Presentation 2010-07-16
An Adaptive Optimization Method of Data Stream Processing
Taiga ABE, Hideyuki KAWASHIMA, Hiroyuki KITAGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, stream data have been increasing by the development of sensing devices such as sensors, GPS and network cameras. One of the requirements of stream data is to provide persistence for analysis. We focused on providing duplicative persistence, and achieved fast persisting process by optimizing the processing tree. But this method ignore rewriting process that rewrite persisted data to data area. We propose a method that makes persisted data to original result. First we discuss a naive method. The method decreases persistent performance because rewriting process includes disk access. Then we propose a method that rewrites the data without harming persisting process. It is possible to rewrite without harming persisting process by control rewriting processing time. And we prove the effectiveness of proposed method through an experiment. Naive method can't persist data at 5 tuples/sec. On the other hand, proposed method can persist data until 15 tuples/sec.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Stream data Processing / Persistence / Optimization
Paper # USN2010-17
Date of Issue

Conference Information
Committee USN
Conference Date 2010/7/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Ubiquitous and Sensor Networks(USN)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) An Adaptive Optimization Method of Data Stream Processing
Sub Title (in English)
Keyword(1) Stream data Processing
Keyword(2) Persistence
Keyword(3) Optimization
1st Author's Name Taiga ABE
1st Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba()
2nd Author's Name Hideyuki KAWASHIMA
2nd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba:Center of Computer Sciences, University of Tsukuba
3rd Author's Name Hiroyuki KITAGAWA
3rd Author's Affiliation Graduate School of Systems and Information Engineering, University of Tsukuba:Center of Computer Sciences, University of Tsukuba
Date 2010-07-16
Paper # USN2010-17
Volume (vol) vol.110
Number (no) 130
Page pp.pp.-
#Pages 6
Date of Issue