§ 瀏覽學位論文書目資料
  
系統識別號 U0002-0808201115402500
DOI 10.6846/TKU.2011.00271
論文名稱(中文) 架構於雲端運算系統儲存之動態負載平衡機制
論文名稱(英文) Dynamic Load Balancing Mechanism based on Cloud Computing Storage System
第三語言論文名稱
校院名稱 淡江大學
系所名稱(中文) 電機工程學系碩士在職專班
系所名稱(英文) Department of Electrical and Computer Engineering
外國學位學校名稱
外國學位學院名稱
外國學位研究所名稱
學年度 99
學期 2
出版年 100
研究生(中文) 林益新
研究生(英文) Yih-Sin Lin
學號 797440053
學位類別 碩士
語言別 繁體中文
第二語言別
口試日期 2011-07-14
論文頁數 56頁
口試委員 指導教授 - 吳庭育
委員 - 丁建文
委員 - 朱國志
委員 - 賴槿峰
委員 - 李維聰
關鍵字(中) 雲端計算系統
負載平衡
關鍵字(英) P2P
Cloud system
Load Balance
第三語言關鍵字
學科別分類
中文摘要
由於網路的普及與便利性,讓目前的3C產品都開始具備網路功能以符合使用者的期望,因應這樣的趨勢雲端運算也就因應而生。對於儲存協定,雲端運算也有相當深入的定義;在儲存協定中,檔案的儲存與管理都是藉由第三方的實體儲存設備,並經由集中式的核心伺服器進行整合與分析,將整合的可用資源,依據使用者的需求進行資料傳輸與保存。
依據雲端運算的架構,其涵蓋的範圍相當大,所轄的網域範圍相當多,在這種情境下,多數使用者會因應使用習慣及所擁有資源執行多種重複性儲存行為及存取高相似度資料。假設儲存設備中所讀寫的內容都有著高相似度與重複性,系統管理者將無法確保雲端運算系統中的每一個儲存節點(Peer)都能保持最佳狀態來進行資料整合的工作;並且當節點不斷擴增,其檔案數量則會倍數成長,屆時將造成系統管理者的工作負擔,也會增加硬體資源的浪費,逐漸失去雲端儲存系統的彈性及速度,只剩下龐大及重複的冗餘資料。
    本論文為了避免存取資料高度重複而產生的系統負擔,提出一種新式資料中心管理架構:索引名稱伺服器 (Index Name Server, INS),INS整合了重複資料比對機制以及存取節點選擇最佳化等相關機制來提升整體雲端資料的存取效能。本論文應用INS特有參數來動態監測IP索引資料及忙碌品質等參數,使整體負載達到平衡。避免資料傳輸時,發生長時間排隊或傳輸擁塞發生。經實驗的驗證可以有效提升整體傳輸效能達到20%~50%。
英文摘要
Thanks to the popularity and convenience of networks, almost all 3C products nowadays can connect to the network in accordance with users’ expectation. For this trend, cloud computing takes shape. Cloud computing has defined the storage protocol thoroughly: data storage and management are executed by the physical storage devices of the third party. After the integration and analysis by the centralized server core, available resource and data is transmitted and stored according to user’s needs.
Since the coverage and domain of cloud computing-based architecture are very extensive, according to users’ habits and available resources, most users save and access the data of high similarity. Supposing the data stored in the storage devices is of high duplication and similarity, the system administrator cannot guarantee that every node (peer) in the cloud computing system can maintain the best status for data integration. Moreover, when the number of nodes keeps increasing, the number of files will be multiplied, which results to not only the heavy workload of the system administrator, but also the waste of hardware resources. Finally, the flexibility and quickness of cloud computing system is gone, and what left in the system is big, duplicated and unnecessary data.
    Therefore, in order to avoid the system burden cased by data duplication, we propose a novel data center management structure: Index Name Server, INS, which integrates schemes, like the de-duplication and the optimized access point selection, to enhance the performance of the cloud computing system. In this paper, with the attempt to attain load balancing, we use several specific parameters of INS to dynamically monitor the parameters like IP information and busy quality index. In this way, the network congestion or the long waiting time can be avoided in data transmission. Our experimental result proves that our proposed method can achieve 20% to 50% improvement for transmission performance.
