NARX-based multi-step ahead response time prediction for database servers

Payam Amani; Maria Kihl; Anders Robertsson

doi:10.1109/ISDA.2011.6121757

NARX-based multi-step ahead response time prediction for database servers

Payam Amani, Maria Kihl, Anders Robertsson

Forskningsoutput: Kapitel i bok/rapport/Conference proceeding › Konferenspaper i proceeding › Peer review

1037 Nedladdningar (Pure)

Sammanfattning

Advanced telecommunication applications are often based on a multi-tier architecture, with application servers and database servers. With a rapidly increasing development of cloud computing and data centers, characterizations of the dynamics for database servers during changing workloads will be a key factor for analysis and performance improvements in these applications. We propose a multi-step ahead response time predictor for database queries based on a nonlinear autoregressive neural network model with exogenous inputs. The estimator shows many promising characteristics which make it a viable candidate for being implemented in admission control products for database servers. Performance of the proposed predictor is evaluated through experiments on a lab setup with a MySQL-server.

Originalspråk	engelska
Titel på värdpublikation	[Host publication title missing]
Förlag	IEEE - Institute of Electrical and Electronics Engineers Inc.
Sidor	813-818
ISBN (tryckt)	978-1-4577-1676-8
DOI	https://doi.org/10.1109/ISDA.2011.6121757
Status	Published - 2011
Evenemang	11th International Conference on Intelligent Systems Design and Applications - Cordoba, Spanien Varaktighet: 2011 nov. 22 → 2011 nov. 24

Publikationsserier

Namn
ISSN (tryckt)	2164-7143

Konferens

Konferens	11th International Conference on Intelligent Systems Design and Applications
Land/Territorium	Spanien
Ort	Cordoba
Period	2011/11/22 → 2011/11/24

Bibliografisk information

key=amani_etal2011isda

Ämnesklassifikation (UKÄ)

Reglerteknik
Elektroteknik och elektronik

Tillgång till dokument

10.1109/ISDA.2011.6121757

PID2077899

LCCC
Holmqvist, A. (Forskare), Andersson, N. (Forskare), Cervin, A. (Forskare), Mannesson, A. (Forskare), Gattami, A. (Forskare), Ghulchak, A. (Forskare), Papadopoulos, A. V. (Forskare), Rantzer, A. (Forskare), Robertsson, A. (Forskare), Sootla, A. (Forskare), THEORIN, A. (Forskare), Bernhardsson, B. (Forskare), Olofsson, B. (Forskare), Wittenmark, B. (Forskare), Grussler, C. (Forskare), Johnsson, C. (Forskare), MADJIDIAN, D. (Forskare), Johannesson, E. (Forskare), Magnusson, F. (Forskare), Ståhl, F. (Forskare), Como, G. (Forskare), Chasparis, G. (Forskare), Turesson, G. (Forskare), Dressler, I. (Forskare), Åkesson, J. (Forskare), Cho, J. H. (Forskare), Årzén, K.-E. (Forskare), Åström, K. J. (Forskare), Sou, K. C. (Forskare), Mårtensson, K. (Forskare), Berntorp, K. (Forskare), Soltesz, K. (Forskare), Lessard, L. (Forskare), Hast, M. (Forskare), Rönn, M. (Forskare), Ansbjerg Kjær, M. (Forskare), Maggio, M. (Forskare), Kristalny, M. (Forskare), Garpinger, O. (Forskare), From, P. J. (Forskare), Larsson, P.-O. (Forskare), Giselsson, P. (Forskare), Johansson, R. (Forskare), Hägglund, T. (Forskare), Vladimerou, V. (Forskare), Romero Segovia, V. (Forskare), Aurelius, A. (Forskare), Cedersjö, G. (Forskare), Bür, K. (Forskare), Dellkrantz, M. (Forskare), Du, M. (Forskare), Amani, P. (Forskare), Larsson, R. (Forskare), Tärneberg, W. (Forskarstuderande), Li, Z. (Forskare), Yin, L. (Forskare), Tufvesson, F. (Forskare), Höst, S. (Forskare), Nilsson, B. (Forskare), Stenström, S. (Forskare), Andersson, J. A. (Forskare), Diehl, S. (Forskare), Dürango, J. (Forskare), Ghazaei Ardakani, M. (Forskare), Forsberg, P.-O. (Forskare), Bengtsson, F. (Forskare), Jörntell, H. (Forskare), Arévalo, C. (Forskare), Führer, C. (Forskare), Andersson, C. (Forskare), Mohammadi, F. (Forskare), Ödling, P. (Forskare), Andersson, M. (Forskare), Kihl, M. (Forskare) & Tunestål, P. (Forskare)
2008/07/01 → 2018/06/30
Projekt: Forskning

