Intelligence Slicing: A Unified Framework to Integrate Artificial Intelligence into 5G Networks

Wei Jiang; Simon Duque Anton; Hans Dieter Schotten

In: 12th IFIP Wireless and Mobile Networking Conference (WMNC). IFIP Wireless and Mobile Networking Conference (WMNC-2019), September 11-13, Paris, France, IFIP, 2019.


The fifth-generation and beyond wireless networks should support extremely high and diversified requirements from a wide variety of emerging applications. It is envisioned that more advanced radio transmission, resource allocation, and networking techniques are required to be developed. Fulfilling these tasks is challenging since the network infrastructure becomes increasingly complicated and heterogeneous. One potential solution is to leverage the great potential of Artificial Intelligence (AI), which has been explored to provide solutions ranging from fading channel prediction to autonomous network management, as well as network security. However, the state of the art of applying AI into wireless networks is mainly limited to use a dedicated AI algorithm to tackle a specific problem. A framework that can take advantage of AI capability in a unified manner is still an open issue. Hence, this paper will present the concept of intelligence slicing, which is able to instantiate and deploy an AI module on demand. Intelligence slices can be applied to solve a wide variety of network problems due to the flexibility of accommodating any existing or emerging AI techniques. Two example slices, i.e., recurrent neural networks based fading channel prediction and detecting security threats in an industrial network, are illustrated to demonstrate this framework.


PID5974643.pdf (pdf, 638 KB )

Deutsches Forschungszentrum für Künstliche Intelligenz
German Research Center for Artificial Intelligence