| B. Wittenmark, J. Nilsson, and M. Trngren. Timing problems in real-time control systems. In Proceedings of the 1995. |
.... via strictly periodic dummy task) In addition, taking into account the different ways of implementing a control loop, different control system models (descriptions) will apply depending on the control loop implementation strategy (discrete time system [4] discrete time system with time delays [10] and discrete time system with actuation in the next sampling [4] Both task approaches (single task or multitask) implementing a control loop may violate one or more control loop assumptions when scheduled in a multitasking real time system due to the introduced jitters. Sampling may be not ....
Wittenmark B., J. Nilsson and M. T rngren. Timing Problems in Real-Time Control Systems . Proc. Of the American Control Conference. US. 1995
....[Sanfridson no. 2, 2000] 2.2.1 Outline Paper A is a state of the art report (a survey) of what is called the timing problems, here defined to be control delay, choice of control period, jitter in period and delay and finally transient error. This definition of the timing problems emanates from [Wittenmark et al. 1995], and is extended by the author by adding the control period. The reason for this is that the timing problems should represent all the temporal properties added when introducing a digital controller. The timing problems are seen from a control engineering perspective, but defined by terminology ....
B. Wittenmark, J. Nilsson, M. Trngren, "Timing Problems in Real-Time Control Systems", ACC 95, 1995.
....control delay and jitter are often assumed to be negligible and it is further assumed that there is no transient error. The interface is rather simple: the sampling period is constant, the delays are small, jitter is negligible, deadlines are hard, and there is never any transient error, see e.g. [Wittenmark et al. 1995]. The digital control theory is actually evolved from these premises. It seems likely that a change of this agreed cut between the disciplines can lead to an improvement to the application as a whole, hopefully without making the design process too complex. The timing problems is another ....
....three reasons: it is subjective, it is difficult to relate weights to cost and components of the weight vector might not be mutually independent. 2. 2 Characteristics of timing problems As mentioned before, the timing problems can be divided into control delay, jitter and transient error as in [Wittenmark et al. 1995]. This enumeration of time related properties is completed by adding the choice of control period. The definition of timing problems used here incorporates four temporal properties of a computer system, as seen from an automatic control point of view. The report is structured according to this ....
B. Wittenmark, J. Nilsson, M. Trngren, "Timing Problems in Real-Time Control Systems", ACC 95, 1995. 53
....index measured as a quadratic loss function. Practice in control engineering is to assume a computer system to have constant or negligible execution and communication delays, no jitter in delay or period, and never any failure of the computer system to actuate the control law, see [5] 6] 8] and [9]. These items all affect the control performance. See the first list in this subsection. The measure of quality provided by control 4 theory is however more closely related to the dynamical properties of the application. If control performance as a function of the temporal behaviour of the system ....
B. Wittenmark, J. Nilsson, M. Trngren, "Timing Problems in Real-Time Control Systems", ACC 95, 1995.
....a set of rules. Establishment of performance and reliability requirements must be related to limited resources. When implementing a control law, it is frequently assumed that: 1) the sampling rate is fixed, 2) control delay is negligible, 3) jitter is negligible and 4) no transient error occurs, [WIT95]. The timing problems address both computer and control engineering. In the synthesis of control and computer design the requirements of the application must be made clear to fully utilize the potential of the embedded distributed computer system. The aim is a fault tolerant and flexible computer ....
....the sampling period, hence a change of control algorithm (or its coefficients) and period has to be coordinated. The switch of controllers or parameters should be bumpless. Intentional changes of control period gives a possible way to achieve graceful degradation after permanent hardware failure, [WIT95]. In [ABD97] the QoS model proposed is used together with a service which manages a pool of distributed processing resources. The idea is to give each task the best level of guaranteed service while maintaining a satisfactory distribution of tasks among the processing resources. The contention ....
B. Wittenmark, J. Nilsson, M. Trngren, "Timing Problems in Real-Time Control Systems", ACC 95, 1995.
....An objective measurement of quality is a justification for applying the notion of QoS to feedback control. The timing properties that play a vital role in computer control can be divided into the timing problems: control delay, jitter, sampling period and effects of transient errors, see [3], 4] and [5] An example is the selection of sampling period. The choice of sampling period is usually based on rules of thumb, because a small change in sampling period does not make a decisive quality improvement on the margin, see Figure 1. Hence, this could be divided into a range of ....
