Correlating resource demand information with ARM data for application services
Proceedings of the 1st international workshop on Software and performance
httperf—a tool for measuring web server performance
ACM SIGMETRICS Performance Evaluation Review
ϵ-Descending Support Vector Machines for Financial Time Series Forecasting
Neural Processing Letters
Parameter estimation for performance models of distributed application systems
CASCON '95 Proceedings of the 1995 conference of the Centre for Advanced Studies on Collaborative research
Support Vector Regression and Classification Based Multi-View Face Detection and Recognition
FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
A tutorial on support vector regression
Statistics and Computing
Exploiting nonstationarity for performance prediction
Proceedings of the 2nd ACM SIGOPS/EuroSys European Conference on Computer Systems 2007
Performance impacts of autocorrelated flows in multi-tiered systems
Performance Evaluation
CPU demand for web serving: Measurement analysis and dynamic estimation
Performance Evaluation
Service System Resource Management Based on a Tracked Layered Performance Model
ICAC '06 Proceedings of the 2006 IEEE International Conference on Autonomic Computing
Real-time performance modeling for adaptive software systems
Proceedings of the Fourth International ICST Conference on Performance Evaluation Methodologies and Tools
Estimating service resource consumption from response time measurements
Proceedings of the Fourth International ICST Conference on Performance Evaluation Methodologies and Tools
Resource demand modeling for multi-tier services
Proceedings of the first joint WOSP/SIPEW international conference on Performance engineering
Hi-index | 0.00 |
Adaptive performance management solutions often rely on models that require accurate resource demand measures that are estimated in an on-line manner. However it is typically not possible to directly measure resource demands at the abstraction they are needed, e.g., for a software service within an application server that is invoked by a URL. For such cases, linear regression techniques are often used to estimate resource demands. We evaluate the effectiveness of the Least Squares (LSQ) and Least Absolute Deviations (LAD) regression techniques, used extensively by others, as well as Support Vector Regression (SVR) for the purpose of demand estimation. To the best of our knowledge SVR has not yet been evaluated for computer resource demand estimation. We consider the predictive accuracy of these methods for three different real and simulated workloads. Our results demonstrate the importance of tuning the regression parameters of the techniques. We propose an on-line method named Mix Driven On-line Resource Demand Estimation (MODE) that automatically and quickly tunes the regression parameters for LSQ, LAD, and SVR to achieve their best results. The method is novel in that it relies on pre-defined workload mixes with known aggregate demand values to support the tuning exercise. We show that when employed in an on-line manner, tuning with respect to pre-defined mixes is significantly more accurate than the traditional approach of using only step by step data.