Flexible Virtual Cell Design for Ultradense Networks: A Machine Learning Approach

Zhiyang Cheng,Dongzhi Zhu,Chen Sun,Youping Zhao

doi:10.1109/access.2021.3091855

Zhiyang Cheng, Dongzhi Zhu + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3091855

Copy DOI

Abstract

With the ever-growing demand for even higher throughput, ultradense networks (UDNs) are being deployed for the fifth generation (5G) mobile communications. Although massively distributed radio access points (APs) result in a considerable increase in throughput, they also cause some critical problems. When employing a wireless backhaul, the backhaul capacity becomes a limiting factor, which may result in a high packet loss rate. Furthermore, dense deployment of APs leads to more frequent handoffs for mobile user equipments, which results in heavy measurement and signaling overhead. To address the problem of frequent handoffs, virtual cell (VC) has been considered as a promising solution. However, the limited wireless backhaul capacity encountered by inflexible VC design may still result in an intolerable packet loss rate. For a better trade-off between the packet loss rate and the handoff overhead, a machine learning approach for flexible VC design is proposed that leverages particle swarm optimization (PSO) to quickly find the optimal VC solution. To be responsive to the dynamic traffic demand and backhaul capacity of APs, a new parameter called “weighted distance” is employed in the modified K-means algorithm, which is nested in the PSO procedures for master AP selection and VC boundary determination. Compared with an exhaustive search, optimal VC solutions can be found efficiently through considerably fewer iterations. The proposed method is generic and applicable to disparate UDN application scenarios.

Highlights

W ITH the explosive growth of mobile traffic during recent decades, the fifth generation (5G) mobile communication system is in the stage of standardization and commercial deployment
SYSTEM MODEL Since small cells are currently widely deployed, we focus on resource management and mobility management in a single-tier ultradense networks (UDNs) with an architecture of small cells
In order to find an optimal virtual cell (VC) design scheme under a certain number of VCs generated by a particle of particle swarm optimization (PSO), the proposed algorithm can be divided into two stages: the access points (APs)-clustering stage and the boundary determination stage

Summary

INTRODUCTION

W ITH the explosive growth of mobile traffic during recent decades, the fifth generation (5G) mobile communication system is in the stage of standardization and commercial deployment. In addition to inter-cell interference, both handoff overhead and backhaul capacity are taken into consideration when forming VCs. VC formation is the process of spectrum allocation, as all APs in the same VC share the same channel(s). For the proposed flexible VC design, the master AP, which manages the backhaul of all user data within the VC and monitors inter-VC handoffs, needs to be dynamically selected. We leverage PSO and modified K-means clustering to dynamically change the coverage of VCs to adapt to varying traffic requirements and backhaul constraints in scenarios with mobile UEs. This is more generic and applicable to various UDN application scenarios.

RELATED WORKS

PROPOSED VC DESIGN

FINDING OPTIMAL NUMBER OF VCS

DETERMINING APPROPRIATE BOUNDARY BETWEEN VCS

15: Generate the boundary of the VCs by Voroni

SIMULATION RESULTS