Grand challenge: Flinkman - Anomaly detection in manufacturing equipment with apache flink

Nicolo Rivetti, Yann Busnel, Avigdor Gal

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We present a (soft) real-time event-based anomaly detection application for manufacturing equipment, built on top of the general purpose stream processing framework Apache Flink. The anomaly detection involves multiple CPUs and/or memory intensive tasks, such as clustering on large time-based window and parsing input data in RDF-format. The main goal is to reduce end-to-end latencies, while handling high input throughput and still provide exact results. Given a truly distributed setting, this challenge also entails careful task and/or data parallelization and balancing. We propose FlinkMan, a system that offers a generic and efficient solution, which maximizes the usage of available cores and balances the load among them. We illustrates the accuracy and efficiency of FlinkMan, over a 3-step pipelined data stream analysis, that includes clustering, modeling and querying.

Original languageEnglish
Title of host publicationDEBS 2017 - Proceedings of the 11th ACM International Conference on Distributed Event-Based Systems
Pages274-279
Number of pages6
ISBN (Electronic)9781450350655
DOIs
StatePublished - 8 Jun 2017
Event11th ACM International Conference on Distributed Event-Based Systems, DEBS 2017 - Barcelona, Spain
Duration: 19 Jun 201723 Jun 2017

Publication series

NameDEBS 2017 - Proceedings of the 11th ACM International Conference on Distributed Event-Based Systems

Conference

Conference11th ACM International Conference on Distributed Event-Based Systems, DEBS 2017
Country/TerritorySpain
CityBarcelona
Period19/06/1723/06/17

Keywords

  • Anomaly detection
  • Clustering
  • Linked-Data
  • Markov chains
  • Stream processing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Control and Systems Engineering
  • Software

Fingerprint

Dive into the research topics of 'Grand challenge: Flinkman - Anomaly detection in manufacturing equipment with apache flink'. Together they form a unique fingerprint.

Cite this