Analytic real-time analysis and timed automata: a hybrid methodology for the performance analysis of embedded real-time systems

Abstract

This paper presents a compositional and hybrid approach for the performance analysis of distributed real-time systems. The developed methodology abstracts system components by either flow-oriented and purely analytic descriptions or by state-based models in the form of timed automata. The interaction among the heterogeneous components is modeled by streams of discrete events. In total this yields a hybrid framework for the compositional analysis of embedded systems. It supplements contemporary techniques for the following reasons: (a) state space explosion as intrinsic to formal verification is limited to the level of isolated components; (b) computed performance metrics such as buffer sizes, delays and utilization rates are not overly pessimistic, because coarse-grained analytic models are used only for components that conform to the stateless model of computation. For demonstrating the usefulness of the presented ideas, a corresponding tool-chain has been implemented. It is used to investigate the performance of a two-staged computing system, where one stage exhibits state-dependent behavior that is only coarsely coverable by a purely analytic and stateless component abstraction. Finally, experiments are performed to ascertain the scalability and the accuracy of the proposed approach.

Arrival Curves for Real-Time Calculus: The Causality Problem and Its Solutions

“…Actually, except [1], the papers do not give answer to them. We will see that [7,3] do not create curves with forbidden regions while [13] could at least in theory, and we explain why. Each of the tools would badly behave in the presence of forbidden regions, and this paper gives a way to get rid of them before using any tool.…”

“…Getting rid of these counter-examples sometimes requires heavyweight state exploration techniques (for example, the -causal option of lesar [15] does this for Boolean programs) but not all tools are able to do it (nbac [5] cannot, for example, and the problem is known to be undecidable for integer programs). The technique that translates the constraints of arrival curves into a model to be analyzed by a verifier tool was used for, e.g., timed automata [7,3], event count automata [13] and synchronous programs [1]. For each tool, one can pose the questions: "what is the behavior of the tool when used on curves with forbidden regions?"…”

“…Indeed, the recent works that interfaces RTC with state-based models face the problem. In [7], the authors get rid of it by constraining the class of curves they compute which are causal by definition (the extension to arbitrary curves which is part of their future works will have to deal with it though). But, in [10], the output curves are computed, one point at a time on an abstract model: this does result into non causal curves, which are refined after being computed.…”

“…System properties may then be computed using algebraic techniques in a compositional way. A wellknown limitation of RTC is that it cannot model systems with states and recent works [7,1,13,11] studied how to interface RTC curves with statebased models. Doing so, while trying, for example to generate a stream of events that satisfies some given pair of curves, we faced a causality problem [14]: it can be the case that, once having generated a finite prefix of an event stream, the generator deadlocks, since no extension of the prefix can satisfy the curves anymore.…”

An ILP-based Worst-case Performance Analysis Technique for Distributed Real-time Embedded Systems

“…To improve the solution quality, a hybrid approach between the MPA and Uppaal has been proposed in [12] where different analysis techniques can be used for intracomponent analysis. The critical processing components for accurate estimation are analyzed by model checking and the others are analyzed by real-time calculus to make a good compromise between the accuracy and the computation speed.…”