成功大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	黃丞宇 Huang, Cheng-Yu
論文名稱：	在網際網路上達到單點對單點、單點對多點、多點對單點、多點對多點公平分配之研究 Point-to-Point, Point-to-Multipoint, Multipoint-to-Point, Multipoint-to-Multipoint fairness in the Internet
指導教授：	李忠憲 Li, Jung-Shian
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 電機工程學系 Department of Electrical Engineering
論文出版年：	2004
畢業學年度：	92
語文別：	英文
論文頁數：	80
中文關鍵詞：	公平頻寬分配、網際網路、資料段公平分配
外文關鍵詞：	fairness algorithm, internet, session fairness
相關次數：	點閱：110 下載：3
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

　　在現今的網際網路之中，存在著各式各樣的應用程式。而其中有許多應用程式會在多個伺服器與用戶端之間建立含有多條連線的資料段。如此的行為在目前以單一連線為資源分配的基本單位的演算法之下，將會造成不公平的頻寬分配。因為包含較多條連線的資料段將會比包含較少連線的資料段獲得更高的輸出量。除此之外，屬於TCP類型的資料流具有一些會讓前述狀況更加惡化的特性，例如，TCP的輸出量和其對應的RTT成反比以及資源分配亦是以單一連線作為基本的單位等。因此如何有效公平分配頻寬的議題更顯重要。在本篇論文中，我們將從資料段的觀點來探討公平頻寬分配的議題。我們將資料段定義為一群伺服器和客戶端之間建立的點對點連線的集合，而伺服器與客戶端的數目都可能是一個以上。我們提出一個嶄新的分散式架構，而這個架構能夠藉由替不同的資料流指派相對應的權重進而達成四種不同的資料段公平分配機制，而此處所指的資料流可能為某個資料段或使用者的成員。由模擬的結果可以看出，我們的機制能夠讓資料段彼此之間獲得較現存的機制更為公平的頻寬分配，主要的原因是我們以一個考慮到整體性的角度去調整各個資料段所應獲得的頻寬。我們為現行的網路環境提出了一個具伸縮性、可行且實際的公平頻寬分配演算法。

　　In the current Internet, various kind of applications existed. Many of them start sessions with multiple connections between multiple senders and receivers. Such behavior would lead to unfair bandwidth allocation under current per-connection rate allocation methods. Sessions or users with more connections gain a higher throughput than those with fewer connections. In addition, TCP flows have many features which make this situation even worse, such as, throughput is inversely proportional to the round-trip delay and network resources are distributed among flows on a flow basis. Therefore, efficient fair bandwidth allocation is more significant in the high-speed networks. In this thesis, we explore the issue about fair sharing of bandwidth among sessions or users under various connection types. We define a session as a set of point-to-point connections started from server to client, where a user may contain multiple servers or clients. We propose a new distributed architecture which can achieve separate fairness definitions by assigning corresponding weight for flows, which represent the member connections of a session, or a user. Simulation results show that our scheme can achieve a fairer distribution of rates than the existing connection fair algorithms, through redistributing the rates of sessions or users with more connections in a global point of view. We present a scalable, feasible and practical fairness algorithm for the Internet.

Introduction...........................1
1 Network Overview ...........................1
2 Motivation for the thesis...........................3
3 Organization...........................6
Related Work...........................7
1 Point-to-Multipoint Fairness Approaches...........................7
1.1 User Fair Queuing...........................7
1.2 ABR Point-to-Multipoint Connections in ATM Networks...........................9
2.3 Multirate multicast scenario...........................10
2 Multipoint-to-Point Fairness Approaches...........................10
2.1 Multipoint-to-Point Session Fairness in the Internet...........................10
2.1 Receiver-Driven Bandwidth Sharing for TCP...........................11
2.3 Fairness for ABR Multpoint-to-Point Connection...........................12
Discussion of Fairness Issues...........................13
1 Concept of Resource Allocation...........................13
2 Definition of Fairness Units...........................14
3 Basic Fairness Definition...........................15
3.1 User Fairness...........................15
3.2 Session Fairness...........................16
3.3 Connection Fairness...........................17
Definitions of Fairness...........................19
1 Existing Definitions of Fairness...........................20
1.1 Max-min Fairness(Connection Fairness)...........................21
1.2 TCP Allocation...........................21
2 Normalized Weighted Max-Min Fairness...........................22
3 Fairness Extension for Various Connection Type...........................23
3.1 Point-to-Point Fairness...........................24
3.2 Point-to-Multipoint Fairness...........................24
3.2.1 Source-based...........................24
3.2.2 Session-based...........................25
3.3 Multipoint-to-Point Fairness...........................26
3.3.1 Destination-based...........................26
3.3.2 Session-based...........................27
3.4 Multipoint-to-Multipoint Fairness...........................28
3.4.1 Session-based...........................28
4 Comparison of Different Fairness Allocation...........................29
4.1 Example Allocation 1...........................29
4.2 Example Allocation 2...........................33
Rate Control with Normalized Weight Assignment......................36
1 Estimation of Total Flow weight........................37
2 ICMP Contorl Message...........................40
3 Architecture of RCNWA...........................41
3.1 Source Operation...........................43
3.2 Router Operation...........................44
3.3 Destination Operation...........................47
Simulation Results...........................49
1 Simulation Model...........................50
2 Performance Metrics...........................51
3 Single Session-Per Node...........................52
3.1 Network Configuration...........................52
3.2 Sender Fairness...........................54
3.3 Receiver Fairness...........................58
3.4 Convergence Time...........................62
3.5 Summary of the Simulation Result...........................63
4 Multisession-Per Node...........................64
4.1 Network Configuration...........................65
4.2 Session Rate Fairness...........................66
4.3 Summary of the Simulation Result...........................69
5 Various Session Types Coexist in the network...........................70
5.1 Network Configuration...........................70
5.2 Session Fairnss...........................71
5.3 Convergence Time...........................73
6 Inter-session Differentiation...........................75
Conclusion and Future Work...........................77
References...........................79

