A Nested DRL-Based Method for Power Allocation and AP Sleep Control in Cell-Free Massive MIMO Systems

Xiukun Xu; Yanxiang Jiang; Yige Huang; Fu Chun Zheng

doi:10.1109/ICCC62609.2024.10942164

A Nested DRL-Based Method for Power Allocation and AP Sleep Control in Cell-Free Massive MIMO Systems

Xiukun Xu
, Yanxiang Jiang^*
, Yige Huang
, Fu Chun Zheng^*

^*Corresponding author for this work

Southeast University, Nanjing
Harbin Institute of Technology Shenzhen

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Cell-free massive MIMO (CFmMIMO) systems are increasingly recognized as a key technology to enhance 6G network performance. The large-scale coverage of access points (APs) and irrational power allocation leads to low energy efficiency and suboptimal Quality of Service (QoS). This paper proposes a nested deep reinforcement learning (DRL)-based optimization method utilizing novel double nested actor-critic (AC) frameworks to optimize power allocation and AP sleep control, which efficiently addresses the complex decision-making processes involved in dynamic environments. Extensive simulations results show that our proposed method enhances the peak energy efficiency in CFmMIMO systems by 19.6% and achieves a better trade-off between QoS and power consumption than the state-of-the-art and heuristic alternatives.

Original language	English
Pages (from-to)	1663-1668
Number of pages	6
Journal	Proceedings of the IEEE International Conference on Computer and Communications, ICCC
Issue number	2024
DOIs	https://doi.org/10.1109/ICCC62609.2024.10942164
State	Published - 2024
Externally published	Yes
Event	10th International Conference on Computer and Communications, ICCC 2024 - Chengdu, China Duration: 13 Dec 2024 → 16 Dec 2024

UN SDGs

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

SDG 7 Affordable and Clean Energy

Keywords

AP sleep control
Cell-free massive MIMO
actor-critic framework
deep reinforcement learning
energy efficiency
power allocation

Access to Document

10.1109/ICCC62609.2024.10942164

Cite this

@article{0967ae355d594aa8a1c9e7a2b859399c,

title = "A Nested DRL-Based Method for Power Allocation and AP Sleep Control in Cell-Free Massive MIMO Systems",

abstract = "Cell-free massive MIMO (CFmMIMO) systems are increasingly recognized as a key technology to enhance 6G network performance. The large-scale coverage of access points (APs) and irrational power allocation leads to low energy efficiency and suboptimal Quality of Service (QoS). This paper proposes a nested deep reinforcement learning (DRL)-based optimization method utilizing novel double nested actor-critic (AC) frameworks to optimize power allocation and AP sleep control, which efficiently addresses the complex decision-making processes involved in dynamic environments. Extensive simulations results show that our proposed method enhances the peak energy efficiency in CFmMIMO systems by 19.6\% and achieves a better trade-off between QoS and power consumption than the state-of-the-art and heuristic alternatives.",

keywords = "AP sleep control, Cell-free massive MIMO, actor-critic framework, deep reinforcement learning, energy efficiency, power allocation",

author = "Xiukun Xu and Yanxiang Jiang and Yige Huang and Zheng, \{Fu Chun\}",

note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 10th International Conference on Computer and Communications, ICCC 2024 ; Conference date: 13-12-2024 Through 16-12-2024",

year = "2024",

doi = "10.1109/ICCC62609.2024.10942164",

language = "英语",

pages = "1663--1668",

journal = "Proceedings of the IEEE International Conference on Computer and Communications, ICCC",

issn = "2837-7109",

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

number = "2024",

}

TY - JOUR

T1 - A Nested DRL-Based Method for Power Allocation and AP Sleep Control in Cell-Free Massive MIMO Systems

AU - Xu, Xiukun

AU - Jiang, Yanxiang

AU - Huang, Yige

AU - Zheng, Fu Chun

PY - 2024

Y1 - 2024

N2 - Cell-free massive MIMO (CFmMIMO) systems are increasingly recognized as a key technology to enhance 6G network performance. The large-scale coverage of access points (APs) and irrational power allocation leads to low energy efficiency and suboptimal Quality of Service (QoS). This paper proposes a nested deep reinforcement learning (DRL)-based optimization method utilizing novel double nested actor-critic (AC) frameworks to optimize power allocation and AP sleep control, which efficiently addresses the complex decision-making processes involved in dynamic environments. Extensive simulations results show that our proposed method enhances the peak energy efficiency in CFmMIMO systems by 19.6% and achieves a better trade-off between QoS and power consumption than the state-of-the-art and heuristic alternatives.

AB - Cell-free massive MIMO (CFmMIMO) systems are increasingly recognized as a key technology to enhance 6G network performance. The large-scale coverage of access points (APs) and irrational power allocation leads to low energy efficiency and suboptimal Quality of Service (QoS). This paper proposes a nested deep reinforcement learning (DRL)-based optimization method utilizing novel double nested actor-critic (AC) frameworks to optimize power allocation and AP sleep control, which efficiently addresses the complex decision-making processes involved in dynamic environments. Extensive simulations results show that our proposed method enhances the peak energy efficiency in CFmMIMO systems by 19.6% and achieves a better trade-off between QoS and power consumption than the state-of-the-art and heuristic alternatives.

KW - AP sleep control

KW - Cell-free massive MIMO

KW - actor-critic framework

KW - deep reinforcement learning

KW - energy efficiency

KW - power allocation

UR - https://www.scopus.com/pages/publications/105006630649

U2 - 10.1109/ICCC62609.2024.10942164

DO - 10.1109/ICCC62609.2024.10942164

M3 - 会议文章

AN - SCOPUS:105006630649

SN - 2837-7109

SP - 1663

EP - 1668

JO - Proceedings of the IEEE International Conference on Computer and Communications, ICCC

JF - Proceedings of the IEEE International Conference on Computer and Communications, ICCC

IS - 2024

T2 - 10th International Conference on Computer and Communications, ICCC 2024

Y2 - 13 December 2024 through 16 December 2024

ER -

A Nested DRL-Based Method for Power Allocation and AP Sleep Control in Cell-Free Massive MIMO Systems

Abstract

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this