The Effect of Redundancy and Repair on the Performability of Distributed Real-Time Control Systems with RepetItive Task Invocation
A. Shallof, Stuart Bennett · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · 1994
Distributed real-time control systems depend on producing correct software and proper hardware architecture to support the software. Hardware components degrade with the time and this can lead to hardware failure, which, in a distributed real-time control system may be manifested through the failure of some tasks to meet their deadline. The effect of random failure, repair and redundancy on the completion of tasks of a system by their deadline have been investigated. We show how a system with redundancy and with random failure and repair rates can be modelled using the General Stochastic Petri net approach and how the performability of the system can be calculated using a method based on the modified Laguerre function.