                                    

[1] D. Bertsekas and R. Gallager, Data Networks, chapter 6, pp.524-529, Prentice-Hall,1987.

[2] B. Krishnamurthy, C. Wills, and Y. Zhang, “On the Use and Performance of Content Distribution Networks,” in Proceedings of ACM SIGCOMM Internet Measurement Workshop, 2001.

[3] J. Padhye, V. Firoiu, D. Towsley, J. Kurose, “Modeling TCP Throughput: A Simple Model and its Empirical Validation”, in proceedings of ACM SIGCOM,1998.

[4] A. Charny, David D. Clark, and R. Jain, “Congestion control with explicit rate indication”, In Proceedings of the IEEE International Communications Conference, June 1995.

[5] P. Rodriguez, A. Kirpal, and E. Biersack, “Parallel-Access for Mirror Sites in the Internet,” in Proceedings of INFOCOM, 2000.

[6] S. Fahmy, R. Jain, R. Goyal, and B. Vandalore, “Fairness for ABR Multipoint-to-point Connections,” Proceedings of SPIE Symposium on Voice, Video and Data Communications, November 1998.

[7] A. Banchs, “User Fair Queueing: Fair Allocation of Bandwidth for Users,” in Proceedings of IEEE INFOCOM, 2002.

[8] J. Ros, and W. K. Tsai, “A Theory of Convergence order of max-min rate allocation and an optimal protocol,” in Proceedings of IEEE INFOCOM, 2001.

[9] P. Mehra, A. Zakhor, and C. D. Vleeschouwer, “Receiver-Driven Bandwidth Sharing for TCP”, in Proceedings of IEEE INFOCOM, 2003.

[10] L. Benmohamed, and S. M. Meerkov, “Feedback Control of Congestion in Packet Switching Networks: The Case of Single Congested Node”, IEEE/ACM Transactions on Networking, December 1993.

[11] Mustafa A.A, Hassan M, and Jha S, “Design and Performance Evaluation of a Rate Feedback Control Architecture for TCP/IP Networks”, Computing, and Communications Conference, 2002. 21st IEEE International, 2002.

[12] J. Postel, “Internet Control Message Protocol”, IETF RFC 792, September 1981.

[13] B. Bloom. Space/time Trade-offs in Hash Coding with Allowable Errors. Communications of the ACM, July 1970.

[14] C. Estan, George Varghese, and Mike Fisk, “Bitmap algorithms for counting active flows on high speed links”, UCSD technical report CS2003-0738, March 2003.

[15] http://www.isi.edu/nsnam/ns/

[16] Shakkottai, Sanjay and Kumar, Anurag and Karnik, Aditya and Anvekar, “TCP performance over end-to-end rate control and stochastic available capacity”, IEEE/ACM Transactions on Networking, August 2001.

[17] P. Karbhari, E. Zegura, M. Ammar, “Multipoint-to-Point Session Fairness in the Internet,” in Proceedings of IEEE INFOCOM, 2003.

[18] The ATM Forum. The ATM Forum traffic management specification version 4.0 ftp://ftp.atmforum.com/pub/approved-specs/af-tm-0056.000.ps, April 1996.

[19] S. Fahmy, R. Jain, R. Goyal, B. Vandalore, S. Kalyanaraman, S. Kota, and P. Samudra, “Feedback Consolidation Algorithms for ABR Point-to-Multipoint Connections in ATM Networks,” in Proceedings of IEEE INFOCOM 1998.

[20] S. McCanne and V. Jacobson, “Receiver-driven Layered Multicast,” in Proceedings of ACM SIGCOMM, 1996

校內：2005-07-15公開
校外：2005-07-15公開

簡易檢索 / 詳目顯示

相關論文