Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems: A Hybrid Action Space-DRL Approach

Zhihui Wu; Yanxiang Jiang; Yige Huang; Fu Chun Zheng; Pengcheng Zhu

doi:10.1109/LCOMM.2024.3424507

Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems: A Hybrid Action Space-DRL Approach

Zhihui Wu
, Yanxiang Jiang^*
, Yige Huang
, Fu Chun Zheng^*
, Pengcheng Zhu

^*Corresponding author for this work

Southeast University, Nanjing
Harbin Institute of Technology Shenzhen

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

19 Scopus citations

Abstract

In this letter, we investigate the problem of joint access point (AP) selection and power control in Cell-free massive MIMO (CF-mMIMO) networks, aiming at maximizing energy efficiency (EE) under a sum spectral efficiency (SSE) requirement. Given the limitations of separate optimizations due to strong couplings between AP selection and power control, a novel deep reinforcement learning (DRL) approach with hybrid action space is proposed. Simulation results show that our proposed algorithm achieves low-dimensional actions by embedding parameters and can achieve higher EE with lower complexity.

Original language	English
Pages (from-to)	2086-2090
Number of pages	5
Journal	IEEE Communications Letters
Volume	28
Issue number	9
DOIs	https://doi.org/10.1109/LCOMM.2024.3424507
State	Published - 2024
Externally published	Yes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Keywords

Cell-free
deep reinforcement learning
energy efficiency
power control

Access to Document

10.1109/LCOMM.2024.3424507

Cite this

@article{9f127a412c25464d944b147e1f31fed3,

title = "Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems: A Hybrid Action Space-DRL Approach",

abstract = "In this letter, we investigate the problem of joint access point (AP) selection and power control in Cell-free massive MIMO (CF-mMIMO) networks, aiming at maximizing energy efficiency (EE) under a sum spectral efficiency (SSE) requirement. Given the limitations of separate optimizations due to strong couplings between AP selection and power control, a novel deep reinforcement learning (DRL) approach with hybrid action space is proposed. Simulation results show that our proposed algorithm achieves low-dimensional actions by embedding parameters and can achieve higher EE with lower complexity.",

keywords = "Cell-free, deep reinforcement learning, energy efficiency, power control",

author = "Zhihui Wu and Yanxiang Jiang and Yige Huang and Zheng, \{Fu Chun\} and Pengcheng Zhu",

note = "Publisher Copyright: {\textcopyright} 1997-2012 IEEE.",

year = "2024",

doi = "10.1109/LCOMM.2024.3424507",

language = "英语",

volume = "28",

pages = "2086--2090",

journal = "IEEE Communications Letters",

issn = "1089-7798",

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

number = "9",

}

TY - JOUR

T1 - Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems

T2 - A Hybrid Action Space-DRL Approach

AU - Wu, Zhihui

AU - Jiang, Yanxiang

AU - Huang, Yige

AU - Zheng, Fu Chun

AU - Zhu, Pengcheng

PY - 2024

Y1 - 2024

N2 - In this letter, we investigate the problem of joint access point (AP) selection and power control in Cell-free massive MIMO (CF-mMIMO) networks, aiming at maximizing energy efficiency (EE) under a sum spectral efficiency (SSE) requirement. Given the limitations of separate optimizations due to strong couplings between AP selection and power control, a novel deep reinforcement learning (DRL) approach with hybrid action space is proposed. Simulation results show that our proposed algorithm achieves low-dimensional actions by embedding parameters and can achieve higher EE with lower complexity.

AB - In this letter, we investigate the problem of joint access point (AP) selection and power control in Cell-free massive MIMO (CF-mMIMO) networks, aiming at maximizing energy efficiency (EE) under a sum spectral efficiency (SSE) requirement. Given the limitations of separate optimizations due to strong couplings between AP selection and power control, a novel deep reinforcement learning (DRL) approach with hybrid action space is proposed. Simulation results show that our proposed algorithm achieves low-dimensional actions by embedding parameters and can achieve higher EE with lower complexity.

KW - Cell-free

KW - deep reinforcement learning

KW - energy efficiency

KW - power control

UR - https://www.scopus.com/pages/publications/85198259352

U2 - 10.1109/LCOMM.2024.3424507

DO - 10.1109/LCOMM.2024.3424507

M3 - 文章

AN - SCOPUS:85198259352

SN - 1089-7798

VL - 28

SP - 2086

EP - 2090

JO - IEEE Communications Letters

JF - IEEE Communications Letters

IS - 9

ER -

Energy-Efficient Joint AP Selection and Power Control in Cell-Free Massive MIMO Systems: A Hybrid Action Space-DRL Approach

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this