Abstract
Graph-based approaches have been widely employed to facilitate in analyzing network flow connectivity behaviors, which aim to understand the impacts and patterns of network events. However, existing approaches suffer from lack of connectivity-behavior information and loss of network event identification. In this paper, we propose network flow connectivity graphs (NFCGs) to capture network flow behavior for modeling social behaviors from network entities. Given a set of flows, edges of a NFCG are generated by connecting pairwise hosts who communicate with each other. To preserve more information about network flows, we also embed node-ranking values and edge-weight vectors into the original NFCG. After that, a network flow connectivity behavior analysis framework is present based on NFCGs. The proposed framework consists of three modules: a graph simplification module based on diversified filtering rules, a graph feature analysis module based on quantitative or semiquantitative analysis, and a graph structure analysis module based on several graph mining methods. Furthermore, we evaluate our NFCG-based framework by using real network traffic data. The results show that NFCGs and the proposed framework can not only achieve good performance on network behavior analysis but also exhibit excellent scalability for further algorithmic implementations.
Highlights
Over the past decades we have witnessed the progressive development of network science technologies and emerging applications from theoretical innovation into practical applications [1, 2]
The main novelty of our proposed method is that we utilize node-ranking values, edge-weight vectors, and various filtering rules to optimize graph construction so that network flow connectivity graphs (NFCGs) become more flexible and contain richer information of network flows
To explore the best of our proposed method in network flow behavior analysis, we have developed a NFCG-based framework and conducted different experiments to analyze NFCGs
Summary
Over the past decades we have witnessed the progressive development of network science technologies and emerging applications from theoretical innovation into practical applications [1, 2]. We propose a novel graph model called network flow connectivity graphs (NFCGs) to comprehensively monitor, analyze, and visualize network-wide flow connectivity relationships. We stress the importance of NFCGs by developing a flow-based network behavior analysis framework In this framework, we start by designing filtering rules to remove insignificant and irrelevant nodes and edges for extracting the principal connectivity relationships and simplifying the graph scale. 3) We develop a NFCG-based framework and combine a series of complex network analysis and graph mining methods to monitor, analyze, and visualize network-wide flow connectivity relationships. Karagiannis et al [15] proposed the BLINC method to build logic graphs of node interaction They utilized the difference among connected patterns of network applications for performing network classification, but ignored general connected relations of network flows. With this kind of approach it is difficult to unveil the hidden relationships between different communities of network
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: TURKISH JOURNAL OF ELECTRICAL ENGINEERING & COMPUTER SCIENCES
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
