Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks

In a multi-cell network, interference management between adjacent cells is a key factor that determines the performance of the entire cellular network. In particular, in order to control inter-cell interference while providing a high data rate to users, it is very important for the base station (BS)...

Full description

Saved in:
Bibliographic Details
Main Authors: Hun Kim, Jaewoo So
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/13/4017
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319905495613440
author Hun Kim
Jaewoo So
author_facet Hun Kim
Jaewoo So
author_sort Hun Kim
collection DOAJ
description In a multi-cell network, interference management between adjacent cells is a key factor that determines the performance of the entire cellular network. In particular, in order to control inter-cell interference while providing a high data rate to users, it is very important for the base station (BS) of each cell to appropriately control the transmit power in the downlink. However, as the number of cells increases, controlling the downlink transmit power at the BS becomes increasingly difficult. In this paper, we propose a multi-agent deep reinforcement learning (MADRL)-based transmit power control scheme to maximize the sum rate in multi-cell networks. In particular, the proposed scheme incorporates a long short-term memory (LSTM) architecture into the MADRL scheme to retain state information across time slots and to use that information for subsequent action decisions, thereby improving the sum rate performance. In the proposed scheme, the agent of each BS uses only its local channel state information; consequently, it does not need to receive signal messages from adjacent agents. The simulation results show that the proposed scheme outperforms the existing MADRL scheme by reducing the amount of signal messages exchanged between links and improving the sum rate.
format Article
id doaj-art-00734044ade64bb499a5cd07a2a082c0
institution Kabale University
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-00734044ade64bb499a5cd07a2a082c02025-08-20T03:50:17ZengMDPI AGSensors1424-82202025-06-012513401710.3390/s25134017Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular NetworksHun Kim0Jaewoo So1Department of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaDepartment of Electronic Engineering, Sogang University, Seoul 04107, Republic of KoreaIn a multi-cell network, interference management between adjacent cells is a key factor that determines the performance of the entire cellular network. In particular, in order to control inter-cell interference while providing a high data rate to users, it is very important for the base station (BS) of each cell to appropriately control the transmit power in the downlink. However, as the number of cells increases, controlling the downlink transmit power at the BS becomes increasingly difficult. In this paper, we propose a multi-agent deep reinforcement learning (MADRL)-based transmit power control scheme to maximize the sum rate in multi-cell networks. In particular, the proposed scheme incorporates a long short-term memory (LSTM) architecture into the MADRL scheme to retain state information across time slots and to use that information for subsequent action decisions, thereby improving the sum rate performance. In the proposed scheme, the agent of each BS uses only its local channel state information; consequently, it does not need to receive signal messages from adjacent agents. The simulation results show that the proposed scheme outperforms the existing MADRL scheme by reducing the amount of signal messages exchanged between links and improving the sum rate.https://www.mdpi.com/1424-8220/25/13/4017multi-cell networkmulti-agent deep reinforcement learningcentralized training with decentralized executiontransmit power control
spellingShingle Hun Kim
Jaewoo So
Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks
Sensors
multi-cell network
multi-agent deep reinforcement learning
centralized training with decentralized execution
transmit power control
title Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks
title_full Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks
title_fullStr Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks
title_full_unstemmed Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks
title_short Distributed Multi-Agent Deep Reinforcement Learning-Based Transmit Power Control in Cellular Networks
title_sort distributed multi agent deep reinforcement learning based transmit power control in cellular networks
topic multi-cell network
multi-agent deep reinforcement learning
centralized training with decentralized execution
transmit power control
url https://www.mdpi.com/1424-8220/25/13/4017
work_keys_str_mv AT hunkim distributedmultiagentdeepreinforcementlearningbasedtransmitpowercontrolincellularnetworks
AT jaewooso distributedmultiagentdeepreinforcementlearningbasedtransmitpowercontrolincellularnetworks