Big Data Network Flow Processing Using Apache Spark

Kamil Jeřábek, Ondřej Ryšavý · 2019

The increasing amount of traffic flows captured as a part of network monitoring activities makes the analysis more complicated. One of the goals for network traffic analysis is to identify malicious communication. In the paper, we present a new system for big data network flow classification and clustering. The proposed system is based on the popular big data engines such as Apache Spark and Apache Ignite. The conducted experiments demonstrate the feasibility of the proposed approach and show the possible scalability.

Read the paper · More papers on PaperTik