Please use this identifier to cite or link to this item:
標題: 壅塞網路中非響應流的頻寬分配控制
A Novel Approach of Unresponsive Flows Control in a Congested TCP/IP Network
作者: 林清泉
Lin, Ching-Chuan
關鍵字: active queue management;主動式佇列管理;congestion control;bandwidth allocation;virtual queue;壅塞控制;頻寬分配;虛擬佇列
出版社: 資訊科學與工程學系所
引用: [1] W. R. Stevens, “TCP/IP Illustrated, Vol.1: The Protocols,” Addison-Wesley, Reading, Mass. 1994. [2] Mark Parris, Kevin Jeffay, Don Smith, “Responsive vs. Unresponsive Traffic: Active Queue Management for a Better-Than-Best-Effort Service,” [3] S. Floyd and V. Jacobson, “Random Early Detection Gateways for Congestion Avoidance,” IEEE/ACM Trans. Networking, vol.1, No.4, pp.397-413, August 1993. [4] Hsien-Ming Wu, Chin-Chi Wu, Woei Lin, “SF-RED - a Novel Server-based AQM to provide Inter-Server Fairness Service,” in Proc. The Twelfth IEEE International Conference on Parallel and Distributed Systems (ICPADS2006), July 2006. [5] J. Nagle, “Congestion Control in IP/TCP Internetworks,” RFC 896, January. 1984. [6] William Stallings, “High-speed Networks and Internets: Performance and Quality of Service-Second Edition,” Prentice Hall, pp.254-259, 2002. [7] V. Jacobson, “Congestion avoidance and control,” in Proc. ACM SIGCOMM , pp.157-173, January 1995. [8] V. Jacobson, “Modified TCP Congestion Avoidance Algorithm,” end2end-interest mailing list, 20, April 1990. [9] Fall, K. and S. Floyd, “Simulation-based Comparisons of Tahoe, Reno and SACK TCP,” Computer Communication Review, July 1996. [10] S. Floyd, T. Henderson, “The NewReno Modification to TCP's Fast Recovery Algorithm”, RFC 2582, April. 1999. [11] M. Mathis, S. Floyd, A. Romanow, “TCP Selective Acknowledgment Options”, RFC 2018, October. 1996. [12] Lawrence S. Brakmo, Larry L. Peterson, “TCP Vegas: End to End Congestion Avoidance on a Global Internet”, IEEE. Journal on Selected Areas in Communications, Vol. 13, No. 8, Page(s): 1465 ~ 1480, October. 1995. [13] S. Floyd and K. Fall, “Promoting the Use of End-to-End Congestion Control in the Internet,” IEEE/ACM Transactions on Networking, Vol.7, No.4, pp.458-472, August 1999. [14] R. Pan, B. Prabhakar, K. Psounis, “CHOKe: A Stateless Active Queue Management Scheme for Approximating Fair Bandwidth Allocation,” IEEE INFOCOM, Mar 2000. [15] R. Pan, L. Breslau, B. Prabhaker, S. Shenker, “Approximate Fairness Through Differential Dropping,” CCR33(2)23--40, April 2003. [16] B. Braden, D. Clark, J. Crowcroft, B. Davie, S. Deering, D. Estrin, S.Floyd, V. Jacobson, G. Minshall, C. Partridge, L. Peterson, K. Ramakrishnan, S. Shenker, J. Wroclawski, & L. Zhang, “Recommendations on Queue Management and Congestion Avoidance in the Internet,” Internet draft, work in progress, April 1998. [17] S. Floyd, R. Gummadi, S. Shenker, “Adaptive RED: An Algorithm for Increasing the Robustness of RED's Active Queue Management,” , August 2001. [18] Sally Floyd, “RED: Discussions of Setting Parameters,”, 1997. [19] S. Srisankar, R. Kunniyur, “An Adaptive Virtual Queue(AVQ) Algorithm for Active Queue Management,” IEEE/ACM Transactions on Networking, vol.12, No.2, pp.286-299, April 