Premium
Clustering Categories for Better Prediction of Computer Resources Utilizations
Author(s) -
Benjamini Yoav,
Igbaria Magid
Publication year - 1991
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2347594
Subject(s) - cluster analysis , computer science , data mining , artificial intelligence , data science
SUMMARY In computer performance evaluation it is useful to be able to predict the level at which a job utilizes some computer hardware from its levels of utilization of other hardware resources. In a heterogeneous computing environment different categories of job may have different utilization patterns, and prediction may further depend on the category to which the job belongs. In this paper we present an algorithm for estimating a prediction function based on some continuous predictors and the membership in a category. The algorithm yields a tree structure of clusters of categories, with a single prediction function for all categories in the same cluster. An example of the algorithm's application is given.