A Tool for Statistical Analysis of Hard Real-Time Scheduling Algorithms

In this paper we shall consider a simulation language (and a tool) for the simulation of scheduling algorithms for real-time systems. In the rst part of this paper we recall some notion on real-time systems and their scheduling algorithms. The second part of the work presents our tool. We rst present shortly the simulation kernel (issued from previous work 3]) which is well suited to simulate the behavior of a single real-time system with some scheduling algorithm. Next, we show the limitations of the simulation kernel and the interest to simulate scheduling algorithms on a large number of task sets in order to be able to perform statistical analysis on scheduling algorithms. We then present the extensions of our tool and the mechanisms we have added for statistical analysis.