Performance analysis of a non-beacon enabled IEEE 802.15.4 network with retransmission and ACK mode

TL;DR

This paper evaluates the performance of non-beacon IEEE 802.15.4 networks with ACK and retransmission limits, using analytical models and neural networks to predict key parameters for practical deployment.

Contribution

It introduces analytical models for non-beacon IEEE 802.15.4 networks and trains neural networks to predict network performance parameters.

Findings

Analytical models accurately predict throughput and reliability.

Neural networks effectively forecast node number and delay.

Models assist practical network deployment decisions.

Abstract

The aim of our work is to evaluate the performance of non-beacon IEEE 802.15.4 networks with acknowledgement (ACK) mode and retransmission limits in a finer time unit. Moreover, we predict network performance parameters using backpropagation artificial neural networks (BP-ANNs) with respect to a given quality of service for real-world applications. Therefore, our proposed methods can assist the deployment of a star network with its performance specified in a more practical way. First, the discrete time Markov chain model and M/M/1/k queue are used to describe the full unslotted carrier sense multiple access with collision avoidance (CSMA/CA) algorithm in a non-beacon network. Considering MAC buffer size, unsaturated traffic, and saturated traffic, we build three analytical models to derive eight important performance metrics, e.g., throughput, delay, and reliability. In addition, extensive simulation results show the accuracy of the analytical models in throughput and reliability. Finally, we use the analytical data to train the BP-ANNs models to predict the key parameters such as node number and delay. All results from the simulation data used to test the BP-ANNs show the accuracy these models. Thus, these methods and results can be used to deploy star networks in application environments.