Title: Discrete-time simulation for performance modelling of FIFO single-server queuing system
Authors: Ridhima Mehta
Addresses: School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi, India
Abstract: Optimal queue management is crucial for improving the network operation since packet loss is commonly attributed to the likelihood of buffer overflow at intermediate routers on end-to-end communication path. In this paper, a transient discrete-time simulation model is proposed based on queuing theory served by single-server system and single first-in first-out (FIFO) queue. This queuing service framework effectively enforces the best-effort service to the streams of incoming data packets across the network with disparate quality of service (QoS) requirements. We plot the network performance measures such as queue length, delay, server utilisation and packet lifetime to validate the practical wireless systems. Besides, we employ conventional multiple-objective genetic algorithm to model the trade-off among key queuing system parameters including queuing delay, packet drop rate and network bandwidth. Finally, the efficiency of our queuing optimisation model is significantly compared with previous works in terms of bandwidth utilisation, delay, and packet loss rate.
Keywords: FIFO queue; genetic algorithm; packet lifetime; queuing delay; queuing server utilisation.
DOI: 10.1504/IJSCC.2022.122263
International Journal of Systems, Control and Communications, 2022 Vol.13 No.2, pp.112 - 132
Received: 18 May 2020
Accepted: 31 May 2021
Published online: 14 Apr 2022 *