Dynamic replica selection using improved kernel density estimation

Yin Pang; Kan Li; Xin Sun; Kaili Bu

doi:10.1109/IITSI.2010.49

Dynamic replica selection using improved kernel density estimation

Yin Pang^*
, Kan Li
, Xin Sun
, Kaili Bu

^*Corresponding author for this work

School of Computer Science and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Replication service in Distributed Systems can reduce access latency and bandwidth consumption. When different nodes hold replicas accessed, there will be a significant benefit by selecting the best replica. Most of the existed replication strategies deal with the prediction of the response time. However, these strategies do not take fully into account the network dynamic and access locality. To solve this problem, a dynamic replica selection strategy using improved Kernel Density Estimation (KDE) is presented. Firstly, it distinguishes old replicas from new ones. Then, it predicts the network load and available bandwidth to choose the best replica. The improved KDE can select accurately the best accessed replica with only a little history data, which is very useful in a dynamic network. Simulation results demonstrate the efficiency and effectiveness of improved KDE in comparison with other approaches.

Original language	English
Title of host publication	3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010
Pages	470-474
Number of pages	5
DOIs	https://doi.org/10.1109/IITSI.2010.49
Publication status	Published - 2010
Event	2010 International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010 - Jinggangshan, China Duration: 2 Apr 2010 → 4 Apr 2010

Publication series

Name	3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010

Conference

Conference	2010 International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010
Country/Territory	China
City	Jinggangshan
Period	2/04/10 → 4/04/10

Keywords

Geographic locality
Improved KDE
Replica selection
Temporal locality

Access to Document

10.1109/IITSI.2010.49

Cite this

Pang, Y., Li, K., Sun, X., & Bu, K. (2010). Dynamic replica selection using improved kernel density estimation. In 3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010 (pp. 470-474). Article 5453669 (3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010). https://doi.org/10.1109/IITSI.2010.49

@inproceedings{ea8970f7133f48529e7f209900e2fee4,

title = "Dynamic replica selection using improved kernel density estimation",

abstract = "Replication service in Distributed Systems can reduce access latency and bandwidth consumption. When different nodes hold replicas accessed, there will be a significant benefit by selecting the best replica. Most of the existed replication strategies deal with the prediction of the response time. However, these strategies do not take fully into account the network dynamic and access locality. To solve this problem, a dynamic replica selection strategy using improved Kernel Density Estimation (KDE) is presented. Firstly, it distinguishes old replicas from new ones. Then, it predicts the network load and available bandwidth to choose the best replica. The improved KDE can select accurately the best accessed replica with only a little history data, which is very useful in a dynamic network. Simulation results demonstrate the efficiency and effectiveness of improved KDE in comparison with other approaches.",

keywords = "Geographic locality, Improved KDE, Replica selection, Temporal locality",

author = "Yin Pang and Kan Li and Xin Sun and Kaili Bu",

year = "2010",

doi = "10.1109/IITSI.2010.49",

language = "English",

isbn = "9780769540207",

series = "3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010",

pages = "470--474",

booktitle = "3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010",

note = "2010 International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010 ; Conference date: 02-04-2010 Through 04-04-2010",

}

Pang, Y, Li, K , Sun, X & Bu, K 2010, Dynamic replica selection using improved kernel density estimation. in 3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010., 5453669, 3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010, pp. 470-474, 2010 International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010, Jinggangshan, China, 2/04/10. https://doi.org/10.1109/IITSI.2010.49

Dynamic replica selection using improved kernel density estimation. / Pang, Yin; Li, Kan ; Sun, Xin et al.
3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010. 2010. p. 470-474 5453669 (3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Dynamic replica selection using improved kernel density estimation

AU - Pang, Yin

AU - Li, Kan

AU - Sun, Xin

AU - Bu, Kaili

PY - 2010

Y1 - 2010

N2 - Replication service in Distributed Systems can reduce access latency and bandwidth consumption. When different nodes hold replicas accessed, there will be a significant benefit by selecting the best replica. Most of the existed replication strategies deal with the prediction of the response time. However, these strategies do not take fully into account the network dynamic and access locality. To solve this problem, a dynamic replica selection strategy using improved Kernel Density Estimation (KDE) is presented. Firstly, it distinguishes old replicas from new ones. Then, it predicts the network load and available bandwidth to choose the best replica. The improved KDE can select accurately the best accessed replica with only a little history data, which is very useful in a dynamic network. Simulation results demonstrate the efficiency and effectiveness of improved KDE in comparison with other approaches.

AB - Replication service in Distributed Systems can reduce access latency and bandwidth consumption. When different nodes hold replicas accessed, there will be a significant benefit by selecting the best replica. Most of the existed replication strategies deal with the prediction of the response time. However, these strategies do not take fully into account the network dynamic and access locality. To solve this problem, a dynamic replica selection strategy using improved Kernel Density Estimation (KDE) is presented. Firstly, it distinguishes old replicas from new ones. Then, it predicts the network load and available bandwidth to choose the best replica. The improved KDE can select accurately the best accessed replica with only a little history data, which is very useful in a dynamic network. Simulation results demonstrate the efficiency and effectiveness of improved KDE in comparison with other approaches.

KW - Geographic locality

KW - Improved KDE

KW - Replica selection

KW - Temporal locality

UR - https://www.scopus.com/pages/publications/77952714089

U2 - 10.1109/IITSI.2010.49

DO - 10.1109/IITSI.2010.49

M3 - Conference contribution

AN - SCOPUS:77952714089

SN - 9780769540207

T3 - 3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010

SP - 470

EP - 474

BT - 3rd International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010

T2 - 2010 International Symposium on Intelligent Information Technology and Security Informatics, IITSI 2010

Y2 - 2 April 2010 through 4 April 2010

ER -

Dynamic replica selection using improved kernel density estimation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this