NANCY SNS-JU project "Italtel Italian in-lab testbed dataset 2"

This Dataset provides input data for the development of the B-RAN and attacks models for the NANCY framework, to model training and model inference functions. The data collected in the Italian in-lab testbed, namely “dataset 2”, focus on the Edge segment of the network and consider the presence of some of the NANCY components, to assess their impact with respect to the baseline defined through the first collected dataset (D6.6 “Italian in-lab testbed dataset 1”), assessment that will be carried out and completed, together with the technology evaluation, in subsequent project activities.       
More specifically, the data collected in the Italtel Italian in-lab testbed, where a MEC assisted 5G network scenario with a video streaming application for generating traffic is provided, consider an Edge server based on ARMv8 CPU architecture, and some components specifically developed by the Partners for the NANCY project; these components are integrated in the Italtel environment and are part of the testbed topology set-up:

·        the “Anomaly detection application module”, provided by CRAT partner (Consortium for Research in Automation and Telecommunications) and focusing on detecting anomalous utilization of computing and network resources

·        the” VOSySmonitor and vManager”, provided by VOS (Virtual Open Systems), a novel virtualization technology, designed by NANCY, to host offloaded VNFs, which can be deployed in a bare-metal fashion ensuring “application isolation”

·        “Malicious traffic generation application” and “PAPI extension for ARM performance counter interaction”, provided by SSS (Sant'Anna Higher School of Pisa) for the technology validation in the context of the Italian testbed set-up

·        “Italtel VTU application”, provided by ITL, which can convert audio and video streams from one format to another, at multiple encodings schemes, changing resolution, bitrate, and video parameters.

The dataset contains time series, collected by transmitting video content through the Italtel VTU application.The collected dataset is representative resource-intensive video traffic that has the greatest impact on 5G/B5G network planning and provisioning. The video streaming dataset includes data directly measured while watching the video on the mobile devices and data directly measured while generating downstream video stream traversing the gNB (i.e., downstream scenario), and vice versa (i.e., upstream scenario). In each experiment, we fixed the location of the UE and the gNB.