Execution Time Analysis for Industrial Control Applications

Abstract

Estimating the execution time of software components is often mandatory when evaluating the non-functional properties of software-intensive systems. This particularly holds for real-time embedded systems, e.g., in the context of industrial automation. In practice it is however very hard to obtain reliable execution time estimates which are accurate, but not overly pessimistic with respect to the typical behavior of the software. This article proposes two new concepts to ease the use of execution time analysis for industrial control applications: (1) a method based on recurring occurrences of code sequences for automatically creating a timing model of a given processor and (2) an interactive way to integrate execution time analysis into the development environment, thus making timing analysis results easily accessible for software developers. The proposed methods are validated by an industrial case study, which shows that a significant amount of code reuse is present in a set of representative industrial control applications.