Intelligent Resource Scheduling for 5G Radio Access Network Slicing

Abstract

It is widely acknowledged that network slicing can tackle the diverse use cases and connectivity services of the forthcoming next generation mobile networks (5G). Resource scheduling is of vital importance for improving resource-multiplexing gain among slices while meeting specific service requirements for Radio Access Network (RAN) slicing. Unfortunately, due to the performance isolation, diversified service requirements and network dynamics (including user mobility and channel states, etc.), resource scheduling in RAN slicing is very challenging. In this paper, we propose an intelligent resource scheduling strategy (iRSS) for 5G RAN slicing. The main idea of iRSS is to exploit a collaborative learning framework which consists of deep learning (DL) in conjunction with Reinforcement Learning (RL). Specifically, DL is used to perform large timescale resource allocation, while RL is used to perform on-line resource scheduling for tackling small timescale network dynamics, including inaccurate prediction and unexpected network states. Depending on the amount of available historical traffic data, iRSS can flexibly adjust the significance between the prediction and online decision modules for assisting RAN in making resource scheduling decisions. Numerical results show that the convergence of iRSS satisfies on-line resource scheduling requirement and can significantly improve resource utilization while guaranteeing performance isolation between slices, compared with other benchmark algorithms.

Multi-Agent Deep Reinforcement Learning Based Spectrum Allocation for D2D Underlay Communications

“…With deep learning techniques, reinforcement learning has shown impressive improvement. [31] exploits a collaborative learning framework that consists of deep learning in conjunction with reinforcement learning for resource scheduling in network slicing. In [25], a decentralized resource allocation mechanism for vehicle-to-vehicle (V2V) communications based on deep RL has been developed, which can be applied to both unicast and broadcast scenarios.…”

Network Slice Reconfiguration by Exploiting Deep Reinforcement Learning With Large Action Space

“…Network slice reconfiguration under traffic uncertainties is inherently a sequential decision problem which can be potentially solved by using RL. Recently, with the advances in computing power, RL is commonly used to automate the resource management in network slicing [24]- [29]. The authors of [24] proposed a learning-based framework for RAN slicing by jointly using Deep Learning (DL) and DRL.…”

Novel Analytical Framework for harnessing Cognitive Radio Resource Optimization in 5G Networks

“…Thummaluru et al [20] have used the concept of MIMO for improving the performance of the reconfigurable antenna. Yan et al [21] have used deep learning as well as a reinforcement learning mechanism in order to perform the allocation of the resource over the 5G network. Ali-Tolppa et al [22] have used a self-organizing concept in order to perform anomaly detection over 5G cognitive networks.…”