Th`ese de Doctorat de l'université Paris VI Pierre et Marie Curie Mlle ...

More documents

Recommendations

Info

7.1 Performance Metrics We consider the following performance metrics: the average accepted load and network extra-revenue. The average accepted load is obtained averaging the total load accepted in the network over all the bandwidth update intervals, while the average network extra-revenue has been defined in Section 4.3. We recall, hereafter, the definition of network extra-revenue: where srk and b n k Uk(b n k) − Uk(srk) k∈Kg represent, respectively, the subscribed rate and the average transmission rate in the n − th update interval for all greedy connections k ∈ Kg, andUk(x) modelsthe perceived utility of the k − th user for an allocation of x bandwidth units. 7.2 Network Scenarios We refer to four network scenarios ranging from a single-bottleneck topology to a complex core network topology to evaluate the performance of our proposed bandwidth allocation algorithms. All numerical results have been calculated over long-lived data exchanges, achieving very narrow 95% confidence intervals [36]. 7.2.1 Single-Bottleneck Scenario In this scenario we gauge the effectiveness of the proposed traffic-based bandwidth allocation algorithms. We consider, in line with [1, 2], the scenario illustrated in Figure 7.1, that consists of a single-bottleneck with 2 core nodes, 6 access nodes, 40 end nodes (20 source-destination pairs) and traffic conditioners at the edge. Each ingress conditioner is configured with one profile for each traffic source, and drops out-of-profile packets. All links are full-duplex and have a propagation delay of 1 ms. The capacity of the link connecting 56
the two core nodes is equal to 6 Mb/s, that of the links connecting the access nodes to core nodes is equal to 10 Mb/s, and that of the links connecting the end nodes to access nodes is 2 Mb/s. The buffer size of each link can contain 50 packets. Sources Destinations 2 Mb/s 10 Mb/s 6 Mb/s 1 2 Figure 7.1: Network topology with a single bottleneck We use 20 Exponential On-Off traffic sources; the average On time is set to 200 s, and the average Off time is varied in the 0 to 150 s range to simulate different traffic load conditions while varying at the same time the percentage of bandwidth left unused by every connection. During On times each source transmits with a constant rate that we refer to hereafter as the source’s peak rate. Six sources have a peak rate of 50 kb/s and a subscribed rate of 150 kb/s, 8 sources have a peak rate of 250 kb/s and a subscribed rate of 200 kb/s, while the remaining six sources have a peak rate of 1 Mb/s and a subscribed rate of 500 kb/s; the minimum bandwidth required by each source, r mink, is equal to 10 kb/s. The algorithm updating interval, Tu, is set to 20 s and γ is set to 0.9. We assume, for simplicity, that all users have the same weight wk and the same type of 57
Page 1 and 2:
Thèse de Doctorat de l’universit
Page 3 and 4:
To my family.
Page 5 and 6:
Abstract Efficient dynamic resource
Page 7:
Acknowledgements I would like to th
Page 10 and 11:
4.2 Connections Classification . .
Page 13 and 14:
Résumé delaThèse 1. La probléma
Page 15 and 16:
supérieure sur les performances qu
Page 17 and 18: compte les fonctions d’utilité d
Page 19 and 20: (Policy Decision Point), d’un ens
Page 21 and 22: ligne pour individualiser la bande
Page 23 and 24: 6. Nous proposons trois algorithmes
Page 25 and 26: appelons débit de crête. Six sour
Page 27 and 28: 6. Conclusion générale et Perspec
Page 29 and 30: Chapter 1 Introduction The Internet
Page 31 and 32: upper bounds to the performance ach
Page 33 and 34: Chapter 2 Dynamic Bandwidth Allocat
Page 35 and 36: Utility Function Types In a multi-a
Page 37 and 38: comes smaller than the application
Page 39 and 40: of which there exist extensive theo
Page 41 and 42: allows us to allocate the bandwidth
Page 43: Shenker in [10] states that the net
Page 46 and 47: implements such service model by pe
Page 48 and 49: considering different constraints l
Page 50 and 51: 4.1 Problem Statement Let us model
Page 52 and 53: y all network users. Using the nota
Page 54 and 55: in the following Section. The struc
Page 56 and 57: Optimum Bandwidth Allocation Algori
Page 58 and 59: Table 5.1: Pseudo-code specificatio
Page 60 and 61: of all greedy connections that are
Page 63 and 64: Chapter 6 Mathematical Model This C
Page 65 and 66: 1 2 3 4 0000000000 1111111111 00000
Page 67: Chapter 7 Numerical Results The mai
Page 71 and 72: Total Accepted Load (Mb/s) 6 5.5 5
Page 75 and 76: plottedinFigure7.9. Figures 7.10 an
Page 77 and 78: Total Accepted Load (Mb/s) 6 5 4 3
Page 79 and 80: S 2 S 3 S 4 1 S 6 S1 S5 2 3 4 5 D 1
Page 81 and 82: high network loads, where it achiev
Page 83 and 84: proposed allocation algorithms in a
Page 85 and 86: Table 7.3: Peak rate, subscribed ra
Page 87 and 88: Chapter 8 Performance Upper Bound T
Page 89 and 90: Table 8.1: Average performance gain
Page 93 and 94: Total Accepted Load (Mb/s) 6 5 4 3
Page 95 and 96: Chapter 9 Conclusion 9.1 Discussion
Page 97: established by creating a session i
Page 100 and 101: [7] F. P. Kelly, “Charging and ra
Page 102 and 103: [26] P. Reichl, S. Leinen, and B. S
Page 105 and 106: Appendix A Algorithm Implementation
Page 107 and 108: these latters are implemented using
Page 109 and 110: • boolean State: the connection s
Page 111 and 112: (CSTtable) is updated by the ingres
Page 113 and 114: Table A.2: Java code for updating t
Page 115 and 116: List of Acronyms ACA Autonomous Com
Page 117 and 118: List of Figures 1 Notre architectur
Page 119 and 120:
8.1 Performance upper bound for all
Page 121:
List of Tables 5.1 Pseudo-code spec
show all

Th`ese de Doctorat de l'université Paris VI Pierre et Marie Curie Mlle ...

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?