Robust multiclass signaling overload control

Sneha Kasera, José Pinheiro, Catherine Loader, Thomas F. La Porta, Mehmet Karaul, Adiseshu Hari

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

7 Citations (Scopus)

Abstract

We propose multi-class signaling overload control algorithms, for telecommunication switches, that are robust against different input traffic patterns and system upgrades. In order to appropriately measure the system load when several classes of signaling traffic are present, we first introduce the concept of equivalent system load measure, that converts the multiple system measures associated with different classes of traffic into a single measure with respect to a pre-defined base class. We use this measure to develop three multi-class overload detection and measurement algorithms. Next, we develop a new algorithm for partitioning the allowable equivalent system load across multiple traffic classes, using a strict priority scheme. Using simulations of call flows from mobile telecommunications standards, we compare different multi-class overload algorithms under a variety of overload conditions. Our simulation results indicate that our algorithm that measures system load using a combination of request acceptance rate and processor occupancy, provides highly reactive and robust overload control. Last, for the purpose of making the overload control algorithms more robust, we propose a measurement-based simple regression technique to dynamically estimate key system parameters. We find that estimates derived in this manner converge rapidly to their true values.

Original languageEnglish (US)
Title of host publicationProceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005
Pages246-255
Number of pages10
DOIs
StatePublished - Dec 1 2005
Event13TH IEEE International Conference on Network Protocols, ICNP 2005 - Boston, MA, United States
Duration: Nov 6 2005Nov 9 2005

Publication series

NameProceedings - International Conference on Network Protocols, ICNP
Volume2005
ISSN (Print)1092-1648

Other

Other13TH IEEE International Conference on Network Protocols, ICNP 2005
CountryUnited States
CityBoston, MA
Period11/6/0511/9/05

Fingerprint

Telecommunication
Robust control
Switches

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Kasera, S., Pinheiro, J., Loader, C., La Porta, T. F., Karaul, M., & Hari, A. (2005). Robust multiclass signaling overload control. In Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005 (pp. 246-255). [1544625] (Proceedings - International Conference on Network Protocols, ICNP; Vol. 2005). https://doi.org/10.1109/ICNP.2005.34
Kasera, Sneha ; Pinheiro, José ; Loader, Catherine ; La Porta, Thomas F. ; Karaul, Mehmet ; Hari, Adiseshu. / Robust multiclass signaling overload control. Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005. 2005. pp. 246-255 (Proceedings - International Conference on Network Protocols, ICNP).
@inproceedings{a467df75434a4b229c90ae993c87f847,
title = "Robust multiclass signaling overload control",
abstract = "We propose multi-class signaling overload control algorithms, for telecommunication switches, that are robust against different input traffic patterns and system upgrades. In order to appropriately measure the system load when several classes of signaling traffic are present, we first introduce the concept of equivalent system load measure, that converts the multiple system measures associated with different classes of traffic into a single measure with respect to a pre-defined base class. We use this measure to develop three multi-class overload detection and measurement algorithms. Next, we develop a new algorithm for partitioning the allowable equivalent system load across multiple traffic classes, using a strict priority scheme. Using simulations of call flows from mobile telecommunications standards, we compare different multi-class overload algorithms under a variety of overload conditions. Our simulation results indicate that our algorithm that measures system load using a combination of request acceptance rate and processor occupancy, provides highly reactive and robust overload control. Last, for the purpose of making the overload control algorithms more robust, we propose a measurement-based simple regression technique to dynamically estimate key system parameters. We find that estimates derived in this manner converge rapidly to their true values.",
author = "Sneha Kasera and Jos{\'e} Pinheiro and Catherine Loader and {La Porta}, {Thomas F.} and Mehmet Karaul and Adiseshu Hari",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/ICNP.2005.34",
language = "English (US)",
isbn = "0769524370",
series = "Proceedings - International Conference on Network Protocols, ICNP",
pages = "246--255",
booktitle = "Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005",

}

Kasera, S, Pinheiro, J, Loader, C, La Porta, TF, Karaul, M & Hari, A 2005, Robust multiclass signaling overload control. in Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005., 1544625, Proceedings - International Conference on Network Protocols, ICNP, vol. 2005, pp. 246-255, 13TH IEEE International Conference on Network Protocols, ICNP 2005, Boston, MA, United States, 11/6/05. https://doi.org/10.1109/ICNP.2005.34

Robust multiclass signaling overload control. / Kasera, Sneha; Pinheiro, José; Loader, Catherine; La Porta, Thomas F.; Karaul, Mehmet; Hari, Adiseshu.

Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005. 2005. p. 246-255 1544625 (Proceedings - International Conference on Network Protocols, ICNP; Vol. 2005).

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

TY - GEN

T1 - Robust multiclass signaling overload control

AU - Kasera, Sneha

AU - Pinheiro, José

AU - Loader, Catherine

AU - La Porta, Thomas F.

AU - Karaul, Mehmet

AU - Hari, Adiseshu

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We propose multi-class signaling overload control algorithms, for telecommunication switches, that are robust against different input traffic patterns and system upgrades. In order to appropriately measure the system load when several classes of signaling traffic are present, we first introduce the concept of equivalent system load measure, that converts the multiple system measures associated with different classes of traffic into a single measure with respect to a pre-defined base class. We use this measure to develop three multi-class overload detection and measurement algorithms. Next, we develop a new algorithm for partitioning the allowable equivalent system load across multiple traffic classes, using a strict priority scheme. Using simulations of call flows from mobile telecommunications standards, we compare different multi-class overload algorithms under a variety of overload conditions. Our simulation results indicate that our algorithm that measures system load using a combination of request acceptance rate and processor occupancy, provides highly reactive and robust overload control. Last, for the purpose of making the overload control algorithms more robust, we propose a measurement-based simple regression technique to dynamically estimate key system parameters. We find that estimates derived in this manner converge rapidly to their true values.

AB - We propose multi-class signaling overload control algorithms, for telecommunication switches, that are robust against different input traffic patterns and system upgrades. In order to appropriately measure the system load when several classes of signaling traffic are present, we first introduce the concept of equivalent system load measure, that converts the multiple system measures associated with different classes of traffic into a single measure with respect to a pre-defined base class. We use this measure to develop three multi-class overload detection and measurement algorithms. Next, we develop a new algorithm for partitioning the allowable equivalent system load across multiple traffic classes, using a strict priority scheme. Using simulations of call flows from mobile telecommunications standards, we compare different multi-class overload algorithms under a variety of overload conditions. Our simulation results indicate that our algorithm that measures system load using a combination of request acceptance rate and processor occupancy, provides highly reactive and robust overload control. Last, for the purpose of making the overload control algorithms more robust, we propose a measurement-based simple regression technique to dynamically estimate key system parameters. We find that estimates derived in this manner converge rapidly to their true values.

UR - http://www.scopus.com/inward/record.url?scp=33750952100&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33750952100&partnerID=8YFLogxK

U2 - 10.1109/ICNP.2005.34

DO - 10.1109/ICNP.2005.34

M3 - Conference contribution

AN - SCOPUS:33750952100

SN - 0769524370

SN - 9780769524375

T3 - Proceedings - International Conference on Network Protocols, ICNP

SP - 246

EP - 255

BT - Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005

ER -

Kasera S, Pinheiro J, Loader C, La Porta TF, Karaul M, Hari A. Robust multiclass signaling overload control. In Proceedings - 13TH IEEE International Conference on Network Protocols, ICNP 2005. 2005. p. 246-255. 1544625. (Proceedings - International Conference on Network Protocols, ICNP). https://doi.org/10.1109/ICNP.2005.34