Estimating Model Parameters of Adaptive Software Systems in Real-Time

Adaptive software systems have the ability to adapt to changes in workload and execution environment. In order to perform resource management through model based control in such systems, an accurate mechanism for estimating the software system’s model parameters is required. This paper deals with real-time estimation of a performance model for adaptive software systems that process multiple classes of transactional workload. First, insights in to the static performance model estimation problem are provided. Then an Extended Kalman Filter (EKF) design is combined with an open queueing network model to dynamically estimate the model parameters in real-time. Specific problems that are encountered in the case of multiple classes of workload are analyzed. These problems arise mainly due to the under-deterministic nature of the estimation problem. This motivates us to propose a modified design of the filter. Insights for choosing tuning parameters of the modified design, i.e., number of constraints and sampling intervals are provided. The modified filter design is shown to effectively tackle problems with multiple classes of workload through experiments.

[1]  Marin Litoiu,et al.  The use of optimal filters to track parameters of performance models , 2005, Second International Conference on the Quantitative Evaluation of Systems (QEST'05).

[2]  Mark S. Squillante,et al.  Workload service requirements analysis: a queueing network optimization approach , 2002, Proceedings. 10th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunications Systems.

[3]  Marin Litoiu,et al.  Service System Resource Management Based on a Tracked Layered Performance Model , 2006, 2006 IEEE International Conference on Autonomic Computing.

[4]  Marin Litoiu,et al.  Performance Model Estimation and Tracking Using Optimal Filters , 2008, IEEE Transactions on Software Engineering.

[5]  Donald F. Towsley,et al.  Smoothing, Statistical Multiplexing, and Call Admission Control for Stored Video , 1997, IEEE J. Sel. Areas Commun..

[6]  Christopher Stewart,et al.  Exploiting nonstationarity for performance prediction , 2007, EuroSys '07.

[7]  Carl M. Harris,et al.  Fundamentals of queueing theory , 1975 .

[8]  D. Ionescu,et al.  A Robust Autonomic Computing Architecture for Server Virtualization , 2008, 2008 International Conference on Intelligent Engineering Systems.

[9]  Asser N. Tantawi,et al.  CPU demand for web serving: Measurement analysis and dynamic estimation , 2008, Perform. Evaluation.

[10]  A. Bemporad,et al.  Model Predictive Control Design: New Trends and Tools , 2006, Proceedings of the 45th IEEE Conference on Decision and Control.

[11]  Asser N. Tantawi,et al.  Enhanced inferencing: estimation of a workload dependent performance model , 2009, VALUETOOLS.

[12]  Fan Zhang,et al.  A Comprehensive Toolset for Workload Characterization, Performance Modeling, and Online Control , 2003, Computer Performance Evaluation / TOOLS.

[13]  D. Simon.  Optimal State Estimation: Kalman, H Infinity, and Nonlinear Approaches , 2006 .

[14]  Matti A. Hiltunen,et al.  Constructing adaptive software in distributed systems , 2001, Proceedings 21st International Conference on Distributed Computing Systems.

[15]  Asser N. Tantawi,et al.  Performance management for cluster-based web services , 2005, IEEE Journal on Selected Areas in Communications.

[16]  Thomas Springer,et al.  A Model-Driven Approach for Developing Adaptive Software Systems , 2008, DAIS.

[17]  Marin Litoiu,et al.  Tracking time-varying parameters in software systems with extended Kalman filters , 2015, CASCON.

[18]  Asser N. Tantawi,et al.  Analytic modeling of multitier Internet applications , 2007, TWEB.

[19]  Marin Litoiu,et al.  A real-time adaptive control of autonomic computing environments , 2007, CASCON.