Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks

Thadpong Pongthawornkamol, Klara Nahrstedt, Guijun Wang

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

Abstract

Content-based publish/subscribe (CBPS) paradigm is a powerful data dissemination paradigm that offers both scalability and flexibility. However, its nature of high expressiveness makes it difficult to analyze or predict the behavior of the system such as event delivery probability and end-to-end delivery delay, especially when deployed over unreliable, best-effort public networks. This paper proposes an analytical model that abstracts both expressiveness of content-based publish/subscribe systems, and uncertainty of underlying networks. The overall goal of this model is to predict quality of service in terms of delivery probability and timeliness based on partial, imprecise statistical attributes of each component in the distributed CBPS system. The evaluation results via extensive simulations with real-world traces yield effectiveness of the proposed prediction model. The proposed prediction model can be used as a building block for automatic quality of service control in publish/subscribe systems such as subscriber admission control, broker capacity planning, overload management, and resource adaptation.

Original languageEnglish (US)
Title of host publicationProceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops
Pages185-194
Number of pages10
DOIs
StatePublished - Jul 23 2010
Event7th IEEE/ACM International Conference on Autonomic Computing and Communications, ICAC-2010 and Co-located Workshops - Washington, DC, United States
Duration: Jun 7 2010Jun 11 2010

Publication series

NameProceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops

Other

Other7th IEEE/ACM International Conference on Autonomic Computing and Communications, ICAC-2010 and Co-located Workshops
CountryUnited States
CityWashington, DC
Period6/7/106/11/10

Fingerprint

Quality of service
Access control
Scalability
Analytical models
Planning
Uncertainty

Keywords

  • distributed systems
  • publish/subscribe
  • quality of service

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Human-Computer Interaction
  • Software

Cite this

Pongthawornkamol, T., Nahrstedt, K., & Wang, G. (2010). Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks. In Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops (pp. 185-194). (Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops). https://doi.org/10.1145/1809049.1809083

Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks. / Pongthawornkamol, Thadpong; Nahrstedt, Klara; Wang, Guijun.

Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops. 2010. p. 185-194 (Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops).

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

Pongthawornkamol, T, Nahrstedt, K & Wang, G 2010, Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks. in Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops. Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops, pp. 185-194, 7th IEEE/ACM International Conference on Autonomic Computing and Communications, ICAC-2010 and Co-located Workshops, Washington, DC, United States, 6/7/10. https://doi.org/10.1145/1809049.1809083
Pongthawornkamol T, Nahrstedt K, Wang G. Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks. In Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops. 2010. p. 185-194. (Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops). https://doi.org/10.1145/1809049.1809083
Pongthawornkamol, Thadpong ; Nahrstedt, Klara ; Wang, Guijun. / Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks. Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops. 2010. pp. 185-194 (Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops).
@inproceedings{15583273162f42a4850cb464e084a1b0,
title = "Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks",
abstract = "Content-based publish/subscribe (CBPS) paradigm is a powerful data dissemination paradigm that offers both scalability and flexibility. However, its nature of high expressiveness makes it difficult to analyze or predict the behavior of the system such as event delivery probability and end-to-end delivery delay, especially when deployed over unreliable, best-effort public networks. This paper proposes an analytical model that abstracts both expressiveness of content-based publish/subscribe systems, and uncertainty of underlying networks. The overall goal of this model is to predict quality of service in terms of delivery probability and timeliness based on partial, imprecise statistical attributes of each component in the distributed CBPS system. The evaluation results via extensive simulations with real-world traces yield effectiveness of the proposed prediction model. The proposed prediction model can be used as a building block for automatic quality of service control in publish/subscribe systems such as subscriber admission control, broker capacity planning, overload management, and resource adaptation.",
keywords = "distributed systems, publish/subscribe, quality of service",
author = "Thadpong Pongthawornkamol and Klara Nahrstedt and Guijun Wang",
year = "2010",
month = "7",
day = "23",
doi = "10.1145/1809049.1809083",
language = "English (US)",
isbn = "9781450300742",
series = "Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops",
pages = "185--194",
booktitle = "Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops",

}

TY - GEN

T1 - Probabilistic QoS modeling for reliability/timeliness prediction in distributed content-based publish/subscribe systems over best-effort networks

AU - Pongthawornkamol, Thadpong

AU - Nahrstedt, Klara

AU - Wang, Guijun

PY - 2010/7/23

Y1 - 2010/7/23

N2 - Content-based publish/subscribe (CBPS) paradigm is a powerful data dissemination paradigm that offers both scalability and flexibility. However, its nature of high expressiveness makes it difficult to analyze or predict the behavior of the system such as event delivery probability and end-to-end delivery delay, especially when deployed over unreliable, best-effort public networks. This paper proposes an analytical model that abstracts both expressiveness of content-based publish/subscribe systems, and uncertainty of underlying networks. The overall goal of this model is to predict quality of service in terms of delivery probability and timeliness based on partial, imprecise statistical attributes of each component in the distributed CBPS system. The evaluation results via extensive simulations with real-world traces yield effectiveness of the proposed prediction model. The proposed prediction model can be used as a building block for automatic quality of service control in publish/subscribe systems such as subscriber admission control, broker capacity planning, overload management, and resource adaptation.

AB - Content-based publish/subscribe (CBPS) paradigm is a powerful data dissemination paradigm that offers both scalability and flexibility. However, its nature of high expressiveness makes it difficult to analyze or predict the behavior of the system such as event delivery probability and end-to-end delivery delay, especially when deployed over unreliable, best-effort public networks. This paper proposes an analytical model that abstracts both expressiveness of content-based publish/subscribe systems, and uncertainty of underlying networks. The overall goal of this model is to predict quality of service in terms of delivery probability and timeliness based on partial, imprecise statistical attributes of each component in the distributed CBPS system. The evaluation results via extensive simulations with real-world traces yield effectiveness of the proposed prediction model. The proposed prediction model can be used as a building block for automatic quality of service control in publish/subscribe systems such as subscriber admission control, broker capacity planning, overload management, and resource adaptation.

KW - distributed systems

KW - publish/subscribe

KW - quality of service

UR - http://www.scopus.com/inward/record.url?scp=77954721086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954721086&partnerID=8YFLogxK

U2 - 10.1145/1809049.1809083

DO - 10.1145/1809049.1809083

M3 - Conference contribution

AN - SCOPUS:77954721086

SN - 9781450300742

T3 - Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops

SP - 185

EP - 194

BT - Proceeding of the 7th International Conference on Autonomic Computing, ICAC '10 and Co-located Workshops

ER -