240 likes | 413 Views
A pattern fusion model for multi-step-ahead CPU load prediction. Systems and Software Dingyu Yanga , Jian Caoa ,∗, Jiwen Fua , Jie Wangb , Jianmei Guoc 鍾舜璽. Introduction.
E N D
A pattern fusion model for multi-step-ahead CPU load prediction Systems and Software DingyuYanga, JianCaoa,∗, JiwenFua, JieWangb, JianmeiGuoc 鍾舜璽
Introduction • Resource availability often changes from time to time and schedulers needs a global view of all resources in a distributed system. • Sometimes high CPU load means performance anomalies that may result in system collapse.
WNN and PSF • Weighted Nearest Neighbors (WNN) algorithm • Pattern Sequence-based Forecasting (PSF) algorithm • Euclidean distance • not enough to match the similar patterns.
WNN and PSF (cont.) • One-step-ahead prediction strategy • if the one-step-ahead value is not accurate, the predictions for the following points in time will become more and more inaccurate.
A pattern fusion model for multi-step-ahead CPU load prediction
Pattern extraction (cont.) • Pattern filtering • Pattern merging
Pattern matching (cont.) • Pattern similarity matching • Euclidean distance matching • Fluctuation pattern set matching
Pattern weighting strategy • Average rule strategy
Pattern weighting strategy (cont.) • Uniform decline strategy
Prediction results function • Adaboost algorithm
Prediction results function (cont.) • Prediction values from different values of various length patterns:
Experiment • Experiment settings • Mean absolute error (MAE) • Mean relative error (MRE)
Experiment (cont.) • Pattern similarity measurement • The influences of filter parameter
Experiment (cont.) • Different pattern weighting strategies • Multi-step-ahead predictions
Experiment (cont.) • Comparison with iterative one-step-ahead prediction
Experiment (cont.) • Comparisons with other prediction approaches • Run time
Conclusion • The contribution of this paper is a fusion model for multi-step-ahead CPU load prediction. • We plan to consider longer steps and improve the prediction accuracy in future. • In addition, multivariate prediction, such as memory usage and disk usage predictions are also interesting topics.