Performance modelling and cost-effective analysis of multiservice integrated networks

The performance prediction and quantitative analysis of multiservice integrated networks are extremely important in view of their ever expanding usage and the multiplicity of their component parts together with the complexity of their functioning. Queueing network models (QNMs) are widely recognised as powerful and realistic tools for representing these systems as complex networks of queues and servers and optimising their performance. This paper highlights the use of cost-effective methodologies as applied to performance modelling studies involving QNMs of asynchronous transfer mode (ATM) switch architectures with bursty and/or correlated traffic. These methodologies offer simple and practical means for performance evaluation and prediction and have their roots in the principle of maximum entropy (ME), queueing theoretic concepts and batch renewal processes for traffic characterisation. Comments on current theoretical advances and future research work are included