Optimizing in-order execution of continuous queries over streamed sensor data

Moustafa A. Hammad, Walid G. Aref, Ahmed Elmagarmid

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

In this paper we study the problem of providing ordered execution of time-based sliding window queries over input streams of sensor data with inherent delays. We present three approaches to achieve the ordered execution. The first approach enforces ordered processing at the input side of the query execution plan. In the second approach we utilize the advantage of out-of-order execution to optimize query operators and enforce an ordered release of the output results. The third approach is adaptive and switches between the first and second approaches to achieve the best overall performance with current input arrival rates and level of multiprogramming. We study the performance of the proposed approaches both analytically and experimentally while using various system configurations. Our performance study is based on an extensive set of experiments using a realization of the proposed approaches in Nile, a prototype stream query processing system.

Original languageEnglish
Title of host publicationProceedings of the International Conference on Scientific and Statistical Database Management, SSDBM
Pages143-146
Number of pages4
Publication statusPublished - 2005
Externally publishedYes
Event17th International Conference Scientific and Statistical Database Management, SSDBM 2005 - Santa Barbara, CA, United States
Duration: 27 Jun 200529 Jun 2005

Other

Other17th International Conference Scientific and Statistical Database Management, SSDBM 2005
CountryUnited States
CitySanta Barbara, CA
Period27/6/0529/6/05

Fingerprint

Multiprogramming
Query processing
Switches
Sensors
Processing
Experiments

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Hammad, M. A., Aref, W. G., & Elmagarmid, A. (2005). Optimizing in-order execution of continuous queries over streamed sensor data. In Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM (pp. 143-146)

Optimizing in-order execution of continuous queries over streamed sensor data. / Hammad, Moustafa A.; Aref, Walid G.; Elmagarmid, Ahmed.

Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM. 2005. p. 143-146.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hammad, MA, Aref, WG & Elmagarmid, A 2005, Optimizing in-order execution of continuous queries over streamed sensor data. in Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM. pp. 143-146, 17th International Conference Scientific and Statistical Database Management, SSDBM 2005, Santa Barbara, CA, United States, 27/6/05.
Hammad MA, Aref WG, Elmagarmid A. Optimizing in-order execution of continuous queries over streamed sensor data. In Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM. 2005. p. 143-146
Hammad, Moustafa A. ; Aref, Walid G. ; Elmagarmid, Ahmed. / Optimizing in-order execution of continuous queries over streamed sensor data. Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM. 2005. pp. 143-146
@inproceedings{8c348a2176e74b95a9806fa7879f0a7c,
title = "Optimizing in-order execution of continuous queries over streamed sensor data",
abstract = "In this paper we study the problem of providing ordered execution of time-based sliding window queries over input streams of sensor data with inherent delays. We present three approaches to achieve the ordered execution. The first approach enforces ordered processing at the input side of the query execution plan. In the second approach we utilize the advantage of out-of-order execution to optimize query operators and enforce an ordered release of the output results. The third approach is adaptive and switches between the first and second approaches to achieve the best overall performance with current input arrival rates and level of multiprogramming. We study the performance of the proposed approaches both analytically and experimentally while using various system configurations. Our performance study is based on an extensive set of experiments using a realization of the proposed approaches in Nile, a prototype stream query processing system.",
author = "Hammad, {Moustafa A.} and Aref, {Walid G.} and Ahmed Elmagarmid",
year = "2005",
language = "English",
pages = "143--146",
booktitle = "Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM",

}

TY - GEN

T1 - Optimizing in-order execution of continuous queries over streamed sensor data

AU - Hammad, Moustafa A.

AU - Aref, Walid G.

AU - Elmagarmid, Ahmed

PY - 2005

Y1 - 2005

N2 - In this paper we study the problem of providing ordered execution of time-based sliding window queries over input streams of sensor data with inherent delays. We present three approaches to achieve the ordered execution. The first approach enforces ordered processing at the input side of the query execution plan. In the second approach we utilize the advantage of out-of-order execution to optimize query operators and enforce an ordered release of the output results. The third approach is adaptive and switches between the first and second approaches to achieve the best overall performance with current input arrival rates and level of multiprogramming. We study the performance of the proposed approaches both analytically and experimentally while using various system configurations. Our performance study is based on an extensive set of experiments using a realization of the proposed approaches in Nile, a prototype stream query processing system.

AB - In this paper we study the problem of providing ordered execution of time-based sliding window queries over input streams of sensor data with inherent delays. We present three approaches to achieve the ordered execution. The first approach enforces ordered processing at the input side of the query execution plan. In the second approach we utilize the advantage of out-of-order execution to optimize query operators and enforce an ordered release of the output results. The third approach is adaptive and switches between the first and second approaches to achieve the best overall performance with current input arrival rates and level of multiprogramming. We study the performance of the proposed approaches both analytically and experimentally while using various system configurations. Our performance study is based on an extensive set of experiments using a realization of the proposed approaches in Nile, a prototype stream query processing system.

UR - http://www.scopus.com/inward/record.url?scp=38049063405&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38049063405&partnerID=8YFLogxK

M3 - Conference contribution

SP - 143

EP - 146

BT - Proceedings of the International Conference on Scientific and Statistical Database Management, SSDBM

ER -