Deep Reinforcement Learning for End-to-End Network Slicing: Challenges and Solutions
Document Type
Article
Publication Date
3-1-2023
Abstract
5G and beyond is expected to enable various emerging use cases with diverse performance requirements from vertical industries. To serve these use cases cost-effectively, network slicing plays a key role in dynamically creating virtual end-to-end networks according to specific resource demands. A network slice may have hundreds of configurable parameters over multiple technical domains that define the performance of the network slice, which makes it impossible to use traditional model-based solutions to orchestrate resources for network slices. In this article, we discuss how to design and deploy deep reinforcement learning (DRL), a model-free approach, to address the network slicing problem. First, we analyze the network slicing problem and present a standard-compliant system architecture that enables DRL-based solutions in 5G and beyond networks. Second, we provide an in-depth analysis of the challenges in designing and deploying DRL in network slicing systems. Third, we explore multiple promising techniques, that is, safety and distributed DRL, and imitation learning, for automating end-to-end network slicing.
Identifier
85135751125 (Scopus)
Publication Title
IEEE Network
External Full Text Location
https://doi.org/10.1109/MNET.113.2100739
e-ISSN
1558156X
ISSN
08908044
First Page
222
Last Page
228
Issue
2
Volume
37
Recommended Citation
Liu, Qiang; Choi, Nakjung; and Han, Tao, "Deep Reinforcement Learning for End-to-End Network Slicing: Challenges and Solutions" (2023). Faculty Publications. 1865.
https://digitalcommons.njit.edu/fac_pubs/1865