Paper Info
Title
Multi-model prediction for enhancing content locality in elastic server infrastructures
Abstract
Infrastructures serving on-line applications experience dynamic workload variations depending on diverse factors such as popularity, marketing, periodic patterns, fads, trends, events, etc. Some predictable factors such as trends, periodicity or scheduled events allow for proactive resource provisioning in order to meet fluctuations in workloads. However, proactive resource provisioning requires prediction models forecasting future workload patterns. This paper proposes a multi-model prediction approach, in which data are grouped into bins based on content locality, and an autoregressive prediction model is assigned to each locality-preserving bin. The prediction models are shown to be identified and fitted in a computationally efficient way. We demonstrate experimentally that our multi-model approach improves locality over the uni-model approach, while achieving efficient resource provisioning and preserving a high resource utilization and load balance.
Year
DOI
Venue
2011
10.1109/HiPC.2011.6152728
HiPC
Keywords
Field
DocType
proactive resource,multi-model approach,multi-model prediction approach,uni-model approach,multi-model prediction,elastic server infrastructure,dynamic workload variation,efficient resource,autoregressive prediction model,prediction model,content locality,high resource utilization,file servers,computational modeling,data models,predictive models,data model,load balance,resource allocation,mathematical model,web servers,resource utilization,internet,computer model
Data modeling,Locality,File server,Load balancing (computing),Computer science,Workload,Provisioning,Resource allocation,Web server,Distributed computing
Conference
Citations 
PageRank 
References 
10
0.64
14
Authors
4
Name
Order
Citations
PageRank
Juan M. Tirado1614.54
Daniel Higuero2483.97
Florin Isaila323424.01
Jesus Carretero423929.04