2004. [20] Wu-chang Feng, Kang G. Shin, Dilip D. Kandlur and Debanjan Saha, “The BLUE Active Queue Management Algorithms,” IEEE/ACM Trans. Networking, vol.10 , no. 4 , pp.513-528, August 2002. [21] B. Wydrowski, M. Zukerman, “GREEN: An Active Queue Management Algorithm for a Self Managed Internet,” Proceedings of ICC 2002, New York, vol. 4, pp.2368-2372, 2002. [22] Rajendra K. Jain, Dah-Ming W. Chiu, William R. Hawe, “A Quantitative Measure of Fairness and Discrimination for Resource Allocation in Shared Computer Systems,” September 1984. Eastern Research Report TR-301. [23] P. Pieda, J. Ethridge, “A Network Simulator Differentiated Services Implementation Open IP, Nortel Networks,” July , 2000. [24] S. Floyd, V. Jacobson, “Link Sharing and Resource Management Models for Packet Networks,” IEEE/ACM Trans. Networking, vol.3 , no. 4, pp.513-528, August 1995. [25] A. Habib, B. Bhargava, “Network Tomography-Based Unresponsive Flow Detection and Control,” ftdcs, pp.258, The Ninth IEEE Workshop on Future Trends of Distributed Computing Systems, 2003.
在TCP/IP網路中,使用主動式佇列管理(Active Queue Management, AQM)的控制機制可以降低網路壅塞(congestion),或是提高頻寬使用的效能。當網路發生壅塞時,TCP會反應壅塞控制機制降低傳送端傳輸速率,以控制封包傳送的數量,等到壅塞情況解除後,再開始增加封包的傳輸速率;然而UDP並不會反應壅塞控制機制無法減少封包的傳輸速率。當網路節點同時有TCP的響應流及UDP的非響應流在傳輸時,因UDP的無響應特性會佔用壅塞網路中的使用頻寬,造成頻寬分配公平性的問題。
本論文主要探討非響應流的頻寬分配與公平性問題,我們提出一個新的主動式佇列管理機制稱為UF-RED,可以有效的解決頻寬分配與公平性問題。我們藉由在一個實體佇列中建立多個虛擬佇列(virtual queue)的方法,隔離網路中來自響應流與非響應流的封包,將響應流與非響應流分別以路由器中個別的虛擬佇列加以控制,並依據實際的頻寬使用率動態的調整各個虛擬佇列的封包丟棄機率,我們的方法可以提供更好且更具公平性的頻寬分配控制。

In the TCP/IP network, the use of active queue management (AQM) can mitigate the network congestion and promote the efficiency of bandwidth utilization. In a congested network, a TCP flow, or a responsive flow, will respond to the congestion condition by decreasing its data sending rate until the congestion being controlled. However, on another hand, UDP doesn't respond to such congestion notifications in any way. Under such circumstances, when TCP responsive flows and UDP unresponsive flows coexist in a congested network, the unresponsive nature of UDP flows will dominate the bandwidth allocation of the congested link, and thus will cause the bandwidth allocation fairness problem.
In this thesis, we address the issue of bandwidth allocation fairness problem incurred by unresponsive flows, and proposed a new AQM approach, named UF-RED, to solve the problem. By applying multiple virtual queues onto the original physical one, we isolate unresponsive flows and responsive flows. And, by controlling the drop rate of each virtual queue independently, our approach provides a better and fairer control of bandwidth allocation. We prove that our approach can also promote the efficiency of network bandwidth utilization at the same time.
We use the ns-2 simulator to identify the bandwidth allocation fairness problem and prove the effectiveness of our new approach for solving the problem.
其他識別: U0005-1307200918400000
Appears in Collections:資訊科學與工程學系所

Show full item record
TAIR Related Article

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.