Gerhard Fohler

Jitter compensation for real-time control systems

In this paper, we first identify the potential violations of control assumptions inherent in standard real-time scheduling approaches (because of the presence of jitters) that causes, degradation in control performance and may even lead to instability. We then develop practical approaches founded on control theory to deal with these violations. Our approach is based on the notion of compensations wherein controller parameters are adjusted at runtime for the presence of jitters. Through time and memory overhead analysis, and by elaborating on the implementation details, we characterize when offline and on-line compensations are feasible. Our experimental results confirm that our approach does compensate for the degraded control performance when EDF and FPS algorithms are used for scheduling the control tasks. Our compensation approach provides us another advantage that leads to better schedulability of control tasks. This derives from the potential to derive more flexible timing constraints, beyond periods and deadlines necessary to apply EDF and FPS. Overall, our approach provides guarantees offline that the control system will be stable at runtime-if temporal requirements are met at runtime-even when actual execution patterns are not known beforehand. With our approach, we can address the problems due to (a) sampling jitters, (b) varying delays between sampling and actuation, or (c) both-not addressable using traditional EDF and FPS based scheduling, or by previous real-time and control integration approaches.

Efficient scheduling of sporadic, aperiodic, and periodic tasks with complex constraints

Many industrial applications with real-time demands are composed of mixed sets of tasks with a variety of requirements. These can be in the form of standard timing constraints, such as periods and deadlines, or complex, e.g. to express application-specific or nontemporal constraints, reliability, performance, etc. Arrival patterns determine whether tasks are treated as periodic, sporadic or aperiodic. As many algorithms only focus on specific sets of task types and constraints, system design has to focus on those supported by a particular algorithm, at the expense of the rest. In this paper, we present an algorithm to deal with a combination of mixed sets of tasks and constraints: periodic tasks with complex and simple constraints, soft and firm aperiodic tasks and sporadic tasks. Instead of providing an algorithm tailored to a specific set of constraints, we propose an EDF (earliest deadline first) based runtime algorithm and the use of an offline scheduler for complexity reduction to transform complex constraints into the EDF model. At runtime, an extension to EDF, two-level EDF, ensures the feasible execution of tasks with complex constraints in the presence of additional tasks or overloads. We present an algorithm for handling offline guaranteed sporadic tasks, with minimum inter-arrival times, in this context, which keeps track of arrivals of instances of sporadic tasks to reduce pessimism about future sporadic arrivals and to improve the response times and acceptance of firm aperiodic tasks. A simulation study underlines the effectiveness of the proposed approach.

RTSS 2007: Preface

Compositional schedulability analysis of hierarchical scheduling frameworks is a well studied problem, as it has wide-ranging applications in the embedded systems domain. Several techniques, such as periodic resource model based abstraction and composition, have been proposed for this problem. However these frameworks are sub-optimal because they incur bandwidth overhead. In this work, we introduce the explicit deadline periodic (EDP) resource model, and present compositional analysis techniques under EDF and DM. We show that these techniques are bandwidth optimal, in that they do not incur any bandwidth overhead in abstraction or composition. Hence, this framework is more efficient when compared to existing approaches.

Certification-Cognizant Time-Triggered Scheduling of Mixed-Criticality Systems

In many modern embedded platforms, safety-critical functionalities that must be certified correct to very high levels of assurance co-exist with less critical software that are not subject to certification requirements. Recent research in real-time scheduling theory has yielded some promising techniques for meeting the dual goals of (i) being able to certify the safety-critical functionalities under very conservative assumptions, and (ii) ensuring high utilization of platform resources under less pessimistic assumptions. This research has centered on an event-triggered/ priority-driven approach to scheduling. However current practice in many safety-critical domains, including (the safety-critical components of) automotive and avionics systems and factory automation, favors a time-triggered approach. In such time-triggered systems, non-interference of safety-critical components by non-critical ones is ensured by strict isolation between components of different criticalities, although such isolation facilitates the certification of the safety-critical functionalities, it can cause very low resource utilization. The research reported in this document is, to our knowledge, the first to study time-triggered scheduling from the perspective of both ensuring certifiability of high-criticality functionalities, and obtaining high resource utilization as in (i) and (ii) above. We present algorithms for time-triggered scheduling of mixed-criticality systems that offers resource utilization guarantees similar to those of event-triggered scheduling. Since the time-triggered approach currently seems to find greater acceptability with certification authorities, it is hoped that this research will hasten the adoption of these results in building embedded systems that are subject to mandatory certification.

