Title

企業導入雲端運算之影響-以Hadoop為例

Translated Titles

The Corporate Effect of Implementing Cloud Computing : A Case Study of Using Hadoop

Authors

李虔銘

Key Words

Hadoop ; 巨量資料 ; 雲端運算 ; Hadoop ; Big Data ; Cloud Computing

PublicationName

中原大學資訊管理研究所學位論文

Volume or Term/Year and Month of Publication

2015年

Academic Degree Category

碩士

Advisor

廖秀莉

Content Language

繁體中文

Chinese Abstract

目前雲端運算無疑是企業用來因應巨量資料需求的主要投資項目之一,而且在像 Facebook、Yahoo 這些大企業都宣稱自己在應用雲端運算來處理巨量資料分析上有相當良好的成效,這亦使得之後面臨巨量資料問題的企業起而效尤。大企業在傳統大型主機的運作上都遇到了速度、規模與成本的問題,所以,擁有處理巨量數據工具的分散式運算平台Hadoop即應運而生。 本研究嘗試提出一個企業運用雲端運算能在降低成本的情況下,還可以在巨量資料下保有良好的效能及橫向擴充的彈性。本研究實驗測試企業常見之高階單一伺服器硬體與雲端運算中低階雲端技術架構,實驗結果顯示雲端運算架構對於巨量檔案的資料處理,較高階單一伺服器具有優秀的運作效能。

English Abstract

Undoubtedly, the Cloud Computing is prime investment projects for big data request used in the enterprise. The Facebook and the Yahoo, these big companies have proclaimed to get great effects on Big data analysis by used Cloud Computing, for this reason, the other companies when is forced with problem of big data are imitate. Enterprise have got speed, scope and cost problem on the traditions large-sized operation system, so, Hadoop was born for new distributed computing environment to analyze big data. Large enterprises in the operation of the traditional mainframes have encountered speed, size and cost, it has a huge amount of data processing tools for Hadoop distributed computing platform that is born. This study tries to put forward a business can use cloud computing to reduce costs in the case, still able to maintain good performance and horizontal expansion of elasticity at big data. In this study, experimental tests of high-end enterprise single common server hardware and low-level cloud computing in the cloud technology architecture, experimental results show that cloud computing architecture for data processing, higher-order single massive archive server has an excellent operational efficiency.

Topic Category 商學院 > 資訊管理研究所
社會科學 > 管理學
Reference
  1. 1.黃獻輝,雲端運算於企業應用之研究,淡江大學,資訊管理學系碩士論文。
    連結:
  2. 3.陳建良、楊朝龍、林純如,2014,巨量資料於製造業之應用機會,先進工程學刊,第九卷第三期。
    連結:
  3. 10.Dhruba, B., "The Hadoop Distributed File System: Architecture and Design,"
    連結:
  4. 12.陳伯文,2001,代理人架構下分散式平行運算平台之設計與建構,元智大學,資訊管理學系碩士論文。
    連結:
  5. 2.林東清,2007,資訊管理的科技觀點 - 資訊管理,台灣:智勝。
  6. 4.開放原始碼促進協會(Open Source Initiative, OSI) : http://www.opensource.org
  7. 5.美國國家標準與技術研究院(National Institute of Standards and Technology, NIST) : http://www.nist.gov
  8. 6.鄭守成,1996,漫談平行電腦與平行計算,國家高速電腦中心,高速計算世界,第七卷第四期。
  9. 7.http://en.wikipedia.org/wiki/Big_data
  10. 8.http://hadoop.apache.org/
  11. 9.White, Tom ,”Hadoop: The Definitive Guide”, O'Reilly Media,10 May 2012
  12. 11.王佩玉,2001,分散式平行計算環境之負載分配,義守大學,資訊工程研究所碩士論文。