Repository logo
  • English
  • 中文
Log In
Have you forgotten your password?
  1. Home
  2. College of Management / 管理學院
  3. Information Management / 資訊管理學系
  4. Efficient Peer-to-Peer Keyword Search Using Adaptive Space Partition
 
  • Details

Efficient Peer-to-Peer Keyword Search Using Adaptive Space Partition

Date Issued
2004
Date
2004
Author(s)
Chen, Po-Hung
DOI
zh-TW
URI
http://ntur.lib.ntu.edu.tw//handle/246246/54267
Abstract
Locating the node that stores a particular data item is a fundamental problem in peer-topeer systems and is traditionally formulated as the construction of a distributed hash table (DHT). Typical DHTs support only a simple map from keys to values, but not keyword search. To support keyword search on a DHT, some distributed inverted index is needed. The challenge is how to evenly distribute the inverted index entries over the peers of the network. Because the keywords frequency in data items is usually of a zipf-distribution, simply partitioning inverted index entries by keywords would cause unbalanced loads. Furthermore, when there are more than one keywords in a query, some intermediate data have to be transmitted across the network and joined with each other to get the final result, incuring much network traffic overhead. We propose a distributed indexing scheme, called Adaptive Space Partition (ASP), that has a good load balancing and incurs little network traffic overhead. The ASP scheme is designed to work on top of the CAN DHT. A CAN network is structured as a d-dimension virtual coordinate space, where each peer node is assigned to a zone in the space. The ASP scheme maps a keyword to a region, consisting of one or more zones. Each object related to a given keyword is inserted into a peer randomly selected from the keyword’s region. To lookup objects related to the same keyword, a peer is randomly selected from the same region as a starting point, which then searches its neighborhood by flooding. Because objects with the same keyword are inserted into the same region, objects have good keyword locality and can be found easily. Furthermore, our scheme partitions inverted index entries according to the number of peers in a region to achieve better scalability. The ASP scheme also optimizes the query operation to have the same complexity as a CAN routing procedure.
Subjects
同儕網路
關鍵字搜尋
keyword search
DHT
p2p
peer-to-peer
Type
other
File(s)
Loading...
Thumbnail Image
Name

ntu-93-R91725035-1.pdf

Size

23.31 KB

Format

Adobe PDF

Checksum

(MD5):ca331202a233f60557d8fcdcf8e34b4e

臺大位居世界頂尖大學之列,為永久珍藏及向國際展現本校豐碩的研究成果及學術能量,圖書館整合機構典藏(NTUR)與學術庫(AH)不同功能平台,成為臺大學術典藏NTU scholars。期能整合研究能量、促進交流合作、保存學術產出、推廣研究成果。

To permanently archive and promote researcher profiles and scholarly works, Library integrates the services of “NTU Repository” with “Academic Hub” to form NTU Scholars.

總館學科館員 (Main Library)
醫學圖書館學科館員 (Medical Library)
社會科學院辜振甫紀念圖書館學科館員 (Social Sciences Library)

開放取用是從使用者角度提升資訊取用性的社會運動,應用在學術研究上是透過將研究著作公開供使用者自由取閱,以促進學術傳播及因應期刊訂購費用逐年攀升。同時可加速研究發展、提升研究影響力,NTU Scholars即為本校的開放取用典藏(OA Archive)平台。(點選深入了解OA)

  • 請確認所上傳的全文是原創的內容,若該文件包含部分內容的版權非匯入者所有,或由第三方贊助與合作完成,請確認該版權所有者及第三方同意提供此授權。
    Please represent that the submission is your original work, and that you have the right to grant the rights to upload.
  • 若欲上傳已出版的全文電子檔,可使用Open policy finder網站查詢,以確認出版單位之版權政策。
    Please use Open policy finder to find a summary of permissions that are normally given as part of each publisher's copyright transfer agreement.
  • 網站簡介 (Quickstart Guide)
  • 使用手冊 (Instruction Manual)
  • 線上預約服務 (Booking Service)
  • 方案一:臺灣大學計算機中心帳號登入
    (With C&INC Email Account)
  • 方案二:ORCID帳號登入 (With ORCID)
  • 方案一:定期更新ORCID者,以ID匯入 (Search for identifier (ORCID))
  • 方案二:自行建檔 (Default mode Submission)
  • 方案三:學科館員協助匯入 (Email worklist to subject librarians)

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science