VARADE: a Variational-based AutoRegressive model for Anomaly Detection on the Edge
This addresses latency and bandwidth issues in cloud-based anomaly detection for Industry 4.0, offering a practical edge solution, though it appears incremental as it builds on existing variational and autoregressive techniques.
The paper tackles the problem of detecting complex anomalies in Industry 4.0 data by proposing VARADE, a lightweight autoregressive model based on variational inference for edge deployment, achieving the best trade-off in accuracy, power consumption, and inference frequency on robotic arm data compared to state-of-the-art methods.
Detecting complex anomalies on massive amounts of data is a crucial task in Industry 4.0, best addressed by deep learning. However, available solutions are computationally demanding, requiring cloud architectures prone to latency and bandwidth issues. This work presents VARADE, a novel solution implementing a light autoregressive framework based on variational inference, which is best suited for real-time execution on the edge. The proposed approach was validated on a robotic arm, part of a pilot production line, and compared with several state-of-the-art algorithms, obtaining the best trade-off between anomaly detection accuracy, power consumption and inference frequency on two different edge platforms.