第三語言摘要
論文目次
目    錄
第一章  緒論	- 1 -
1.1	前言	- 1 -
1.2	動機與目的	- 1 -
1.3	論文章節架構	- 3 -
第二章  相關背景研究	- 4 -
2.1	對等式網路(Peer To Peer,P2P)	- 4 -
2.1.1	非固定式結構 (Unstructured)	- 7 -
2.1.2	固定式結構 (Structured)	- 13 -
2.2	分散式雜湊表(Distributed Hash Table)	- 14 -
2.3	雲端運算(Cloud Computing)	- 17 -
2.3.1 雲端概念	- 17 -
2.3.2 雲端負載平衡	- 19 -
第三章  雲端負載平衡最佳化	- 22 -
3.1	索引名稱伺服器 (Index Name Server,INS)	- 23 -
3.2	索引名稱伺服器負載平衡(INS System Balance)	- 27 -
3.2.1	本地備援緩衝	- 40 -
3.2.2	異地備援調節	- 41 -
第四章  模擬環境及結果分析	- 44 -
4.1 實驗環境	- 44 -
4.2 負載對備援節點的影響	- 45 -
4.3 遠端備援的最佳方式	- 47 -
第五章  結論與未來展望	- 53 -
參考文獻	- 54 -
 
圖目錄
圖2.1 傳統網路架構圖	- 5 -
圖2.2 P2P連結示意圖	- 6 -
圖2.3 P2P連結網路	- 7 -
圖2.4 非固定式網路查詢	- 8 -
圖2.5 中央式P2P管理	- 10 -
圖2.6 分散式P2P	- 11 -
圖2.7 複合式架構	- 12 -
圖2.8 分散式雜湊表指定資料示意圖	- 16 -
圖3.1 索引名稱伺服器(Index Name Server,INS)堆疊架構	- 23 -
圖3.2 索引名稱伺服器(Index Name Server,INS)架構	- 24 -
圖3.3 INS 流程	- 26 -
圖3.4 建立資料索引碼(Data Index)	- 29 -
圖3.5 索引碼(Index)表列	- 29 -
圖3.6 路徑權重判斷	- 30 -
圖3.7 路徑品質計算	- 31 -
圖3.8 忙碌參數B(i)動作流程	- 34 -
圖3.9 備援取消判斷流程圖	- 36 -
圖3.10 備援建立判斷流程圖	- 37 -
圖3.11 備援建立示意圖	- 39 -
圖3.12 近端需求備援	- 41 -
圖3.13 具遠端需求備援機制	- 43 -
圖4.1 小區域節點備援效率比較	- 46 -
圖4.2 大區域節點備援效率比較	- 46 -
圖4.3 遠端單個節點備援效率比較	- 48 -
圖4.4 遠端3個節點備援效率比較	- 49 -
圖4.5 遠端5個節點備援效率比較	- 49 -
圖4.6 遠端單個節點備援傳輸成本比較	- 50 -
圖4.7 遠端3個節點備援傳輸成本比較	- 51 -
圖4.8 遠端5個節點備援傳輸成本比較	- 51 -
 
表目錄
表2.1 雲端設備分類表	- 18 -
表3.1 忙碌等級分級表	- 33 -
表4.1 模型環境參數表	- 45 -
參考文獻
[1]	Shufen Zhang, Shuai Zhang, Xuebin Chen, Shangzhuo Wu, “Analysis and Research of Cloud Computing System Instance”, 2010 Second International Conference on Future Networks, 2010
[2]	Tucker, R.S., “Green Optical Communications—Part II: Energy Limitations in Networks”,Selected Topics in Quantum Electronics, IEEE Journal of , March-April 2011, On page(s): 261 - 274,  Volume: 17 Issue: 2
[3]	Mazzariello, C.; Bifulco, R.; Canonico, R.; “Integrating a network IDS into an open source Cloud Computing environment” Information Assurance and Security (IAS), 2010 Sixth International Conference , 23-25 Aug. 2010, on page(s): 265
[4]	Xin Huang ; Tingting Zhang ; Yifan Hou ; “ID management among clouds”, Future Information Networks, 2009. ICFIN 2009. First International Conference on , 14-17 Oct. 2009, on page(s): 237-241
[5]	Cheng-Chia Huang“Analysis of Management Policy for P2P Network Architecture”, Ttatung University,2009
[6]	Frank Dabek,“A Distributed Hash Table”,Massachusetts Institute of Technology Sep. 2005
[7]	Nasri, M.; Sharifi, M.; “Load Balancing using Consistent Hashing: a Real Challenge for Large Scale Distributed Web Crawlers”,Advanced Information Networking and Applications Workshops,2009. WAINA '09. International Conference on,2009,on Page(s): 715 - 720
[8]	Wenzheng Li; Hongyan Shi; “Dynamic Load Balancing Algorithm Based on FCFS”, Innovative Computing, Information and Control (ICICIC),2009 Fourth International Conference on ,2009,on Page(s): 1528 - 1531
[9]	Sun Nian; Liang Guangmin; “Dynamic Load Balancing Algorithm for MPI Parallel Computing”,New Trends in Information and Service Science, 2009. NISS '09. International Conference on,2009,Page(s): 95 - 99
[10]	Shu-Ching Wang; Kuo-Qin Yan; Wen-Pin Liao; Shun-Sheng Wang;“Towards a Load Balancing in a Three-level Cloud Computing Network”, Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on ,Volume: 1,2010, Page(s): 108 - 113
[11]	嚴國慶,王淑卿,王順生,曾莉雅, 陳慶維,“以改良式Min-Min 排程演算法提供動態階層式雲端運算網路拓樸之負載平衡”,2010 年資訊科技國際研討會論文集,2010
[12]	Ananth Rao,Karthik Lakshminarayanan,Sonesh Surana,Richard Karp ,Ion Stoica,“Load Balancing in Structured P2P Systems”, Lecture Notes in Computer Science,2003,Volume 2735/2003,68-79, DOI: 10.1007/978-3-540-45172-3_6. 
