264(1)
B.4.1.2 Filtered Regressor
265(1)
B.4.2 Lyapunov-Based Training
266(1)
B.4.2.1 LIP Case
266(1)
B.4.2.2 NLIP Case
266(1)
B.4.3 Steepest Descent Training
267(1)
B.4.4 Recursive Least Squares Training
268(1)
B.4.5 Robust On-Line Training
269(4)
Bibliography 273(28)
Index 301
Christos N. Houmkozlis is currently in the Department of Electrical and Computer Engineering at Aristotle University of Thessaloniki. His research interests include nonlinear systems, robust adaptive control, modeling and control of communications networks, control over heterogeneous networks, resource management, and pricing in networks.

George A. Rovithakis is Associate Professor in the Department of Electrical and Computer Engineering at Aristotle University of Thessaloniki. His research interests include nonlinear robust adaptive control, neural networks for identification, control of uncertain systems, and control issues arising in computer networks.