東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Managing large scale distributed dat...

Zhang, Chi.

FindBook

Google Book

Amazon

博客來

Managing large scale distributed data with peer-to-peer search trees.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Managing large scale distributed data with peer-to-peer search trees./
作者:	Zhang, Chi.
面頁冊數:	149 p.
附註:	Source: Dissertation Abstracts International, Volume: 68-01, Section: B, page: 0414.
Contained By:	Dissertation Abstracts International68-01B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3250045

Managing large scale distributed data with peer-to-peer search trees.
Zhang, Chi.

Managing large scale distributed data with peer-to-peer search trees. - 149 p.

Source: Dissertation Abstracts International, Volume: 68-01, Section: B, page: 0414.

Thesis (Ph.D.)--Princeton University, 2007.

Massive data sets have been increasingly shared by distributed users following the success of broad-band Internet services. Indexing and complex queries are essential for such data collections in applications like multimedia retrieval, data mining, and spatial databases. Traditional service infrastructures rely on centralized management and query processing. This approach does not scale with the rapidly increasing amount of application data available on massively distributed systems like the Internet. In recent years, peer-to-peer computing has emerged as a promising model for building large, scalable systems. A number of peer-to-peer systems have been proposed by the research community, typically taking the form of Distributed Hash Tables (DHT). Such systems provide excellent scalability and resilience for storage applications. However, they do not provide complex query capabilities beyond exact matching. This thesis proposes Brushwood, a peer-to-peer infrastructure for building distributed search trees to support complex queries. Users define how their tree nodes handle index queries and insertion requests. The execution of query/insertion operations and maintenace of the search tree are implemented by Brushwood infrastructure, which guarantees logarithmic cost with decentralized tree navigation and maintenance, even in the face of skewed data sets and unbalanced tree structures. The platform is flexible to support diversified applications. I present two examples in this thesis: an index service for high dimensional data, and a content-based publish/subscribe system. The high-dimensional index supports range queries and nearest neighbor search based on Brushwood tree navigation. The publish/subscribe system supports complex sementics for matching dynamic events to user subscriptions. They use significantly different index structures built upon the same Brushwood platform. Experimental results demonstrated the versatility and scalability of the systems.Subjects--Topical Terms:

626642
Computer Science.

Managing large scale distributed data with peer-to-peer search trees.
LDR:02824nmm 2200253 4500 001 1835361
005 20071217104326.5
008 130610s2007 eng d
035 $a (UMI)AAI3250045
035 $a AAI3250045
040 $a UMI $c UMI
100 1 $a Zhang, Chi. $3 1033852
245 1 0 $a Managing large scale distributed data with peer-to-peer search trees.
300 $a 149 p.
500 $a Source: Dissertation Abstracts International, Volume: 68-01, Section: B, page: 0414.
500 $a Adviser: Jaswinder Pal Singh.
502 $a Thesis (Ph.D.)--Princeton University, 2007.
520 $a Massive data sets have been increasingly shared by distributed users following the success of broad-band Internet services. Indexing and complex queries are essential for such data collections in applications like multimedia retrieval, data mining, and spatial databases. Traditional service infrastructures rely on centralized management and query processing. This approach does not scale with the rapidly increasing amount of application data available on massively distributed systems like the Internet. In recent years, peer-to-peer computing has emerged as a promising model for building large, scalable systems. A number of peer-to-peer systems have been proposed by the research community, typically taking the form of Distributed Hash Tables (DHT). Such systems provide excellent scalability and resilience for storage applications. However, they do not provide complex query capabilities beyond exact matching. This thesis proposes Brushwood, a peer-to-peer infrastructure for building distributed search trees to support complex queries. Users define how their tree nodes handle index queries and insertion requests. The execution of query/insertion operations and maintenace of the search tree are implemented by Brushwood infrastructure, which guarantees logarithmic cost with decentralized tree navigation and maintenance, even in the face of skewed data sets and unbalanced tree structures. The platform is flexible to support diversified applications. I present two examples in this thesis: an index service for high dimensional data, and a content-based publish/subscribe system. The high-dimensional index supports range queries and nearest neighbor search based on Brushwood tree navigation. The publish/subscribe system supports complex sementics for matching dynamic events to user subscriptions. They use significantly different index structures built upon the same Brushwood platform. Experimental results demonstrated the versatility and scalability of the systems.
590 $a School code: 0181.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 0 $a Princeton University. $3 645579
773 0 $t Dissertation Abstracts International $g 68-01B.
790 1 0 $a Singh, Jaswinder Pal, $e advisor
790 $a 0181
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3250045