Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/133893
|
| Title: | 壅塞最小化：透過網路流分類與簡化健忘路由
Congestion Minimization by Flow Classification and Simplified Oblivious Routing |
| Authors: | 張筆翔
Chang, Pi-Hsiang |
| Contributors: | 郭桐惟
Kuo, Tung-Wei
張筆翔
Chang, Pi-Hsiang |
| Keywords: | 壅塞程度
軟體定義網路
線性規劃
大象流
健忘路由
Network congestion
Software-defined networks
Linear programming
Elephant flow
Oblivious routing |
| Date: | 2020 |
| Issue Date: | 2021-02-01 14:10:22 (UTC+8) |
| Abstract: | 為維持良好的網路服務品質及增加線路損壞後回復的可能性，網管人員需要盡可能地降低網路壅塞程度。另一方面，由於使用者的需求變化迅速，我們需要透過軟體定義網路即時地設定網路路由以即時降低壅塞程度。一般而言，最小化網路壅塞程度的網路路由設定可以透過線性規劃求得。然而，隨著拓樸規模增加，線性規劃的計算時間也會快速增加。為了減少計算時間，本論文區分大象流及老鼠流，並對兩者做不同的處理方式。更明確地說，我們對大象流使用線性規劃取得最小化壅塞程度的路徑規劃，並透過簡化版的健忘路由取得老鼠流的網路路由路徑。我們使用Fat tree、VL2、Bcube及Rocketfuel所提供的電信網路拓樸來進行實驗，其中在Fat tree網路中，我們的方法不僅可以有效地減少計算時間（計算時間為原有計算時間的10%），同時保持近乎最佳解的網路壅塞程度（網路壅塞程度為最佳解的1.004倍）。
In order to maintain good service quality and increase the possibility of recovery after link failures, network administrators need to reduce network congestion as much as possible. On the other hand, due to the rapid changes in user needs, we need to set up network routing through software-defined networks to reduce congestion in real time. In general, network routing settings that minimize network congestion can be obtained through linear programming. However, as the scale of the topology increases, the calculation time of linear programming also increases rapidly. In order to reduce the calculation time, this thesis distinguishes elephant flows and mouse flows, and treats the two in different ways. More specifically, we apply linear programming on elephant flows to minimize network congestion, and obtain network routing paths of mouse flows through a simplified version of oblivious routing.
We do experiments under Fat trees, VL2s, Bcubes and the telecommunication network topologies provided by Rocketfuel. Results show that under Fat trees, our method can not only effectively reduce the calculation time (the resulting calculation time is only 10% of the original calculation time), while maintaining near-optimal network congestion (the resulting network congestion is only 1.004 times the optimum). |
| Reference: | 參考文獻
[1] Kashif Bilal Samee U. Khan Limin Zhang Hongxiang Li Khizar Hayat Sajjad A. Madani Nasro Min‐Allah Lizhe Wang Dan Chen Majid Iqbal Cheng‐Zhong Xu Albert Y. Zomaya, “Quantitative comparisons of the state‐of‐the‐art data center architectures,” 20 December 2012. [線上]. Available: https://doi.org/10.1002/cpe.2963.
[2] E. Mannie, “Generalized Multi-Protocol Label Switching (GMPLS) architecture,” 10 2004.
[3] N. McKeown, “Software-defined networking,” INFOCOM keynote talk, pp. 30-32, 4 2009.
[4] Nick McKeown,Tom Anderson,Hari Balakrishnan,Guru Parulkar,Larry Peterson,Jennifer Rexford,Scott Shenker,Jonathan Turner, “OpenFlow: enabling innovation in campus networks,” ACM SIGCOMM Computer Communication Review, pp. 69-74, 4 2008.
[5] S. Vissicchio, O. Tilmans, L. Vanbever and J. Rexford, "Central control over distributed routing," in In: ACM SIGCOMM Computer Communication Review. ACM, 2015.
[6] C.-Y. Hong, S. Kandula, R. Mahajan, M. Zhang, V. Gill, M. Nanduri and R. Wattenhofer, "Achieving High Utilization with Software-Driven WAN," in ACM Special Interest Group on Data Communication (SIGCOMM), 2013.
[7] Fahimeh Alizadeh Moghaddam,Paola Grosso, “Linear programming approaches for power savings in software-defined networks,” IEEE NetSoft Conference and Workshops (NetSoft), 2016.
