Learning Based on Graph: A Joint Interference Coordination for Cluster-wise Distributed MU-MIMO

Chang Ge; Sijie Xia; Qiang Chen; Fumiyuki Adachi

doi:10.1109/LCOMM.2023.3239605

Learning Based on Graph: A Joint Interference Coordination for Cluster-wise Distributed MU-MIMO

Chang Ge, Sijie Xia, Qiang Chen, Fumiyuki Adachi

ENG - Communications Engineering

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

Abstract

In a cellular system with distributed MU-MIMO, an application of cluster-wise distributed MU-MIMO reduces the computational complexity. However, both the intracell interference and the intercell interference are produced. Considering the scalability of the system, in this letter, we propose a fully decentralized interference coordination (IC) which jointly applies the graph coloring algorithm (GCA) and the deep reinforcement learning (DRL). Based on online training with consideration of the time-varying wireless environment, our proposed joint IC can adapt quickly to the changing environment. The simulation reveals that our proposed joint IC can significantly improve the capacity compared to the no IC case.

Original language	English
Pages (from-to)	1
Number of pages	1
Journal	IEEE Communications Letters
DOIs	https://doi.org/10.1109/LCOMM.2023.3239605
Publication status	Accepted/In press - 2023

Keywords

Color
Integrated circuit modeling
Integrated circuits
Intercell interference
Interference
Interference coordination
MIMO communication
Training
deep reinforcement learning
distributed MU-MIMO
graph coloring algorithm

ASJC Scopus subject areas

Modelling and Simulation
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/LCOMM.2023.3239605

Cite this

@article{3b1b766c190142a3a8c2b7130281bd05,

title = "Learning Based on Graph: A Joint Interference Coordination for Cluster-wise Distributed MU-MIMO",

abstract = "In a cellular system with distributed MU-MIMO, an application of cluster-wise distributed MU-MIMO reduces the computational complexity. However, both the intracell interference and the intercell interference are produced. Considering the scalability of the system, in this letter, we propose a fully decentralized interference coordination (IC) which jointly applies the graph coloring algorithm (GCA) and the deep reinforcement learning (DRL). Based on online training with consideration of the time-varying wireless environment, our proposed joint IC can adapt quickly to the changing environment. The simulation reveals that our proposed joint IC can significantly improve the capacity compared to the no IC case.",

keywords = "Color, Integrated circuit modeling, Integrated circuits, Intercell interference, Interference, Interference coordination, MIMO communication, Training, deep reinforcement learning, distributed MU-MIMO, graph coloring algorithm",

author = "Chang Ge and Sijie Xia and Qiang Chen and Fumiyuki Adachi",

note = "Publisher Copyright: IEEE",

year = "2023",

doi = "10.1109/LCOMM.2023.3239605",

language = "English",

pages = "1",

journal = "IEEE Communications Letters",

issn = "1089-7798",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Learning Based on Graph

T2 - A Joint Interference Coordination for Cluster-wise Distributed MU-MIMO

AU - Ge, Chang

AU - Xia, Sijie

AU - Chen, Qiang

AU - Adachi, Fumiyuki

N1 - Publisher Copyright: IEEE

PY - 2023

Y1 - 2023

N2 - In a cellular system with distributed MU-MIMO, an application of cluster-wise distributed MU-MIMO reduces the computational complexity. However, both the intracell interference and the intercell interference are produced. Considering the scalability of the system, in this letter, we propose a fully decentralized interference coordination (IC) which jointly applies the graph coloring algorithm (GCA) and the deep reinforcement learning (DRL). Based on online training with consideration of the time-varying wireless environment, our proposed joint IC can adapt quickly to the changing environment. The simulation reveals that our proposed joint IC can significantly improve the capacity compared to the no IC case.

AB - In a cellular system with distributed MU-MIMO, an application of cluster-wise distributed MU-MIMO reduces the computational complexity. However, both the intracell interference and the intercell interference are produced. Considering the scalability of the system, in this letter, we propose a fully decentralized interference coordination (IC) which jointly applies the graph coloring algorithm (GCA) and the deep reinforcement learning (DRL). Based on online training with consideration of the time-varying wireless environment, our proposed joint IC can adapt quickly to the changing environment. The simulation reveals that our proposed joint IC can significantly improve the capacity compared to the no IC case.

KW - Color

KW - Integrated circuit modeling

KW - Integrated circuits

KW - Intercell interference

KW - Interference

KW - Interference coordination

KW - MIMO communication

KW - Training

KW - deep reinforcement learning

KW - distributed MU-MIMO

KW - graph coloring algorithm

UR - http://www.scopus.com/inward/record.url?scp=85147292322&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85147292322&partnerID=8YFLogxK

U2 - 10.1109/LCOMM.2023.3239605

DO - 10.1109/LCOMM.2023.3239605

M3 - Article

AN - SCOPUS:85147292322

SN - 1089-7798

SP - 1

JO - IEEE Communications Letters

JF - IEEE Communications Letters

ER -

Learning Based on Graph: A Joint Interference Coordination for Cluster-wise Distributed MU-MIMO

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this