To sustain their important role for our digital society, communication networks need to flexibly accommodate new requirements and changing contexts. In particular, softwarized networks provide ample opportunities for highly flexible network operations, enabling fast and simple adaptation of network resources and flows. This presentation highlights opportunities and challenges of flexible softwarized networks and introduces a conceptual framework for adaptations. The multitude of options in softwarized networks complicate the decision making. Hence, we present enhancements for data-driven decision making, e.g., machine learning modules. The data-driven decision making modules can learn and react to changes in the environment to support meaningful decision making for adaptation in flexible softwarized networks. Finally, we make the case for employing the concept of empowerment to realize truly “self-driving” networks.     «

To sustain their important role for our digital society, communication networks need to flexibly accommodate new requirements and changing contexts. In particular, softwarized networks provide ample opportunities for highly flexible network operations, enabling fast and simple adaptation of network resources and flows. This presentation highlights opportunities and challenges of flexible softwarized networks and introduces a conceptual framework for adaptations. The multitude of options in softw...     »