[8] Apostolos Destounis ,Stefano Paris,Lorenzo Maggi,Georgios S. Paschos,Jérémie Leguay, “Minimum Cost SDN Routing With Reconfiguration Frequency Constraints,” IEEE/ACM Transactions on Networking, pp. 1577-1590, 8 2018.
[9] Danda B. Rawat , Chandra Bajracharya, “Software Defined networking for reducing energy consumption and carbon emission,” SoutheastCon, 2016.
[10] Seungbeom Song , Jaiyong Lee , Kyuho Son , Hangyong Jung , Jihoon Lee, “A congestion avoidance algorithm in SDN environment,” International Conference on Information Networking (ICOIN), 2016.
[11] Jaehyun Hwang,Joon Yoo,Sang-Hun Lee,Hyun-Wook Jin, “Scalable Congestion Control Protocol based on SDN in Data Center Networks,” IEEE Global Communications Conference (GLOBECOM), pp. 1-6, 12 2015.
[12] Y Guo, Z Wang, X Yin, X Shi, J Wu, “Traffic engineering in hybrid SDN networks with multiple traffic matrices,” 於 Computer Networks, 2017, pp. 187-199.
[13] Tao Hu ,Zehua Guo, Peng Yi ,Thar Baker , Julong Lan, “Multi-controller Based Software-Defined Networking: A Survey,” IEEE Access ( Volume: 6 ), pp. 15980 - 15996, 2018.
[14] Othmane Blial, Mouad Ben Mamoun, and Redouane Benaini, “An Overview on SDN Architectures with Multiple Controllers,” 2016. [線上]. Available: http://dx.doi.org/10.1155/2016/9396525.
[15] David Applegate , Edith Cohen, “Making Routing Robust to Changing Traffic Demands: Algorithms and Evaluation,” IEEE/ACM Transactions on Networking, pp. 1193-1206, 12 2006.
[16] Liu, Jing; Li, Jie; Shou, Guochu; Hu, Yihong; Guo, Zhigang; Dai, Wei, “SDN based load balancing mechanism for elephant flow in data center networks,” International Symposium on Wireless Personal Multimedia Communications (WPMC), pp. 486-490, 2014.
[17] Xiao, Peng; Qu, Wenyu; Qi, Heng; Xu, Yujie; Li, Zhiyang, “An efficient elephant flow detection with cost-sensitive in SDN,” 於 2015 1st International Conference on Industrial Networks and Intelligent Systems (INISCom), Tokyo, 2015.
[18] Albert Greenberg,James R. Hamilton,Navendu Jain,Srikanth Kandula,Changhoon Kim,Parantap Lahiri,David A. Maltz,Parveen Patel,Sudipta Sengupta, “VL2: a scalable and flexible data center network,” ACM SIGCOMM Computer Communication Review, 8 2009.
[19] M. Al-Fares, A. Loukissas, A. Vahdat, “A scalable, commodity data center network architecture,” SIGCOMM, 2008.
[20] C. Guo, H.Wu, K. Tan, L. Shiy, Y. Zhang, S. Lu, “Bcube: A high performance, server-centric network architecture for modular data centers.,” SIGCOMM, 2009.
[21] Tung-Wei Kuo, Bang-Heng Liou, Kate Ching-Ju Lin,Ming-Jer Tsai, “Deploying Chains of Virtual Network Functions:On the Relation Between Link and Server Usage,” IEEE/ACM Transactions on Networking, pp. 1562-1576, 8 2018.
[22] Piotr Jurkiewicz, Grzegorz Rzym, Piotr Boryło, “Flow length and size distributions in campus Internet traffic,” arXiv:1809.03486, 2018.
[23] X. Li , C. Qian, “Low-complexity multi-resource packet scheduling,” in IEEE Conference on Computer Communications (INFOCOM), pp. 1400-1408, 2015. |
| Description: | 碩士
國立政治大學
資訊科學系
106753038 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0106753038 |
| Data Type: | thesis |
| DOI: | 10.6814/NCCU202100161 |
| Appears in Collections: | [資訊科學系] 學位論文
|
Files in This Item:
| File |
Description |
Size | Format | |
|---|
| 303801.pdf | | 4445Kb | Adobe PDF2 | 0 | View/Open |
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
