Online Anomaly Detection Based On Reservoir Sampling and LOF for IoT devices
This addresses the problem of real-time anomaly detection for IoT device operators, but it is incremental as it adapts an existing method to hardware constraints.
The paper tackles the challenge of implementing anomaly detection on resource-constrained IoT devices by analyzing a pipeline and adapting the Local Outlier Factor (LOF) algorithm with reservoir sampling, enabling on-device training for practical deployment.
The growing number of IoT devices and their use to monitor the operation of machines and equipment increases interest in anomaly detection algorithms running on devices. However, the difficulty is the limitations of the available computational and memory resources on the devices. In the case of microcontrollers (MCUs), these are single megabytes of program and several hundred kilobytes of working memory. Consequently, algorithms must be appropriately matched to the capabilities of the devices. In the paper, we analyse the processing pipeline for anomaly detection and implementation of the Local Outliner Factor (LOF) algorithm on a MCU. We also show that it is possible to train such an algorithm directly on the device, which gives great potential to use the solution in real devices.