An approach to modelling open networks with unreliable servers and finite buffers.

Networks of queues are extensively used in modelling transaction processing systems, and the interactions among nodes in communication networks. Today, many practical queuing systems widely used in computing and communication have finite capacities. Often, in such systems, servers are prone to failures. In this paper, the performance modelling of a multi-node system, with heterogeneous nodes, each node serving external as well as routed internal arrivals of jobs is considered. An analytical model has been developed with certain approximations, and solved for performability measures. In an attempt to improve accuracy in performability evaluation, assumptions made have been minimised and a series of computations have been performed for open queuing networks with breakdowns, repairs, and finite queuing capacity. Results obtained using the analytical model are validated through simulation and presented.