Reinforcement Learning based Per-antenna Discrete Power Control for Massive MIMO Systems

Navneet Garg; Mathini Sellathurai; Tharmalingam Ratnarajah

doi:10.1109/IEEECONF51394.2020.9443383

Reinforcement Learning based Per-antenna Discrete Power Control for Massive MIMO Systems

Navneet Garg, Mathini Sellathurai, Tharmalingam Ratnarajah

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

57 Downloads (Pure)

Abstract

Power consumption is one of the major issues in massive MIMO (multiple input multiple output) systems, causing increased long-term operational cost and overheating issues. In this paper, we consider per-antenna power allocation with a given finite set of power levels towards maximizing the long-term energy efficiency of the multi-user systems, while satisfying the QoS (quality of service) constraints at the end users in terms of required SINRs (signal-to-interference-plus-noise ratio), which depends on channel information. Assuming channel states to vary as a Markov process, the constraint problem is modeled as an unconstraint problem, followed by the power allocation based on Q-learning algorithm. Simulation results are presented to demonstrate the successful minimization of power consumption while achieving the SINR threshold at users.

Original language	English
Title of host publication	54th Asilomar Conference on Signals, Systems, and Computers 2020
Editors	Michael B. Matthews
Publisher	IEEE
Pages	1028-1032
Number of pages	5
ISBN (Electronic)	9780738131269
DOIs	https://doi.org/10.1109/IEEECONF51394.2020.9443383
Publication status	Published - 3 Jun 2021
Event	54th Asilomar Conference on Signals, Systems and Computers 2020 - Pacific Grove, United States Duration: 1 Nov 2020 → 5 Nov 2020

Conference

Conference	54th Asilomar Conference on Signals, Systems and Computers 2020
Abbreviated title	ACSSC 2020
Country/Territory	United States
City	Pacific Grove
Period	1/11/20 → 5/11/20

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

UN SDGs

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

Access to Document

10.1109/IEEECONF51394.2020.9443383

Download pdf
© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 409 KB

Cite this

@inproceedings{3c20f82c39d6482fa1f695a33597b9bf,

title = "Reinforcement Learning based Per-antenna Discrete Power Control for Massive MIMO Systems",

abstract = "Power consumption is one of the major issues in massive MIMO (multiple input multiple output) systems, causing increased long-term operational cost and overheating issues. In this paper, we consider per-antenna power allocation with a given finite set of power levels towards maximizing the long-term energy efficiency of the multi-user systems, while satisfying the QoS (quality of service) constraints at the end users in terms of required SINRs (signal-to-interference-plus-noise ratio), which depends on channel information. Assuming channel states to vary as a Markov process, the constraint problem is modeled as an unconstraint problem, followed by the power allocation based on Q-learning algorithm. Simulation results are presented to demonstrate the successful minimization of power consumption while achieving the SINR threshold at users.",

author = "Navneet Garg and Mathini Sellathurai and Tharmalingam Ratnarajah",

note = "Funding Information: The work was supported by the U.K. Engineering and Physical Sciences Research Council (EPSRC) under Grants EP/P009549/1 and EP/P009670/1. Publisher Copyright: {\textcopyright} 2020 IEEE.; 54th Asilomar Conference on Signals, Systems and Computers 2020, ACSSC 2020 ; Conference date: 01-11-2020 Through 05-11-2020",

year = "2021",

month = jun,

day = "3",

doi = "10.1109/IEEECONF51394.2020.9443383",

language = "English",

pages = "1028--1032",

editor = "Matthews, {Michael B.}",

booktitle = "54th Asilomar Conference on Signals, Systems, and Computers 2020",

publisher = "IEEE",

address = "United States",

}

Garg, N, Sellathurai, M & Ratnarajah, T 2021, Reinforcement Learning based Per-antenna Discrete Power Control for Massive MIMO Systems. in MB Matthews (ed.), 54th Asilomar Conference on Signals, Systems, and Computers 2020. IEEE, pp. 1028-1032, 54th Asilomar Conference on Signals, Systems and Computers 2020, Pacific Grove, California, United States, 1/11/20. https://doi.org/10.1109/IEEECONF51394.2020.9443383

TY - GEN

T1 - Reinforcement Learning based Per-antenna Discrete Power Control for Massive MIMO Systems

AU - Garg, Navneet

AU - Sellathurai, Mathini

AU - Ratnarajah, Tharmalingam

PY - 2021/6/3

Y1 - 2021/6/3

N2 - Power consumption is one of the major issues in massive MIMO (multiple input multiple output) systems, causing increased long-term operational cost and overheating issues. In this paper, we consider per-antenna power allocation with a given finite set of power levels towards maximizing the long-term energy efficiency of the multi-user systems, while satisfying the QoS (quality of service) constraints at the end users in terms of required SINRs (signal-to-interference-plus-noise ratio), which depends on channel information. Assuming channel states to vary as a Markov process, the constraint problem is modeled as an unconstraint problem, followed by the power allocation based on Q-learning algorithm. Simulation results are presented to demonstrate the successful minimization of power consumption while achieving the SINR threshold at users.

AB - Power consumption is one of the major issues in massive MIMO (multiple input multiple output) systems, causing increased long-term operational cost and overheating issues. In this paper, we consider per-antenna power allocation with a given finite set of power levels towards maximizing the long-term energy efficiency of the multi-user systems, while satisfying the QoS (quality of service) constraints at the end users in terms of required SINRs (signal-to-interference-plus-noise ratio), which depends on channel information. Assuming channel states to vary as a Markov process, the constraint problem is modeled as an unconstraint problem, followed by the power allocation based on Q-learning algorithm. Simulation results are presented to demonstrate the successful minimization of power consumption while achieving the SINR threshold at users.

UR - http://www.scopus.com/inward/record.url?scp=85107805321&partnerID=8YFLogxK

U2 - 10.1109/IEEECONF51394.2020.9443383

DO - 10.1109/IEEECONF51394.2020.9443383

M3 - Conference contribution

AN - SCOPUS:85107805321

SP - 1028

EP - 1032

BT - 54th Asilomar Conference on Signals, Systems, and Computers 2020

A2 - Matthews, Michael B.

PB - IEEE

T2 - 54th Asilomar Conference on Signals, Systems and Computers 2020

Y2 - 1 November 2020 through 5 November 2020

ER -

Reinforcement Learning based Per-antenna Discrete Power Control for Massive MIMO Systems

Abstract

Conference

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this