Machine Learning Models for LoRa Wan IoT Anomaly Detection

Abstract

LoRaWAN provides a long-range communication among IoT devices. Since a LoRaWAN gateway becomes a bridge between LoRaWAN nodes and back-end server, it could has potential security risks. We present an anomaly detection system to secure LoRa Wangateway devices by evaluating incoming packet data. To evaluate our proposed system, we build machine learning models using various outlier detection algorithms. We construct and evaluate LoRaWAN dataset from LoRaWAN gateway devices. The simulation and experimental results show that machine learning to address anomaly detection on constrained LoRa Wandevices guarantees feasibility, accu-racy and performance.