Load Balancing Using Time Series Analysis for Soft Real Time Systems with Statiscally Periodic Loads

From Tetherless World Wiki

Jump to: navigation, search

Citation: Max Hailperin. (1993) Load Balancing Using Time Series Analysis for Soft Real Time Systems with Statiscally Periodic Loads. In KSL-93-48, 1993.

Publication techreport ( Edit )
type Technical Report
bibtype techreport
Bibtex basics
author Max Hailperin
title Load Balancing Using Time Series Analysis for Soft Real Time Systems with Statiscally Periodic Loads
number KSL-93-48
institution Stanford University
address Stanford, CA, USA
year 1993
Bibtex more
note STAN-CS-94-1514.
Access Paper
abstract This thesis provides design and analysis of techniques for global load balancing on ensemble architectures running soft-real-time object-oriented applications with statistically periodic loads. It focuses on estimating the instantaneous average load over all the processing elements.The major contribution is the use of explicit stochastic process models for both the loading and the averaging itself. These models are exploited via statistical time-series analysis and Bayesian inference to provide improved average laod estimates, and thus to facilitate global load balancing.This thesis explains the distributed algorithms used and provides some optimality results. It also describes the algorithms' implementation and gives performance results from simulation. These results show that our techniques allow more accurate estimation of the global system loading, resulting in fewer object migrations than local methods. Our method is shown to provide superior performance, relative not only to static load-balancing schemes but also to many adaptive load-balancing methods. Results from a preliminary analysis of another system and from simulation with a synthetic load provide some evidence of more general applicability.

KSL Technical Report ID: KSL-93-48
Facts about Load Balancing Using Time Series Analysis for Soft Real Time Systems with Statiscally Periodic LoadsRDF feed
Abstract This thesis provides design and analysis o … This thesis provides design and analysis of techniques for global load balancing on ensemble architectures running soft-real-time object-oriented applications with statistically periodic loads. It focuses on estimating the instantaneous average load over all the processing elements.The major contribution is the use of explicit stochastic process models for both the loading and the averaging itself. These models are exploited via statistical time-series analysis and Bayesian inference to provide improved average laod estimates, and thus to facilitate global load balancing.This thesis explains the distributed algorithms used and provides some optimality results. It also describes the algorithms' implementation and gives performance results from simulation. These results show that our techniques allow more accurate estimation of the global system loading, resulting in fewer object migrations than local methods. Our method is shown to provide superior performance, relative not only to static load-balancing schemes but also to many adaptive load-balancing methods. Results from a preliminary analysis of another system and from simulation with a synthetic load provide some evidence of more general applicability. me evidence of more general applicability.
Address Stanford, CA, USA  +
Author Max Hailperin  +
Bibtype techreport  +
Has author Max Hailperin  +
Has identifier KSL-93-48  +
Has publishing details 1993  +
Has title Load Balancing Using Time Series Analysis for Soft Real Time Systems with Statiscally Periodic Loads  +
Has where published KSL-93-48  +
Has year 1993  +
Institution Stanford University  +
Ksl tr id KSL-93-48  +
Note STAN-CS-94-1514.
Number KSL-93-48  +
Process note NO  +
Title Load Balancing Using Time Series Analysis for Soft Real Time Systems with Statiscally Periodic Loads  +
Year 1993  +
Retrieved from "http://tw.rpi.edu/wiki/Load_Balancing_Using_Time_Series_Analysis_for_Soft_Real_Time_Systems_with_Statiscally_Periodic_Loads"
Personal tools