In this paper, we present the 5G3E (5G End-to-End Emulation) dataset created to support 5G network automation. The dataset contains thousands of time-series, built at different sampling rates, related to the observation of multiple resources involved in 5G network operation: radio, computing and network resources. The variety of collected features ranges from radio front-end metrics to physical server operating system and network function metrics. We describe the testbed we deployed to support the creation of traffic starting from real traffic traces of a commercial network operator.

We present how to distribute an anomaly detection framework at the state of the art, called SYRROCA (SYstem Radiography and ROot Cause Analysis), for edge computing and 5G environment, using federated learning. The goal is to leverage on the distributed nature of federated learning to support data locality and local training of artificial intelligence modules, such as anomaly detection modules needed for closed-loop automation systems. We describe how the different functional modules interact and can be demonstrated.