Anticipatory Session Management and User Plane Function Placement for AI-Driven Beyond 5G Networks

• DOI: 10.1016/j.procs.2019.11.090
• Publication Date: 2019-11-21T16:13:28Z
• Authors: Sebastian Peters; Manzoor Ahmed Khan
• Keywords: Core network

In this paper we aim at facilitating the flexible 5G core network architecture with foresighted session management. To achieve propose a 5G-native utilizing three-stage learning approach, which covers dimensions of interest to manage sessions in manner. perspective exploit concepts per-user mobility and activity patterns, apply our CODIPAS RL Framework anticipate user behavior requirements, utilize outcome for learning-based optimization on level transport stretch Learning approach. We further contribute model that exploits management approach by prediction optimized intermediate User Plane Function (iUPF) placement.