B. Wittenmark, J. Nilsson, M. Trngren, "Timing Problems in Real-Time Control Systems", ACC 95, 1995.
....control loops. In a distributed control loop, sensors are connected to remote nodes, and actuator nodes receive sensor values over the network. To achieve sufficient control performance without excessive sampling rates it is important to minimize timing variations in sampling and actuation [15]. The most important factors for temporal behavior are the choice of task and communication scheduling policy, and whether or not a global time is used. In this paper we will therefore compare the timing characteristics of a control function when fixed priority and static cyclic scheduling is ....
....6. 2. Related work We focus specifically on control aspects of scheduling in distributed systems. Timing problems in real time systems are discussed in e.g. 5] and [8] but they do not treat distributed systems. Timing problems are described from a more control oriented perspective in e.g. [15] and [14] In [7] an event triggered (CAN) and a static cyclic, or time triggered, protocol (TTP) are compared regarding protocol services, dependability aspects, performance and system design issues. The paper also mentions problems with timing variations but does not go into details regarding ....
B. Wittenmark, J. Nilsson, and M. Trngren, "Timing Problems in Real-Time Control Systems," presented at 1995 IFAC American Control Conference, Seattle, Washington, 1995.
....systems require an agreed timebase. The timebase is represented by a number of clocks, one in each node, that are synchronized at regular intervals. Synchronized clocks are used in distributed control systems to avoid timing variations that would otherwise result in poor control performance [1]. In safety critical systems, synchronized clocks are necessary for many fault tolerance mechanisms. Numerous clock synchronization methods for distributed systems have been presented. In this paper we will concentrate on clock synchronization in safety critical systems using a broadcast bus. We ....
B. Wittenmark, Nilsson, J, Trngren, M, "Timing problems in real-time control systems," presented at 1995 American Control Conference, Seattle, Washington, 1995.
....systems require an agreed timebase. The timebase is represented by a number of clocks, one in each node, that are synchronized at regular intervals. Synchronized clocks are used in distributed control systems to avoid timing variations that would otherwise result in poor control performance [1]. In safety critical systems, synchronized clocks are necessary for many fault tolerance mechanisms. Numerous clock synchronization methods for distributed systems have been presented. In this paper we will concentrate on clock synchronization in safety critical systems using a broadcast bus. We ....
B. Wittenmark, Nilsson, J, Trngren, M, "Timing problems in real-time control systems," presented at 1995 American Control Conference, Seattle, Washington, 1995.
....to control performance e.g. in terms of path profiles, velocities, accelerations or in the frequency domain in terms of closed loop bandwidth. Refining the timing requirements. Time triggering has so far been a prerequisite for the implementation of discrete time sampled data systems, see Nilsson et al. 1998). However, within DICOSMOS, also a theory for event triggered sampling is being investigated, Bernhardsson (1998) For other control tasks, the implementation of triggers, i.e. the use of time or event triggering needs to be decided (i.e. polling vs. interrupts) some of the trade offs are ....
....constant, and feedback loops in multirate systems are assumed to be synchronized, Trngren (1998) In this process of timing requirements analysis and conceptual design, solutions from the control engineering perspective vs. from the computer engineering side need to be considered as discussed by Nilsson et al. 1998). Highly related is the support for the required information interaction and iterations between control and computer engineering; some examples are given here (taken from Trngren et al. 1995) Nilsson et al. 1998) Claesson et al. 1998) Useful information from control to computer ....
[Article contains additional citation context not shown here]
Nilsson J., Wittenmark B., Trngren M., Sanfridson M. (1998). Timing Problems in Real-time Control Systems. In Research problem formulations in the DICOSMOS project. See Trngren and Sanfridson (1998).
No context found.
Nilsson J., Wittenmark B., Trngren M., Sanfridson M. Timing Problems in Real-time Control Systems. In Research problem formulations in the DICOSMOS project. Technical Report, Dept. of Machine Design, The Royal Institute of Technology, Stockholm. TRITA-MMK 1998:20, ISSN 14001179, ISRN KTH/MMK/R--98/20--SE.
No context found.
B. Wittenmark, J. Nilsson, and M. Trngren. Timing problems in real-time control systems. In Proceedings of the 1995.
No context found.
Wittenmark, B.; J. Nilsson; M. Torngren. Timing problems in real-time control systems. Proceedings of the
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC