Digital Infrastructures refers to all the Internet engineering technologies that realise the communication system of critical infrastructures in key sectors like communications, energy, transportation, finance,… The objective of applying advance Internet technologies in such critical infrastructures is to make them not only more efficient in their operations & maintenance but also more robust against failures or cyberthreats.
FBK CREATE-NET focus within this application domain is the softwarisation of communication networks and the application of Artificial Intelligence techniques to make critical infrastructures more resilient and autonomous.
A set of realistic Use Cases developed in collaboration with some of our partners are described in the following:
- Security and robustness of critical infrastructures. Leveraging novel data plane programmability solutions offered by the P4 programming language and linux kernel data-path technologies, networking flows are monitored and analysed (by means of AI-based anomaly detection algorithms) to protect individual software processes, connected devices, appliances and communications, possibly avoiding any human intervention. The validation of the proposed approach is carried out in testbed running over the FBK CREATE-NET DIVINE facility, which is equipped with 3 carrier-grade P4 switches and several linux-based machines representing edge/fog nodes. Target infrastructures are industrial and telecommunication networks. For more information about this use case please refer to RiSING Unit.
- End-to-end Active 5G Network Slicing. Future 5G network will be required to support different verticals each of them coming with a different set of requirements in terms of capacity, bandwidth, and latency. Telecom operators want to transition from a low revenue model based on monetising capacity to a new paradigm where bandwidth is monetised. This raises three sets of problems: 1) how to provide isolation between concurrent verticals, 2) how to tailor each slice to the requirements of a vertical, and 3) how to make an efficient use of the network resources (end-to-end). For more information about this use case please refer to WiN Unit.