Simulation of real-time scheduling with various execution time models

Abstract

In this paper, we present SimSo, a simulator that aims at facilitating the design of experimental evaluations for real-time scheduling algorithms. Currently, more than twentyfive algorithms were implemented. Special attention is paid to the execution time model of tasks. We show that the worst-case execution time for experimental simulation can introduce a bias in evaluation and we discuss as a work in progress how cache effects could be taken into consideration in the simulation.