Host load prediction in a Google compute cloud with a Bayesian model

Prediction of host load in Cloud systems is critical for achieving service-level agreements. However, accurate prediction of host load in Clouds is extremely challenging because it fluctuates drastically at small timescales. We design a prediction method based on Bayes model to predict the mean load...

Full description

Saved in:
Bibliographic Details
Published in2012 International Conference for High Performance Computing, Networking, Storage and Analysis pp. 1 - 11
Main Authors Di, Sheng, Kondo, Derrick, Cirne, Walfredo
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2012
Subjects
Bayesian methods
Google
Indexes
Load modeling
Noise
Predictive models
Vectors
Online AccessGet full text
ISBN1467308056
9781467308052
ISSN2167-4329
DOI10.1109/SC.2012.68

Cover

More Information
Summary:Prediction of host load in Cloud systems is critical for achieving service-level agreements. However, accurate prediction of host load in Clouds is extremely challenging because it fluctuates drastically at small timescales. We design a prediction method based on Bayes model to predict the mean load over a long-term time interval, as well as the mean load in consecutive future time intervals. We identify novel predictive features of host load that capture the expectation, predictability, trends and patterns of host load. We also determine the most effective combinations of these features for prediction. We evaluate our method using a detailed one-month trace of a Google data center with thousands of machines. Experiments show that the Bayes method achieves high accuracy with a mean squared error of 0.0014. Moreover, the Bayes method improves the load prediction accuracy by 5.6 -- 50% compared to other state-of-the-art methods based on moving averages, auto-regression, and/or noise filters.
ISBN:1467308056
9781467308052
ISSN:2167-4329
DOI:10.1109/SC.2012.68