Accurate identification and categorization of network traffic according to application type is an important element of many network management and engineering tasks related with QoS, capacity planning and detection of network attacks.
Terabytes of data may be transferred through the core network of a typical ISP every day. Moreover, it is expected an exponential growth of more than 50 billions of connected devices to Internet. Therefore, this scenario hampers network data capture and analysis.
Proactive and dynamic QoS Management, Network detection intrusion and Early detection of congestion network problems, among others applications in the context of network management and engineering, can benefit from the existence of an accurate and scalable mechanism for online characterization of network traffic patterns evolution.
To this end ONTIC project proposes to investigate, implement and test:
A novel architecture of scalable mechanisms and techniques to be able to a) characterize online network traffic data streams, identifying traffic patterns evolution, and b) proactively detecting anomalies in real time when hundreds of thousands of packets per second are processed.
A completely new set of scalable offline data mining mechanisms and techniques to characterize network traffic, applying a big data analytics approach and using distributed computation paradigms in the cloud on extremely large network traffic summary datasets consisting on trillions of records.
ONTIC project will integrate offline and online mechanisms and techniques into an autonomous network traffic characterization system to be used as cornerstone of a new generation of scalable and proactive network management and engineering applications.
Additionally, ONTIC project will generate a petabyte size dataset composed of real network traffic summaries obtained during several months from a set of data flows (1.5 Gbps on average) that cross the core network of a medium size ISP that participates in the ONTIC consortium. The contents of this dataset will be anonymized and made publicly available at the end of the project to foster new research initiatives in the field of big data analytics.
Finally, ONTIC will lead the dissemination and adoption of project outcomes to other application domains (e.g. bioinformatics, medicine, physics, social sciences, and finances). Then, ONTIC will generate an open source scalable offline/online analytics framework to be used by developers in other application domains.