A Predictive File Replication Strategy for Grid Computing

Chenhan Liao; Frank Wang; Sining Wu; Md Mamunur  Rashid; Na Helian

doi:10.4203/ccp.90.21

A Predictive File Replication Strategy for Grid Computing

Chenhan Liao, Frank Wang, Sining Wu, Md Mamunur Rashid, Na Helian

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

Abstract

Replicating files among Grid nodes is due to the distributed nature of the Data Grids where geographically distributed data lead to access latency. Most replication methods either monitor the popularity of files or use complicated functions to calculate overall cost whether a replication decision or a deletion decision should be issued. However, when the replication decision is executed, the popularity of the files had changed and may have already given impact on access latency and resource usage. This paper proposes a predictive file replication strategy that forecasts files' future popularity based on their characteristics on the Grids

Original language	English
Title of host publication	Proceedings of the First International Conference on Parallel, Distributed and Grid Computing for Engineering
Publisher	Civil-Comp Press
DOIs	https://doi.org/10.4203/ccp.90.21
Publication status	Published - 2009

Access to Document

10.4203/ccp.90.21

Cite this

@inproceedings{252820f607ee448f9746f00977a0efd1,

title = "A Predictive File Replication Strategy for Grid Computing",

abstract = "Replicating files among Grid nodes is due to the distributed nature of the Data Grids where geographically distributed data lead to access latency. Most replication methods either monitor the popularity of files or use complicated functions to calculate overall cost whether a replication decision or a deletion decision should be issued. However, when the replication decision is executed, the popularity of the files had changed and may have already given impact on access latency and resource usage. This paper proposes a predictive file replication strategy that forecasts files' future popularity based on their characteristics on the Grids",

author = "Chenhan Liao and Frank Wang and Sining Wu and Rashid, {Md Mamunur} and Na Helian",

year = "2009",

doi = "10.4203/ccp.90.21",

language = "English",

booktitle = "Proceedings of the First International Conference on Parallel, Distributed and Grid Computing for Engineering",

publisher = "Civil-Comp Press",

address = "United Kingdom",

}

TY - GEN

T1 - A Predictive File Replication Strategy for Grid Computing

AU - Liao, Chenhan

AU - Wang, Frank

AU - Wu, Sining

AU - Rashid, Md Mamunur

AU - Helian, Na

PY - 2009

Y1 - 2009

N2 - Replicating files among Grid nodes is due to the distributed nature of the Data Grids where geographically distributed data lead to access latency. Most replication methods either monitor the popularity of files or use complicated functions to calculate overall cost whether a replication decision or a deletion decision should be issued. However, when the replication decision is executed, the popularity of the files had changed and may have already given impact on access latency and resource usage. This paper proposes a predictive file replication strategy that forecasts files' future popularity based on their characteristics on the Grids

AB - Replicating files among Grid nodes is due to the distributed nature of the Data Grids where geographically distributed data lead to access latency. Most replication methods either monitor the popularity of files or use complicated functions to calculate overall cost whether a replication decision or a deletion decision should be issued. However, when the replication decision is executed, the popularity of the files had changed and may have already given impact on access latency and resource usage. This paper proposes a predictive file replication strategy that forecasts files' future popularity based on their characteristics on the Grids

U2 - 10.4203/ccp.90.21

DO - 10.4203/ccp.90.21

M3 - Conference contribution

BT - Proceedings of the First International Conference on Parallel, Distributed and Grid Computing for Engineering

PB - Civil-Comp Press

ER -

A Predictive File Replication Strategy for Grid Computing

Abstract

Access to Document

Fingerprint

Cite this