Q-Learning-Based Multi-channel ALOHA MAC for LoRaWAN

Mohamed Osman Omar; Louai Al-Awami; Uthman Baroudi; Akram Fadhl Ahmed

doi:10.1007/s10922-025-09997-y

Q-Learning-Based Multi-channel ALOHA MAC for LoRaWAN

Mohamed Osman Omar, Louai Al-Awami^*, Uthman Baroudi, Akram Fadhl Ahmed

^*Corresponding author for this work

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

Abstract

LoRaWAN is a popular IoT wireless access technology that is characterized by low power and long range. This paper proposes a new decentralized access scheme that utilizes Reinforcement Learning to enhance the capacity of the multichannel ALOHA used by LoRaWAN. The performance of the proposed scheme is evaluated via extensive simulations and compared to the standard multichannel ALOHA in LoRaWAN. The simulation results demonstrate that the new scheme can achieve a throughput of compared to by the conventional multi-channel ALOHA scheme with. Moreover, collision rate and power consumption are both reduced substantially.

Original language	English
Article number	21
Journal	Journal of Network and Systems Management
Volume	34
Issue number	1
DOIs	https://doi.org/10.1007/s10922-025-09997-y
State	Published - Mar 2026

Bibliographical note

Publisher Copyright:
© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

Keywords

ALOHA
IoT
LoRaWAN
MAC
multichannel ALOHA
Q-Learning
RL

ASJC Scopus subject areas

Information Systems
Hardware and Architecture
Computer Networks and Communications
Strategy and Management

Access to Document

10.1007/s10922-025-09997-y

Cite this

@article{3ffb9749952a433c8cefd620cedf9021,

title = "Q-Learning-Based Multi-channel ALOHA MAC for LoRaWAN",

abstract = "LoRaWAN is a popular IoT wireless access technology that is characterized by low power and long range. This paper proposes a new decentralized access scheme that utilizes Reinforcement Learning to enhance the capacity of the multichannel ALOHA used by LoRaWAN. The performance of the proposed scheme is evaluated via extensive simulations and compared to the standard multichannel ALOHA in LoRaWAN. The simulation results demonstrate that the new scheme can achieve a throughput of compared to by the conventional multi-channel ALOHA scheme with. Moreover, collision rate and power consumption are both reduced substantially.",

keywords = "ALOHA, IoT, LoRaWAN, MAC, multichannel ALOHA, Q-Learning, RL",

author = "Omar, \{Mohamed Osman\} and Louai Al-Awami and Uthman Baroudi and Ahmed, \{Akram Fadhl\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.",

year = "2026",

month = mar,

doi = "10.1007/s10922-025-09997-y",

language = "English",

volume = "34",

journal = "Journal of Network and Systems Management",

issn = "1064-7570",

publisher = "Springer New York",

number = "1",

}

TY - JOUR

T1 - Q-Learning-Based Multi-channel ALOHA MAC for LoRaWAN

AU - Omar, Mohamed Osman

AU - Al-Awami, Louai

AU - Baroudi, Uthman

AU - Ahmed, Akram Fadhl

N1 - Publisher Copyright: © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

PY - 2026/3

Y1 - 2026/3

N2 - LoRaWAN is a popular IoT wireless access technology that is characterized by low power and long range. This paper proposes a new decentralized access scheme that utilizes Reinforcement Learning to enhance the capacity of the multichannel ALOHA used by LoRaWAN. The performance of the proposed scheme is evaluated via extensive simulations and compared to the standard multichannel ALOHA in LoRaWAN. The simulation results demonstrate that the new scheme can achieve a throughput of compared to by the conventional multi-channel ALOHA scheme with. Moreover, collision rate and power consumption are both reduced substantially.

AB - LoRaWAN is a popular IoT wireless access technology that is characterized by low power and long range. This paper proposes a new decentralized access scheme that utilizes Reinforcement Learning to enhance the capacity of the multichannel ALOHA used by LoRaWAN. The performance of the proposed scheme is evaluated via extensive simulations and compared to the standard multichannel ALOHA in LoRaWAN. The simulation results demonstrate that the new scheme can achieve a throughput of compared to by the conventional multi-channel ALOHA scheme with. Moreover, collision rate and power consumption are both reduced substantially.

KW - ALOHA

KW - IoT

KW - LoRaWAN

KW - MAC

KW - multichannel ALOHA

KW - Q-Learning

KW - RL

UR - https://www.scopus.com/pages/publications/105021003968

U2 - 10.1007/s10922-025-09997-y

DO - 10.1007/s10922-025-09997-y

M3 - Article

AN - SCOPUS:105021003968

SN - 1064-7570

VL - 34

JO - Journal of Network and Systems Management

JF - Journal of Network and Systems Management

IS - 1

M1 - 21

ER -

Q-Learning-Based Multi-channel ALOHA MAC for LoRaWAN

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this