Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach

TL;DR

This paper introduces a communication-efficient federated learning framework with a novel attention-based CNN-LSTM model for accurate, privacy-preserving anomaly detection in industrial IoT time-series data, achieving significant communication reduction.

Contribution

It proposes a new federated learning framework with an attention-based CNN-LSTM model and gradient compression for industrial anomaly detection, enhancing accuracy and privacy.

Findings

Achieves 50% reduction in communication overhead.

Demonstrates high anomaly detection accuracy on real-world datasets.

Effectively balances timeliness and privacy in industrial IoT applications.

Abstract

Since edge device failures (i.e., anomalies) seriously affect the production of industrial products in Industrial IoT (IIoT), accurately and timely detecting anomalies is becoming increasingly important. Furthermore, data collected by the edge device may contain the user's private data, which is challenging the current detection approaches as user privacy is calling for the public concern in recent years. With this focus, this paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT. Specifically, we first introduce a FL framework to enable decentralized edge devices to collaboratively train an anomaly detection model, which can improve its generalization ability. Second, we propose an Attention Mechanism-based Convolutional Neural Network-Long Short Term Memory (AMCNN-LSTM) model to accurately detect anomalies. The AMCNN-LSTM model uses attention mechanism-based CNN units to capture important fine-grained features, thereby preventing memory loss and gradient dispersion problems. Furthermore, this model retains the advantages of LSTM unit in predicting time series data. Third, to adapt the proposed framework to the timeliness of industrial anomaly detection, we propose a gradient compression mechanism based on Top-\textit{k} selection to improve communication efficiency. Extensive experiment studies on four real-world datasets demonstrate that the proposed framework can accurately and timely detect anomalies and also reduce the communication overhead by 50\% compared to the federated learning framework that does not use a gradient compression scheme.