Ulrich Klehmet

Compositional performance modelling with the TIPPtool

Stochastic process algebras have been proposed as compositional specification formalisms for performance models. In this paper, we describe a tool which aims at realising all beneficial aspects of compositional performance modelling, the TIPPtool. It incorporates methods for compositional specification as well as solution, based on state-of-the-art techniques, and wrapped in a user-friendly graphical front end. Apart from highlighting the general benefits of the tool, we also discuss some lessons learned during development and application of the TIPPtool. A non-trivial model of a real life communication system serves as a case study to illustrate benefits and limitations.

Stochastic and deterministic performance evaluation of automotive CAN communication

The performance of communication systems can be evaluated using various distinct techniques and paradigms, e.g. queuing theory, simulation or worst case analysis. Mean values for performance measures like transmission delay, queue length or system utilization are valuable information for network dimensioning. However, in many cases, quantile-based approaches or deterministic upper bounds are indispensable, especially for systems that need real-time guarantees. A typical application area are safety-critical functions in automotive environments, where hard real-time transmission deadlines have to be met to assure safe operation of the vehicle. In this paper, we investigate a contemporary automotive in-car communication system, the Controller Area Network (CAN). A simulation study of the system yields stochastic quantile-related use case performance measures for non-time-critical communication. It is complemented by a deterministic evaluation using Network Calculus, which allows to determine worst case transmission times and provides closed and easily applicable formulas for delay bounds of messages on all priority levels. Comprising the outcomes from this dual evaluation approach supports the design, dimensioning and parameterization of the overall CAN bus system with respect to both hard real-time demands and performance characteristics in typical use case scenarios.

Real-Time Guarantees for CAN Traffic

Modern cars comprise a multitude of electronic features which are implemented in tens of communicating control units. To connect these in-car embedded systems, the CAN bus offers a sustainable performance, hence it is used as a widespread communication infrastructure, even for safety critical applications. However, CAN media access is priority based and performed competitive and non-preemptive. Thus, assessing the worst case end-to-end delay is inevitable in order to provide safe and efficient operation of functions with hard real-time properties. In this paper, we use the analytical method of network calculus to determine guaranteed upper bounds for transmission delays of all CAN priorities. We demonstrate the applicability of our approach by investigating current real-life CAN communication data from the German car manufacturer Audi.

Compositional Performance Modelling with TIPPtool

Stochastic Process Algebras have been proposed as compositional specification formalisms for performance models. In this paper, we describe a tool which aims at realising all beneficial aspects of compositional performance modelling, the TIPPtool. It incorporates methods for compositional specification as well as solution, based on state-of-the-art-techniques, and wrapped in a user-friendly graphical front end.

A Framework for Establishing Performance Guarantees in Industrial Automation Networks

In this paper we investigate the application of Network Calculus for industrial automation networks to obtain performance bounds (latency, jitter and backlog). In our previous work we identified the modeling of industrial networks as the most challenging aspect since in industry most users do not have detailed knowledge about the traffic load caused by applications. However, exactly this knowledge is indispensable when it comes to modeling the corresponding arrival curves. Thus, we suggest the use of generalized traffic profiles, which are provided by the engineering tool. During the engineering process, the user has to specialize these profiles to meet the application configurations. The engineering tool derives the corresponding arrival curves from the specialized profiles and calculates the performance bounds using Network Calculus. To guarantee that the calculated performance bounds are kept during the runtime of the industrial automation, we must ensure that the real traffic flows do not exceed their engineered arrival curves. We therefore propose the use of shapers at the edge of the network domain. The shaper configurations can be automatically derived from the engineered arrival curves of the flows.