A Light-weight and Unsupervised Method for Near Real-time Behavioral Analysis using Operational Data Measurement
This work addresses the need for efficient and adaptive monitoring in large-scale computing systems, though it appears incremental as it builds on existing anomaly detection approaches.
The paper tackles the problem of automated anomaly detection in large computing systems by proposing a lightweight, unsupervised method that requires only 4 hours of data and 50 epochs per training to accurately model system behavior for near real-time monitoring.
Monitoring the status of large computing systems is essential to identify unexpected behavior and improve their performance and uptime. However, due to the large-scale and distributed design of such computing systems as well as a large number of monitoring parameters, automated monitoring methods should be applied. Such automatic monitoring methods should also have the ability to adapt themselves to the continuous changes in the computing system. In addition, they should be able to identify behavioral anomalies in useful time, to perform appropriate reactions. This work proposes a general lightweight and unsupervised method for near real-time anomaly detection using operational data measurement on large computing systems. The proposed model requires as little as 4 hours of data and 50 epochs for each training process to accurately resemble the behavioral pattern of computing systems.