INTEGRATION OF ANN MLP AND COMPUTER SIMULATION FOR INTELLIGENT DESIGN OF QUEUING SYSTEMS

摘要

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) knowledgebase 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.