Improving quality-of-control using flexible timing constraints: metric and scheduling

Closed-loop control systems are dynamic systems subject to perturbations. One of the main concerns of the control is to design controllers to correct or limit the deviation that transient perturbations cause in the controlled system response. The smaller and shorter the deviation, the better the achieved performance. However, such controllers have been traditionally implemented using fixed timing constraints (periods and deadlines). This precludes controllers to execute dynamically, accordingly to the system dynamics, which may lead to sub-optimal implementations: although higher execution rates may be preferable when reacting to perturbations in order to minimize the response deviations, they imply wastage of resources when the system is in equilibrium. In this paper we argue and demonstrate that the responsibility of maximizing the performance of closed-loop systems relies on both the controller designer and the scheduler. We show that the dynamic optimization of the quality of the controlled system response calls for (a) flexible control task timing constraints that deliver effective control performance; flexible constraints allow us to achieve faster reaction by adaptively choosing the controller sampling rate and completion time upon transient perturbations, (b) a quality-of-control (QoC) metric; it associates with each control task timing a quantitative value expressing control performance (in terms of the closed-loop system error), and (c) new scheduling approaches; their goal is to quickly react to perturbations by dynamically scheduling tasks based on the chosen control task execution parameters to maximize the QoC. This combination offers the possibility of taking scheduling decisions based on the control information for each control task invocation, rather than using fixed timing constraints with constant periods and deadlines.

Timing constraints of MPEG-2 decoding for high quality video: misconceptions and realistic assumptions

Decoding MPEG-2 video streams imposes hard real-time constraints for consumer devices such as TV sets. The freedom of encoding choices provided by the MPEG-2 standard results in high variability inside streams, in particular with respect to frame structures and their sizes. In this paper, we identify realistic timing constraints demanded by MPEG-2 video decoding. We present results from a study of realistic MPEG-2 video streams to analyze the validity of common assumptions for software decoding and identify a number of misconceptions. Furthermore, we identify constraints imposed by frame buffer handling and discussed their implications on decoding architecture and timing constraints.

Resource Management on Multicore Systems: The ACTORS Approach

High-performance embedded systems require the execution of many applications on multicore platforms and are subject to stringent restrictions and constraints. The ACTORS project approach provides temporal isolation through resource reservation over a multicore platform, adapting the available resources on the basis of the overall quality requirements. The architecture is fully operational on both ARM MPCore and x86 multicore platforms.

Static scheduling of pipelined periodic tasks in distributed real-time systems

Many distributed real time applications involve periodic activities with end to end timing constraints that are larger than the periods. That is, a new instance of a periodic activity will come into existence before the previous instance has been completed. Also, such activities typically involve communicating modules in a distributed system where some modules may be replicated for resilience. For such activities, pipelined execution allows us to meet the various resource and timing constraints imposed on them. We discuss an approach to dealing with the pipelined execution of a set of periodic activities that have the above characteristics. It can be called a meta algorithm since it works in conjunction with another scheduling algorithm-one that creases the actual schedules. The idea is to exploit the existence of many such scheduling algorithms, which, however typically work with activities whose deadlines are equal to or less than their periods. Our meta algorithm invokes such a scheduling algorithm, perhaps multiple times, to generate a pipelined execution for the tasks. The effectiveness of the approach is shown via simulation studies.

The design of real-time systems: from specification to implementation and verification

Presents an engineering approach to the design of distributed real-time systems, which guarantee hard deadlines and can tolerate a specified set of faults. The methodology covers the stepwise refinement of the given requirements, expressed in the form of real-time transactions, to task and protocol executions. It also includes a timing analysis and dependability evaluation of the still incomplete design. The testability of the evolving system is considered to be of essential concern. A set of coherent tools for the support of the methodology is described in some detail. The methodology assumes that the runtime architecture is based on static scheduling, and a globally synchronised time-base is available to co-ordinate the system actions in the domain of real time.

Handling interrupts with static scheduling in an automotive vehicle control system

The requirements of industrial applications only rarely permit the exclusive use of single paradigms in the development of real-time systems. Product cost, reuse of existing solutions, and efficiency require diverse, or even opposing methods to coexist or to be integrated. In this paper, we deal with one problem encountered during the development of a real-time system for motion control in automotive vehicles, the integration of static scheduling and interrupts. The user mandates pre run-time scheduling for a number of reasons, e.g., predictability, testability and low run-time overhead. However, the interrupt overhead cannot be ignored in a safety critical system, and therefore has to be accounted for when creating a static schedule. We propose a method that combines static scheduling and run-time interrupts by applying standard static scheduling techniques and exact analysis. The appropriateness of this method is underlined by successful industrial deployment.