Citera det här

@inproceedings{ffc14c2fee61436f803bf560465decf1,

title = "NARX-based multi-step ahead response time prediction for database servers",

abstract = "Advanced telecommunication applications are often based on a multi-tier architecture, with application servers and database servers. With a rapidly increasing development of cloud computing and data centers, characterizations of the dynamics for database servers during changing workloads will be a key factor for analysis and performance improvements in these applications. We propose a multi-step ahead response time predictor for database queries based on a nonlinear autoregressive neural network model with exogenous inputs. The estimator shows many promising characteristics which make it a viable candidate for being implemented in admission control products for database servers. Performance of the proposed predictor is evaluated through experiments on a lab setup with a MySQL-server.",

author = "Payam Amani and Maria Kihl and Anders Robertsson",

note = "key=amani_etal2011isda; 11th International Conference on Intelligent Systems Design and Applications ; Conference date: 22-11-2011 Through 24-11-2011",

year = "2011",

doi = "10.1109/ISDA.2011.6121757",

language = "English",

isbn = "978-1-4577-1676-8",

publisher = "IEEE - Institute of Electrical and Electronics Engineers Inc.",

pages = "813--818",

booktitle = "[Host publication title missing]",

address = "United States",

}

Amani, P , Kihl, M & Robertsson, A 2011, NARX-based multi-step ahead response time prediction for database servers. i [Host publication title missing]. IEEE - Institute of Electrical and Electronics Engineers Inc., s. 813-818, 11th International Conference on Intelligent Systems Design and Applications, Cordoba, Spanien, 2011/11/22. https://doi.org/10.1109/ISDA.2011.6121757

TY - GEN

T1 - NARX-based multi-step ahead response time prediction for database servers

AU - Amani, Payam

AU - Kihl, Maria

AU - Robertsson, Anders

N1 - key=amani_etal2011isda

PY - 2011

Y1 - 2011

N2 - Advanced telecommunication applications are often based on a multi-tier architecture, with application servers and database servers. With a rapidly increasing development of cloud computing and data centers, characterizations of the dynamics for database servers during changing workloads will be a key factor for analysis and performance improvements in these applications. We propose a multi-step ahead response time predictor for database queries based on a nonlinear autoregressive neural network model with exogenous inputs. The estimator shows many promising characteristics which make it a viable candidate for being implemented in admission control products for database servers. Performance of the proposed predictor is evaluated through experiments on a lab setup with a MySQL-server.

AB - Advanced telecommunication applications are often based on a multi-tier architecture, with application servers and database servers. With a rapidly increasing development of cloud computing and data centers, characterizations of the dynamics for database servers during changing workloads will be a key factor for analysis and performance improvements in these applications. We propose a multi-step ahead response time predictor for database queries based on a nonlinear autoregressive neural network model with exogenous inputs. The estimator shows many promising characteristics which make it a viable candidate for being implemented in admission control products for database servers. Performance of the proposed predictor is evaluated through experiments on a lab setup with a MySQL-server.

U2 - 10.1109/ISDA.2011.6121757

DO - 10.1109/ISDA.2011.6121757

M3 - Paper in conference proceeding

SN - 978-1-4577-1676-8

SP - 813

EP - 818

BT - [Host publication title missing]

PB - IEEE - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Conference on Intelligent Systems Design and Applications

Y2 - 22 November 2011 through 24 November 2011

ER -

NARX-based multi-step ahead response time prediction for database servers

Sammanfattning

Publikationsserier

Konferens

Bibliografisk information

Ämnesklassifikation (UKÄ)

Tillgång till dokument

Fingeravtryck

Projekt

LCCC

Citera det här