Graph Neural Networks Based Anomalous RSSI Detection

TL;DR

This paper introduces a graph neural network approach that converts time series data into graphs to detect anomalies in wireless links, achieving competitive accuracy with significantly fewer parameters.

Contribution

The paper proposes a novel GNN architecture based on graph attention networks for anomaly detection in wireless links, with improved efficiency and comparable performance.

Findings

Achieves anomaly detection with ~171 times fewer trainable parameters.

Provides competitive results against state-of-the-art methods.

Efficiently detects anomalies at individual measurement levels.

Abstract

In today's world, modern infrastructures are being equipped with information and communication technologies to create large IoT networks. It is essential to monitor these networks to ensure smooth operations by detecting and correcting link failures or abnormal network behaviour proactively, which can otherwise cause interruptions in business operations. This paper presents a novel method for detecting anomalies in wireless links using graph neural networks. The proposed approach involves converting time series data into graphs and training a new graph neural network architecture based on graph attention networks that successfully detects anomalies at the level of individual measurements of the time series data. The model provides competitive results compared to the state of the art while being computationally more efficient with ~171 times fewer trainable parameters.