Abstract

Most existing approaches to complex event processing over streaming data rely on the assumption that the matches to the queries are rare and that the goal of the system is to identify these few matches within the incoming deluge of data. In many applications, such as user credit card purchase pattern monitoring, however the matches to the user queries are in fact plentiful and the system has to efficiently sift through these many matches to locate only the few most preferable matches. In this paper, we propose a complex pattern ranking (CPR) framework for specifying top-k pattern queries over streaming data, present new algorithms to support top-k pattern queries in data streaming environments, and verify the effectiveness and efficiency of the proposed algorithms. The algorithms we develop identify top-k matching results satisfying both patterns and additional criteria. To support real-time processing of the data streams, instead of computing top-k results from scratch for each time window, we maintain top-k results dynamically as new events come and old ones expire. We also develop new top-k join execution strategies that are able to adapt to the changing situations (e.g., sorted and random access costs, join rates) without having to assume a priori presence of distributed stream statistics. Experiments show significant improvements over existing approaches.

Original languageEnglish (US)
Title of host publicationDEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems
Pages279-290
Number of pages12
DOIs
StatePublished - 2011
Event5th ACM International Conference on Distributed Event-Based Systems, DEBS'11 - New York, NY, United States
Duration: Jul 11 2011Jul 15 2011

Other

Other5th ACM International Conference on Distributed Event-Based Systems, DEBS'11
CountryUnited States
CityNew York, NY
Period7/11/117/15/11

Fingerprint

Processing
Statistics
Monitoring
Costs
Experiments

Keywords

  • complex event processing
  • pattern ranking
  • topk query

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Wang, X., Candan, K., & Song, J. (2011). Complex Pattern Ranking (CPR): Evaluating top-k pattern queries over event streams. In DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems (pp. 279-290) https://doi.org/10.1145/2002259.2002296

Complex Pattern Ranking (CPR) : Evaluating top-k pattern queries over event streams. / Wang, Xinxin; Candan, Kasim; Song, Junehwa.

DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems. 2011. p. 279-290.

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

Wang, X, Candan, K & Song, J 2011, Complex Pattern Ranking (CPR): Evaluating top-k pattern queries over event streams. in DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems. pp. 279-290, 5th ACM International Conference on Distributed Event-Based Systems, DEBS'11, New York, NY, United States, 7/11/11. https://doi.org/10.1145/2002259.2002296
Wang X, Candan K, Song J. Complex Pattern Ranking (CPR): Evaluating top-k pattern queries over event streams. In DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems. 2011. p. 279-290 https://doi.org/10.1145/2002259.2002296
Wang, Xinxin ; Candan, Kasim ; Song, Junehwa. / Complex Pattern Ranking (CPR) : Evaluating top-k pattern queries over event streams. DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems. 2011. pp. 279-290
@inproceedings{ed3e735cf6984f52980c859e9bc615c6,
title = "Complex Pattern Ranking (CPR): Evaluating top-k pattern queries over event streams",
abstract = "Most existing approaches to complex event processing over streaming data rely on the assumption that the matches to the queries are rare and that the goal of the system is to identify these few matches within the incoming deluge of data. In many applications, such as user credit card purchase pattern monitoring, however the matches to the user queries are in fact plentiful and the system has to efficiently sift through these many matches to locate only the few most preferable matches. In this paper, we propose a complex pattern ranking (CPR) framework for specifying top-k pattern queries over streaming data, present new algorithms to support top-k pattern queries in data streaming environments, and verify the effectiveness and efficiency of the proposed algorithms. The algorithms we develop identify top-k matching results satisfying both patterns and additional criteria. To support real-time processing of the data streams, instead of computing top-k results from scratch for each time window, we maintain top-k results dynamically as new events come and old ones expire. We also develop new top-k join execution strategies that are able to adapt to the changing situations (e.g., sorted and random access costs, join rates) without having to assume a priori presence of distributed stream statistics. Experiments show significant improvements over existing approaches.",
keywords = "complex event processing, pattern ranking, topk query",
author = "Xinxin Wang and Kasim Candan and Junehwa Song",
year = "2011",
doi = "10.1145/2002259.2002296",
language = "English (US)",
isbn = "9781450309059",
pages = "279--290",
booktitle = "DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems",

}

TY - GEN

T1 - Complex Pattern Ranking (CPR)

T2 - Evaluating top-k pattern queries over event streams

AU - Wang, Xinxin

AU - Candan, Kasim

AU - Song, Junehwa

PY - 2011

Y1 - 2011

N2 - Most existing approaches to complex event processing over streaming data rely on the assumption that the matches to the queries are rare and that the goal of the system is to identify these few matches within the incoming deluge of data. In many applications, such as user credit card purchase pattern monitoring, however the matches to the user queries are in fact plentiful and the system has to efficiently sift through these many matches to locate only the few most preferable matches. In this paper, we propose a complex pattern ranking (CPR) framework for specifying top-k pattern queries over streaming data, present new algorithms to support top-k pattern queries in data streaming environments, and verify the effectiveness and efficiency of the proposed algorithms. The algorithms we develop identify top-k matching results satisfying both patterns and additional criteria. To support real-time processing of the data streams, instead of computing top-k results from scratch for each time window, we maintain top-k results dynamically as new events come and old ones expire. We also develop new top-k join execution strategies that are able to adapt to the changing situations (e.g., sorted and random access costs, join rates) without having to assume a priori presence of distributed stream statistics. Experiments show significant improvements over existing approaches.

AB - Most existing approaches to complex event processing over streaming data rely on the assumption that the matches to the queries are rare and that the goal of the system is to identify these few matches within the incoming deluge of data. In many applications, such as user credit card purchase pattern monitoring, however the matches to the user queries are in fact plentiful and the system has to efficiently sift through these many matches to locate only the few most preferable matches. In this paper, we propose a complex pattern ranking (CPR) framework for specifying top-k pattern queries over streaming data, present new algorithms to support top-k pattern queries in data streaming environments, and verify the effectiveness and efficiency of the proposed algorithms. The algorithms we develop identify top-k matching results satisfying both patterns and additional criteria. To support real-time processing of the data streams, instead of computing top-k results from scratch for each time window, we maintain top-k results dynamically as new events come and old ones expire. We also develop new top-k join execution strategies that are able to adapt to the changing situations (e.g., sorted and random access costs, join rates) without having to assume a priori presence of distributed stream statistics. Experiments show significant improvements over existing approaches.

KW - complex event processing

KW - pattern ranking

KW - topk query

UR - http://www.scopus.com/inward/record.url?scp=80051923463&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051923463&partnerID=8YFLogxK

U2 - 10.1145/2002259.2002296

DO - 10.1145/2002259.2002296

M3 - Conference contribution

AN - SCOPUS:80051923463

SN - 9781450309059

SP - 279

EP - 290

BT - DEBS'11 - Proceedings of the 5th ACM International Conference on Distributed Event-Based Systems

ER -