Schedulability Analysis of Real-Time Systems with Uncertain Worst-Case Execution Times

Schedulability analysis is about determining whether a given set of real-time software tasks are schedulable, i.e., whether task executions always complete before their specified deadlines. It is an important activity at both early design and late development stages of real-time systems. Schedulability analysis requires as input the estimated worst-case execution times (WCET) for software tasks. However, in practice, engineers often cannot provide precise point WCET estimates and prefer to provide plausible WCET ranges. Given a set of real-time tasks with such ranges, we provide an automated technique to determine for what WCET values the system is likely to meet its deadlines, and hence operate safely. Our approach combines a search algorithm for generating worst-case scheduling scenarios with polynomial logistic regression for inferring safe WCET ranges. We evaluated our approach by applying it to a satellite on-board system. Our approach efficiently and accurately estimates safe WCET ranges within which deadlines are likely to be satisfied with high confidence.