A survey on AI-enabled mobility and handover management in future wireless networks: key technologies, use cases, and challenges

Citation

Ullah, Yasir and Roslee, Mardeni and Mitani, Sufian Mousa and Sheraz, Muhammad and Ali, Farman and Aurangzeb, Khursheed and Osman, Anwar Faizd and Ali, Fatimah Zaharah (2025) A survey on AI-enabled mobility and handover management in future wireless networks: key technologies, use cases, and challenges. Journal of King Saud University Computer and Information Sciences, 37 (4). ISSN 1319-1578

[img] Text
s44443-025-00048-9.pdf - Published Version
Restricted to Repository staff only

Download (2MB)

Abstract

Heterogeneous Networks (HetNets) integrate Small Cells (SCs) with connectivity technologies like Long-Term Evolution (LTE), Wireless Fidelity (WiFi), and Zigbee, supported by communication protocols such as transmission control protocol and internet protocol for reliable data services. While HetNets offer high data rates, throughput, and low latency, the dense deployment of SCs increases network complexity, leading to frequent Handovers (HOs) and potential service disruptions. Seamless HOs are essential for maintaining uninterrupted connectivity and addressing issues like HO Failure (HOF) and network congestion. Future Wireless Networks (FWNs) utilize advanced technologies like millimeter Wave (mmWave), Terahertz (THz), Massive Multiple-Input Multiple-Output (M-MIMO), beamforming, Reconfigurable Intelligent Surface (RIS), and Unmanned Aerial Vehicles (UAVs) to meet the growing demand for high Quality of Service (QoS). However, mobility in HetNets introduces challenges such as HOF and service degradation, highlighting the need for effective mobility management to ensure seamless connectivity. This paper provides a comprehensive discussion of FWN technologies and their significance in HO and mobility management. It examines HO management schemes, performance metrics, and key factors influencing mobility management in FWNs. Additionally, it reviews existing studies utilizing Machine Learning (ML) for mobility and HO management, covering supervised, unsupervised, and Reinforcement Learning (RL) techniques. The paper also explores use cases of advanced mobility management techniques to address these issues. Finally, it identifies key challenges and proposes solutions for effective mobility management in FWNs.

Item Type: Article
Uncontrolled Keywords: Future wireless networks
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Rosnani Abd Wahab
Date Deposited: 26 Jun 2025 06:37
Last Modified: 26 Jun 2025 06:37
URII: http://shdl.mmu.edu.my/id/eprint/14093

Downloads

Downloads per month over past year

View ItemEdit (login required)