A Comparative Study of Accuracy and Efficiency Using Artificial Neural Networks for Simulating M^a/M/s Queuing Models

Abstract

This study explores the use of artificial neural networks (ANNs) for simulating Mᵃ/M/s queuing models, which are essential in queuing theory for analyzing multi-server systems. By employing ANNs, we aim to capture and replicate the complex dynamics of these queuing systems more effectively. The study demonstrates how ANNs can provide accurate and efficient simulations, enhancing the understanding and optimization of queuing processes. We compare the results obtained from ANN simulations with traditional analytical methods to assess their accuracy and efficiency. The findings highlight the potential of ANNs to address the challenges posed by variable arrival and service rates, offering valuable insights for improving decision-making and resource allocation in real-world applications. This research underscores the effectiveness of ANNs in modeling and simulating complex queuing systems, contributing to advancements in both theoretical and practical domains.