[13]	Zhu,Y.; Hu,Y.; “Efficient,Proximity-Aware Load Balancing for DHT-Based P2P Systems”,Parallel and Distributed Systems,IEEE Transactions on Volume: 16,Issue: 4, 2005,Page(s): 349 - 361
[14]	Jiexi Zha; Junping Wang; Renmin Han; Maoqiang Song;  “Research on load balance of Service Capability Interaction Management”, Broadband Network and Multimedia Technology (IC-BNMT), 2010 3rd IEEE International Conference on,2010,Page(s): 212 - 217
[15]	Ruixia Tong; Xiongfeng Zhu; “A Load Balancing Strategy Based on the Combination of static and Dynamic”,Database Technology and Applications (DBTA),2010 2nd International Workshop on,2010,on Page(s): 1 - 4
[16]	Lin Xia; Han-Cong Duan; Xu Zhou; Zhifeng Zhao; Xiao-Wen Nie; “Heterogeneity and Load Balance in Structured P2P Syste” Communications, Circuits and Systems (ICCCAS), 2010 International Conference on 2010,Page(s): 245 - 248
[17]	Yonghui Zhang; Chunhong Zhang; Yang Ji; Wei Mi; “A NOVEL LOAD BALANCING SCHEME FOR DHT-BASED SERVER FARM”,Broadband Network and Multimedia Technology (IC-BNMT), 2010 3rd IEEE International Conference on,2010,on Page(s): 980 - 984
[18]	蕭維廷,“一套兼具負載平衡與區域性的動態階層式點對點網路架構”,國立台灣大學電機工程研究所 碩士論文,2003
[19]	Lu Gao; Min Peng; “Optimal Super peer Selection Based on Load Balance for P2P File-sharing System”,Artificial Intelligence,2009. JCAI '09. International Joint Conference on,2009,Page(s): 92 - 95
[20]	Isaac Keslassy,Cheng-shang Chang,Nick Mckeown,Duan-Shin Lee “Optimal Load-Balancing”,in Proceedings of IEEE Infocom,2005
[21]	翁傳奇,“利用階層式資源分類建立具快速查詢之結構化點對點網路“,朝陽科技大學 資訊工程系碩士班 碩士論文,2006
[22]	楊家華,“在無線隨意網路中尋找符合指定權重之節點群的研究”, 國立台灣科技大學 資訊工程系 碩士論文 ,2004
[23]	陳文村,“分散式點對點網路服務架構之研究”,行政院國家科學委員會專題研究計, 國立清華大學資訊工程學系(所),2004
[24]	李斌豪,“在移動式IPv6網路上一個以時間及距離為基礎的群播演算法”,銘傳大學 資訊管理學系碩士班 碩士論文,2005
[25]	吳庭育,林宗翰,林益新,“架構於綠色雲端運算系統上高效能存取(R/W)系統“,TANET 2010. Taiwan Academic Network Conference,2010
論文全文使用權限
校內
紙本論文於授權書繳交後5年公開
同意電子論文全文授權校園內公開
校內電子論文於授權書繳交後5年公開
校外
同意授權
校外電子論文於授權書繳交後5年公開

如有問題,歡迎洽詢!
圖書館數位資訊組 (02)2621-5656 轉 2487 或 來信