Overload management in real-time control applications using (m, k)-firm guarantee

Abstract

AbstractÐTasks in a real-time control application are usually periodic and they have deadline constraints by which each instance of a task is expected to complete its computation, even in the adverse circumstances caused by component failures. Techniques to recover from processor failures often involve a reconfiguration in which all tasks are assigned to fault-free processors. This reconfiguration may result in processor overload where it is no longer possible to meet the deadlines of all tasks. In this paper, we discuss an overload management technique which discards selected task instances in such a way that the performance of the control loops in the system remain satisfactory even after a failure. The technique is based on the rationale that real-time control applications can tolerate occasional misses of the control law updates, especially if the control law is modified to account for these missed updates. The paper devises a scheduling policy which deterministically guarantees when and where the misses will occur. The paper also proposes a methodology for modifying the control law to minimize the deterioration in the control system behavior as a result of these missed control law updates.

EE-(m,k)-firm: Operations Management Approach In Enterprise Environment

“…On the other hand, it is apparent that a system under (m,k)-firm constraints requires less resources than a classic system because some invocations may be disregarded. To effectively manage the tasks under (m,k)-firm constraints, new scheduling algorithms have been proposed [31]. They are divided into two main groups.…”

Survey of Real-Time Communication in CSMA-Based Networks

“…On the other hand, it is also allowed that the HC starts a TXOP during the CP. 1 Similarly to the PCF scheme, the HC also polls all the stations in the polling list, even though some stations may have no messages to transmit. When the HC polls a station that has no packets to transfer, the station will transmit a null frame, after the QoS CF-poll.…”

“…EQuB allows the coexistence of RT and non-RT traffic on the same network domain, providing a bounded access delay to RT packets. The EQuB 1 mechanism is based on the assumption that RT stations generate packets in specific intervals, designated as sessions. During a session, RT stations expect to have undisputed access to the medium through the EQuB mechanism.…”

Generalized Elastic Scheduling

“…For example, Ramanathan et al proposed both online [15] and offline [24] scheduling algorithms that are based on the (m,k) model, which is analyzed in [16]. In this model, up to k − m consecutive jobs are allowed to be dropped in any sliding window of k. Moreover, [28] presented the Dynamic Window-Constrained Scheduling (DWCS) algorithm, which is similar except that the window k is fixed.…”