Machine Learning Methods for Monitoring of Quasi-Periodic Traffic in Massive IoT Networks
This addresses the challenge of network performance monitoring for IoT deployments, but it appears incremental as it adapts existing methods to a specific domain.
The paper tackles the problem of monitoring link status in massive IoT networks with quasi-periodic traffic, which can be confused with failures, by presenting traffic models and both supervised and unsupervised machine learning methods for applications like smart-metering and environmental monitoring.
One of the central problems in massive Internet of Things (IoT) deployments is the monitoring of the status of a massive number of links. The problem is aggravated by the irregularity of the traffic transmitted over the link, as the traffic intermittency can be disguised as a link failure and vice versa. In this work we present a traffic model for IoT devices running quasi-periodic applications and we present both supervised and unsupervised machine learning methods for monitoring the network performance of IoT deployments with quasi-periodic reporting, such as smart-metering, environmental monitoring and agricultural monitoring. The unsupervised methods are based on the Lomb-Scargle periodogram, an approach developed by astronomers for estimating the spectral density of unevenly sampled time series.