MAD-SDN · Multivariate Analysis of Big Data in Software Defined Networks
Horizon 2020 — Marie Skłodowska-Curie Actions
- Duration
- 2021-03-01 → 2023-02-28
- EU contribution
- €172,932
- Participants
- 1
- Scheme
- MSCA-IF
Lines connect the coordinator with its partners.
Results in brief
Multivariate Analysis of Big Data in Software Defined Networks
The networks of the future will be self-configuring, self-maintaining, self-securing and self-monitoring networks – autonomous networks. Although many efforts have been made in this area, autonomous networks still need innovative methods that enable them to quickly adapt to rapidly changing conditions in the network environment. The MAD-SDN project focused on the two main problems: network traffic classification and anomaly detection in the network security domain. The project proposed approaches based on multivariate big data analysis methods. We have performed comprehensive research with the MBDA methodology and several multivariate methods like Principal Component Analysis (PCA) or Partial Least Squares (PLS). Research and analyses conducted in this area revealed important issues that affect the results of Machine Learning modelling, and that are most often overlooked in our research area. A major problem relates to the quality of the network datasets. High-quality datasets are the key to the high performance of ML models and their usefulness in real networks. Research results were presented at conferences and discussed with the community. However, our outcomes do not solve all the problems and this area requires further work.
Data: CORDIS, © European Union
Project objective
One of the main problems of the Internet is the rapidly growing volume of diverse data. The Future Internet needs new efficient methods to support data management, processing and analysis. The Software Defined Networking (SDN) is a novel network architecture that overcomes the limitations of traditional networks, separating the control and data planes, and providing programmability capabilities of network functionalities. Yet, modern SDN deployments are difficult to manage and optimize. Big Data analysis techniques can be useful in SDN to identify problems, troubleshoot them and optimize network performance. One promising approach for this is the Multivariate Big Data Analysis (MBDA), which extends multivariate analysis to Big Data sets. However, MBDA has not been applied to SDN yet. During this project, MBDA will be used to detect anomalies and classify network traffic in complex SDN environment. In addition, in order to ensure privacy, MBDA will be extended with Federated Learning, a cutting-edge approach recently developed by Google with application to distributed data analysis problems. This project will be carry out by the experienced researcher (ER) who worked during her PhD thesis on network traffic analysis using advanced statistical methods on time series. The ER will cooperate with the Supervisor who is an expert in the field of multivariate analysis for anomaly detection and optimization of networks, and the principal developer of the MBDA approach.
Original text from CORDIS.
Participants
- UNIVERSIDAD DE GRANADA · GranadaCoordinatorSpain
Links
Data: CORDIS, © European Union