The article Cascaded Anomaly Detection with Coarse Sampling in Distributed Systems, co-authored by Marek Bolanowski, PhD, and Andrzej Paszkiewicz, PhD, has been published in the Springer Lecture Notes in Computer Science book series (LNCS, volume 13167). The presentation covering the issues discussed in the paper was given by Marek Bolanowski, PhD, at the 9th International Conference on Big Data Analytics, BDA 2021, (December 7-9, 2021).
The paper, is the result of collaboration between Department of Complex Systems of Rzeszow University of Technology employees and researchers from the Systems Research Institute of the Polish Academy of Sciences and the University of Craiova (Craiova, Romania), Institute of Information and Communication Technologies Bulgarian Academy of Sciences (Sofia, Bulgaria), University of Novi Sad, Faculty of Sciences (Novi Sad, Serbia).
The paper presents an analysis of the usefulness of selected parameters of a distributed information system for early detection of anomalies in its operation. The paper proposes a cascade model in which any number of elements can be monitored using microservices. The threshold values of sampling frequency and the effect of the number of analyzed parameters on the quality of anomaly detection are also determined.
We invite you to read the entire article, which is available at:
https://link.springer.com/chapter/10.1007/978-3-030-96600-3_13
