On the Specialization of FDRL Agents for Scalable and Distributed 6G RAN Slicing Orchestration
Por:
Rezazadeh F., Zanzi L., Devoti F., Chergui H., Costa-Perez X., Verikoukis C.
Publicada:
1 mar 2023
Ahead of Print:
1 ene 2022
Resumen:
Network slicing enables multiple virtual networks to be instantiated and customized to meet heterogeneous use case requirements over 5G and beyond network deployments. However, most of the solutions available today face scalability issues when considering many slices, due to centralized controllers requiring a holistic view of the resource availability and consumption over different networking domains. In order to tackle this challenge, we design a hierarchical architecture to manage network slices resources in a federated manner. Driven by the rapid evolution of deep reinforcement learning (DRL) schemes and the Open RAN (O-RAN) paradigm, we propose a set of traffic-aware local decision agents (DAs) dynamically placed in the radio access network (RAN). These federated decision entities tailor their resource allocation policy according to the long-term dynamics of the underlying traffic, defining specialized clusters that enable faster training and communication overhead reduction. Indeed, aided by a traffic-aware agent selection algorithm, our proposed Federated DRL approach provides higher resource efficiency than benchmark solutions by quickly reacting to end-user mobility patterns and reducing costly interactions with centralized controllers.
Filiaciones:
Rezazadeh F.:
Telecommunications Technological Center of Catalonia (CTTC), Technical University of Catalonia (UPC), Barcelona, Spain
Zanzi L.:
NEC Laboratories Europe, Heidelberg, Germany
Devoti F.:
NEC Laboratories Europe, Heidelberg, Germany
Chergui H.:
Telecommunications Technological Center of Catalonia (CTTC), Barcelona, Spain
Costa-Perez X.:
NEC Laboratories Europe, i2CAT Foundation, and ICREA, Barcelona, Spain
Verikoukis C.:
University of Patras, ATHENA/ISI, and IQUADRAT Informatica, Barcelona, Spain
Green Submitted, Green Published, All Open Access; Green
|