Anton Cervin

Real Time Scheduling Theory: A Historical Perspective

In this 25th year anniversary paper for the IEEE Real Time Systems Symposium, we review the key results in real-time scheduling theory and the historical events that led to the establishment of the current real-time computing infrastructure. We conclude this paper by looking at the challenges ahead of us.

How does control timing affect performance? Analysis and simulation of timing using Jitterbug and TrueTime

To achieve good performance in systems with limited computer resources, the constraints of the implementation platform must be taken into account at design time. To facilitate this, software tools are needed to analyze and simulate how timing affects control performance. This article describes two such tools: Jitterbug and TrueTime.

An introduction to control and scheduling co-design

The paper presents the emerging field of integrated control and CPU-time scheduling, where more general scheduling models and methods that better suit the needs of control systems are developed. This creates possibilities for dynamic and flexible integrated control and scheduling frameworks, where the control design methodology takes the availability of computing resources into account during design and allows online trade-offs between control performance and computing resource utilization.

JITTERBUG: a tool for analysis of real-time control performance

The paper presents JITTERBUG, a MATLAB-based toolbox for real-time control performance analysis. The control system is described using a number of connected continuous-time and discrete-time linear systems driven by white noise. The control performance is measured by a continuous-time quadratic cost function. A stochastic timing model is used to describe when the different discrete-time systems are updated during the control period. Building different models, the tool makes it easy to investigate how the control performance is affected by e.g. delay, jitter, lost samples, aborted computations, and jitter compensation. Aperiodic and multi-rate controllers may also be studied. The tool is also capable of computing the spectral densities of the different signals in the system.

A Matlab toolbox for real-time and control systems co-design

The paper presents a Matlab toolbox for simulation of real-time control systems. The basic idea is to simulate a real-time kernel in parallel with continuous plant dynamics. The toolbox allows the user to explore the timely behavior of control algorithms, and to study the interaction between the control tasks and the scheduler. From a research perspective, it also becomes possible to experiment with more flexible approaches to real-time control systems, such as feedback scheduling. The importance of a more unified approach for the design of real-time control systems is discussed. The implementation is described in some detail and a number of examples are given.

Improved scheduling of control tasks

The paper considers the implementation of digital controllers as real-time tasks in priority-preemptive systems. The performance of a digital feedback control system depends critically on the timing of its sampling and control actions. It is desirable to minimize the computational delay in the controller as well as the sampling jitter and the control jitter. It is shown that by scheduling the two main parts of a control algorithm as separate tasks, the computational delay can often be reduced significantly. A heuristic method for assigning deadlines to the parts is presented. Further modifications are given to reduce the jitter and to facilitate delay compensation. The result is improved control performance under maintained schedulability.

Implementation-Aware Embedded Control Systems

Most embedded control systems have constrained computationalresources. This makes codesign of the control algorithms and thereal-time scheduling an interesting issue. There is also a strongtrend in the real-time community of moving away from the hardreal-time model. Hence, embedded controllers must be designed sothat they are aware of the resource constraints and timinguncertainty of the implementation platform. This paper discussestemporal determinism, design approaches, and codesign tools for suchsystems.