DRL-Based Joint RAT Association, Power and Bandwidth Optimization for Future HetNets

Abdulmalik Alwarafy; Bekir Sait Ciftler; Mohamed Abdallah; Mounir Hamdi; Naofal Al-Dhahir

doi:10.1109/LWC.2022.3177250

DRL-Based Joint RAT Association, Power and Bandwidth Optimization for Future HetNets

Abdulmalik Alwarafy^*, Bekir Sait Ciftler, Mohamed Abdallah, Mounir Hamdi, Naofal Al-Dhahir

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

Abstract

Multi-radio access technologies (RATs) networks, where various heterogeneous networks (HetNets) coexist, are in service nowadays and considered a main enabling technology for future networks. In such networks, managing radio resources is challenge. In this letter, we address the problem of RATs-edge devices (EDs) association and joint power and bandwidth allocation in multi-RAT multi-homing HetNets. The problem is formulated as mixed-integer non-linear programming, whose objective is to cost-effectively maximize the network constrained sum-rate. Due to the high complexity of the problem, we propose a multi-agent deep reinforcement learning (DRL)-based scheme to solve it. Simulation results show that our proposed scheme efficiently learns the optimal policy and enhances the network sum-rate by 80.95% compared to key benchmarks.

Original language	English
Pages (from-to)	1503-1507
Number of pages	5
Journal	IEEE Wireless Communications Letters
Volume	11
Issue number	7
DOIs	https://doi.org/10.1109/LWC.2022.3177250
Publication status	Published - 1 Jul 2022

Keywords

Bandwidth
Channel allocation
Deep reinforcement learning
Downlink
Heterogeneous networks
Optimization
Power
RAT association
Radio access technologies
Rats
Resource management

Access to Document

10.1109/LWC.2022.3177250

Cite this

@article{d2bf2dd10b364f25abe58df84c1b21fa,

title = "DRL-Based Joint RAT Association, Power and Bandwidth Optimization for Future HetNets",

abstract = "Multi-radio access technologies (RATs) networks, where various heterogeneous networks (HetNets) coexist, are in service nowadays and considered a main enabling technology for future networks. In such networks, managing radio resources is challenge. In this letter, we address the problem of RATs-edge devices (EDs) association and joint power and bandwidth allocation in multi-RAT multi-homing HetNets. The problem is formulated as mixed-integer non-linear programming, whose objective is to cost-effectively maximize the network constrained sum-rate. Due to the high complexity of the problem, we propose a multi-agent deep reinforcement learning (DRL)-based scheme to solve it. Simulation results show that our proposed scheme efficiently learns the optimal policy and enhances the network sum-rate by 80.95% compared to key benchmarks.",

keywords = "Bandwidth, Channel allocation, Deep reinforcement learning, Downlink, Heterogeneous networks, Optimization, Power, RAT association, Radio access technologies, Rats, Resource management",

author = "Abdulmalik Alwarafy and Ciftler, {Bekir Sait} and Mohamed Abdallah and Mounir Hamdi and Naofal Al-Dhahir",

note = "Publisher Copyright: {\textcopyright} 2012 IEEE.",

year = "2022",

month = jul,

day = "1",

doi = "10.1109/LWC.2022.3177250",

language = "English",

volume = "11",

pages = "1503--1507",

journal = "IEEE Wireless Communications Letters",

issn = "2162-2337",

publisher = "IEEE Communications Society",

number = "7",

}

TY - JOUR

T1 - DRL-Based Joint RAT Association, Power and Bandwidth Optimization for Future HetNets

AU - Alwarafy, Abdulmalik

AU - Ciftler, Bekir Sait

AU - Abdallah, Mohamed

AU - Hamdi, Mounir

AU - Al-Dhahir, Naofal

PY - 2022/7/1

Y1 - 2022/7/1

N2 - Multi-radio access technologies (RATs) networks, where various heterogeneous networks (HetNets) coexist, are in service nowadays and considered a main enabling technology for future networks. In such networks, managing radio resources is challenge. In this letter, we address the problem of RATs-edge devices (EDs) association and joint power and bandwidth allocation in multi-RAT multi-homing HetNets. The problem is formulated as mixed-integer non-linear programming, whose objective is to cost-effectively maximize the network constrained sum-rate. Due to the high complexity of the problem, we propose a multi-agent deep reinforcement learning (DRL)-based scheme to solve it. Simulation results show that our proposed scheme efficiently learns the optimal policy and enhances the network sum-rate by 80.95% compared to key benchmarks.

AB - Multi-radio access technologies (RATs) networks, where various heterogeneous networks (HetNets) coexist, are in service nowadays and considered a main enabling technology for future networks. In such networks, managing radio resources is challenge. In this letter, we address the problem of RATs-edge devices (EDs) association and joint power and bandwidth allocation in multi-RAT multi-homing HetNets. The problem is formulated as mixed-integer non-linear programming, whose objective is to cost-effectively maximize the network constrained sum-rate. Due to the high complexity of the problem, we propose a multi-agent deep reinforcement learning (DRL)-based scheme to solve it. Simulation results show that our proposed scheme efficiently learns the optimal policy and enhances the network sum-rate by 80.95% compared to key benchmarks.

KW - Bandwidth

KW - Channel allocation

KW - Deep reinforcement learning

KW - Downlink

KW - Heterogeneous networks

KW - Optimization

KW - Power

KW - RAT association

KW - Radio access technologies

KW - Rats

KW - Resource management

UR - http://www.scopus.com/inward/record.url?scp=85130790656&partnerID=8YFLogxK

U2 - 10.1109/LWC.2022.3177250

DO - 10.1109/LWC.2022.3177250

M3 - Article

AN - SCOPUS:85130790656

SN - 2162-2337

VL - 11

SP - 1503

EP - 1507

JO - IEEE Wireless Communications Letters

JF - IEEE Wireless Communications Letters

IS - 7

ER -

DRL-Based Joint RAT Association, Power and Bandwidth Optimization for Future HetNets

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

EX-QNRF-NPRPS-37: Secure Federated Edge Intelligence Framework for AI-driven 6G Applications

Cite this

DRL-Based Joint RAT Association, Power and Bandwidth Optimization for Future HetNets

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Projects

EX-QNRF-NPRPS-37: Secure Federated Edge Intelligence Framework for AI-driven 6G Applications

Cite this