Farhad Rezazadeh
Hatim Chergui
Loizos Christofi
Christos Verikoukis
2021-06-23
<p>To harness the full potential of beyond 5G (B5G) communication systems, zero-touch network slicing (NS) is viewed as a promising fully-automated management and orchestration (MANO) system. This paper proposes a novel knowledge plane (KP)-based MANO framework that accommodates and exploits recent NS technologies and is termed KB5G. Specifically, we deliberate on algorithmic innovation and artificial intelligence (AI) in KB5G. We invoke a continuous model-free deep reinforcement learning (DRL) method to minimize energy consumption and virtual network function (VNF) instantiation cost. We present a novel Actor-Critic-based NS approach to stabilize learning called, twin-delayed double-Q soft Actor-Critic (TDSAC) method. The TDSAC enables central unit (CU) to learn continuously to accumulate the knowledge learned in the past to minimize future NS costs. Finally, we present numerical results to showcase the gain of the adopted approach and verify the performance in terms of energy consumption, CPU utilization, and time efficiency.</p>
This work has been supported in part by the research projects 5GSTEPFWD (722429), MonB5G (871780), 5G-SOLUTIONS
(856691), AGAUR(2017-SGR-891) and SPOT5G (TEC2017-87456-P).
https://doi.org/10.5281/zenodo.6477470
oai:zenodo.org:6477470
Zenodo
https://zenodo.org/communities/eu
https://doi.org/10.5281/zenodo.6477469
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/legalcode
ICC2021, IEEE International Conference on Communications, Canada, 14-23 June 2021
Actor-Critic-Based Learning for Zero-touch Joint Resource and Energy Control in Network Slicing
info:eu-repo/semantics/conferencePaper