Online Discovery of Quantitative Model for Web Service Management

• Published in: Advances in Natural Computation pp. 539 - 542
• Main Authors: Chen, Jing, Yin, Xiao-chuan, Zhang, Shui-ping
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Database Metrics; Exact sciences and technology; Online Discovery; Quantitative Model; Service Level Agreement; Service Level Agreement Violation; Correlation; Linear regression; Variability; Web service; Regression analysis; Modeling; Time response; Linear model; Workload; Variable metric method; Response time; Least squares method; Database; Metric; Oracle; Quantitative analysis
• ISBN: 9783540283256; 3540283250; 3540283234; 9783540283232
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11539117_77

Due to the existence of strong correlation between database metrics and response times, an online discovery quantitative models system of web service management with the linear least-squares regression algorithms was proposed. The model used the stepwise linear regression algorithms to choose a particular subset from the numerous metrics as the explanatory variables of the model, so it can be updated continuously in response to the changes made in provider configurations and the evolution of business demands. The simulation experiment for Oracle Universal Database under a TPC-W workload chose three most influential metrics that weight 66% of the variability of response time.The results show that the effectiveness of quantitative model constructing system and model constructing algorithms.