Optimum Machine Performance in Fault-Tolerant Networked Control Systems

This paper investigates the effect of failures on the productivity of fault-tolerant networked control systems under varying loads. Higher speeds of operation are sometimes used to increase production and compensate for down time due to component failures. Improved Markov models are developed and used to calculate system probabilities. When these probabilities are combined with the maximum speed of operation in each system state, the average speed of operation is obtained. If machines cannot be run at maximum speed all the time, the Markov models are used again to find the best speed mix that would yield maximum output capacity