Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Geometric streams monitoring on Apache Flink

Epoure Entouarnt

Full record


URI: http://purl.tuc.gr/dl/dias/62E7B086-E854-42B3-9C0F-694D36B87028
Year 2020
Type of Item Diploma Work
License
Details
Bibliographic Citation Entouarnt Epoure, "Geometric streams monitoring on Apache Flink", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2020 https://doi.org/10.26233/heallink.tuc.87753
Appears in Collections

Summary

The amount of data generated every day by online applications is continuously growing, which results in a demand for capable real-time stream processing frameworks. Numerous monitoring algorithms have been proposed over the years, yielding exceptional results but with common shortcomings. The problem not yet addressed by previous work on monitoring algorithms is their integration into large data-stream processing frameworks. Part of the reasonmay be the lack of uniformity each monitoring algorithm presents and the requirements it imposes on the system architecture. That’s where Apache Flink comes into play. It is an open-source framework and distributed processing engine for stateful computation over unbounded data-streams. Flink is a very versatile tool, designed to run in all common cluster environments and perform computations at any scale. This thesis describes the implementation of theFunctional Geometric Monitoring algorithm on Apache Flink, while comparing the extracted results with these of previous simulated implementations of monitoring algorithms.

Available Files

Services

Statistics