Automatic, Model-Based Software Performance Improvement for Component-Based Software Designs

Free registration required

Executive Summary

Formal performance prediction methods, based on queueing network models, allow evaluating software architectural designs for performance. Existing methods provide prediction results such as response times and throughputs, but do not guide the software architect on how to improve the design. The authors propose a novel approach to optimise the expected performance of component-based software designs by automatically generating and evaluating design alternatives. The design space spanned by different design options (e.g., available components and configuration options) is systematically explored using metaheuristic search techniques and performance-domain heuristics.

  • Format: PDF
  • Size: 408.12 KB