Deep Reinforcement Learning for Resource Management in Network Slicing

TLDR

Network slicing enables operators to sell customized slices to tenants, but its resource management faces technical challenges that demand intelligent solutions, with deep reinforcement learning emerging as a promising approach. This study explores how deep reinforcement learning can optimize radio and core network slicing resource allocation and shows its superiority over existing methods, while outlining potential deployment challenges. The authors apply DRL to radio and core network slicing problems, evaluating its performance against competing schemes via extensive simulation experiments.

Abstract

Network slicing is born as an emerging business to operators by allowing them to sell the customized slices to various tenants at different prices. In order to provide better-performing and costefficient services, network slicing involves challenging technical issues and urgently looks forward to intelligent innovations to make the resource management consistent with users' activities per slice. In that regard, deep reinforcement learning (DRL), which focuses on how to interact with the environment by trying alternative actions and reinforcing the tendency actions producing more rewarding consequences, is assumed to be a promising solution. In this paper, after briefly reviewing the fundamental concepts of DRL, we investigate the application of DRL in solving some typical resource management for network slicing scenarios, which include radio resource slicing and priority-based core network slicing, and demonstrate the advantage of DRL over several competing schemes through extensive simulations. Finally, we also discuss the possible challenges to apply DRL in network slicing from a general perspective.