INTEGRATION OF ANN MLP AND COMPUTER SIMULATION FOR INTELLIGENT DESIGN OF QUEUING SYSTEMS
Ali Azadeh and Zahra Faiz
Summer Computer Simulation Conference 2007 (SCSC 2007)
San Diego, California (USA), July 15-18, 2007
Abstract
This paper describes a framework for design and development of intelligent simulation environment for queuing system. The intelligent simulation environment utilizes Artificial Neural Network (ANN) to simulate and optimize a complex queuing system. The integrated simulation ANN model is a computer program capable of improving its performance by referring to production constraints, system's limitations and desired targets. It is a goal oriented, flexible and integrated approach and produces the optimum solution by utilizing Multi Layer Perceptron (MLP). The properties and modules of the prescribed intelligent simulation ANN are: 1) parametric modeling, 2) flexibility module, 3) integrated modeling, 4) knowledge-base module, 5) integrated database and 6) learning module. The integrated simulation ANN is applied to 30 distinct G/G/K queuing systems. Furthermore, its superiority over conventional simulation approach is shown in two dimensions which are running time and number of required iterations.