Optimal design and performance modelling of M/G/1/K queueing systems

Approximating the performance measures of M/G/1/K systems is a difficult, challenging, and important problem for applications in science and engineering. An approach based on a two-moment approximation of the process is presented and is contrasted with an embedded Markov chain approach, Gelenbeʹs approach, simulation, and finally, the statistics of M/M/1/K systems. The closed form expressions for the different performance measures should be very handy. The use of the approximation in the performance modelling and design of M/G/1/K systems is also explored in order to demonstrate the practical usefulness of the concepts contained within the paper.