Influence of different system abstractions on the performance analysis of distributed real-time systems

Abstract

System level performance analysis plays a fundamental role in the design process of real-time embedded systems. Several different approaches have been presented so far to address the problem of accurate performance analysis of distributed embedded systems in early design stages. The existing formal analysis methods are based on essentially different concepts of abstraction. However, the influence of these different models on the accuracy of the system analysis is widely unknown, as a direct comparison of performance analysis methods has not been considered so far. We define a set of benchmarks aimed at the evaluation of performance analysis techniques for distributed systems. We apply different analysis methods to the benchmarks and compare the results obtained in terms of accuracy and analysis times, highlighting the specific effects of the various abstractions. We also point out several pitfalls for the analysis accuracy of single approaches and investigate the reasons for pessimistic performance predictions.

Modeling and Validating Distributed Embedded Real-Time Systems with VDM++

“…To the best of our knowledge, it is the first time that such a quantitative comparison was performed on a single case study at this scale, although there exist several surveys that attempt to make a qualitative comparison. The exception being the recent work of Perathoner et al reported in [79,81]. They investigated the influence of system abstractions on the performance analysis of distributed real-time systems, applying several different techniques to a set of well-known benchmark problems and concluded that the accuracy of the various approaches may differ significantly and that none of the methods performs best in all cases.…”

“…Furthermore, other researchers have looked at different aspects of the case study, such as [35], [36], [12] or use different approaches to construct quantitative performance models, such as [34,37] and [33]. Last but not least, the comparison was continued with a significantly larger scope involving more case studies and additional tools in [81]. The authors of this paper also exposed a problem in the timed automata models presented earlier in [51] which has been corrected in this thesis.…”

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

“…At first, comparison is made with some examples used in [14] with respect to the tightness of the WCRT. Afterwards, we use randomly generated graphs to evaluate the practical value of the proposed technique.…”

“…The state-of-the-art ILP solver CPLEX [16] is used for ILP solution. Figure 7(a) and (b) show two small-size examples with which several approaches are compared in [14] as shown in Figure 7. All starting offsets are set to 0.…”

Formal Modeling and Scheduling of Datapaths of Digital Document Printers

“…In particular, timed automata technology has been applied successfully to optimal planning and scheduling problems [7,1], and performance analysis of distributed real-time systems [8,12]. A timed automaton is a finite automaton extended with clock variables, which are continuous variables with rate 1.…”