Towards a cognitive MAC layer: Predicting the MAC-level performance in Dynamic WSN using Machine learning

TL;DR

This paper proposes a machine learning-based approach to predict MAC layer performance in dynamic wireless sensor networks, enabling more reliable and predictable network behavior in low-power applications.

Contribution

It introduces a data-driven method using neural networks for real-time MAC performance prediction in WSNs, validated through extensive experiments and trace-driven evaluation.

Findings

Neural network models outperform other machine learning techniques.

The approach achieves accurate real-time performance prediction.

Extensive experiments validate the effectiveness of the model.

Abstract

Predictable network performance is key in many low-power wireless sensor network applications. In this paper, we use machine learning as an effective technique for real-time characterization of the communication performance as observed by the MAC layer. Our approach is data-driven and consists of three steps: extensive experiments for data collection, offline modeling and trace-driven performance evaluation. From our experiments and analysis, we find that a neural networks prediction model shows best performance.