Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN
Owing to the recent research and development on the Internet-of-Things (IoT) and machine-to-machine (M2M) communication, wireless sensor networks have attracted considerable attention. Among these networks, low power wide area networks (LPWANs), which realize low power, low data rate, and wide commu...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9467365/ |
_version_ | 1811274224386441216 |
---|---|
author | Aoto Kaburaki Koichi Adachi Osamu Takyu Mai Ohta Takeo Fujii |
author_facet | Aoto Kaburaki Koichi Adachi Osamu Takyu Mai Ohta Takeo Fujii |
author_sort | Aoto Kaburaki |
collection | DOAJ |
description | Owing to the recent research and development on the Internet-of-Things (IoT) and machine-to-machine (M2M) communication, wireless sensor networks have attracted considerable attention. Among these networks, low power wide area networks (LPWANs), which realize low power, low data rate, and wide communication area, are most commonly used for long-range communication. These networks adopt asynchronous random-access protocols, such as the pure ALOHA protocol in the medium access control (MAC) layer. Thus, there is a high possibility that multiple nodes transmit packets simultaneously on the same frequency channel, resulting in packet collisions. Carrier-sense multiple access/collision avoidance (CSMA/CA) and centralized resource allocation are effective for avoiding packet collisions. However, these schemes increase the energy consumption of battery-powered LPWAN nodes. In addition, LPWAN has a large coverage area; hence, there is a high possibility that the carrier sense will not work successfully. Thus, this paper proposes a simple but effective machine-learning-based scheme that tackles the packet collision problem by offsetting the transmission timings and avoiding unnecessary packet transmission in an autonomous decentralized manner. Each LPWAN node adjusts the transmission probability and timing using the Q-learning technique. The proposed scheme provides effective packet collision avoidance for LPWAN nodes without the need for an additional control signal. The computer simulation results show that the proposed scheme can improve the average packet delivery ratio (PDR) by 60% compared to the pure ALOHA protocol. |
first_indexed | 2024-04-12T23:15:08Z |
format | Article |
id | doaj.art-9812daf50b2b4100af8f78d3ff2b9d5b |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T23:15:08Z |
publishDate | 2021-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-9812daf50b2b4100af8f78d3ff2b9d5b2022-12-22T03:12:43ZengIEEEIEEE Access2169-35362021-01-019936519366110.1109/ACCESS.2021.30934219467365Autonomous Decentralized Traffic Control Using Q-Learning in LPWANAoto Kaburaki0https://orcid.org/0000-0002-5751-5852Koichi Adachi1https://orcid.org/0000-0003-3463-1233Osamu Takyu2https://orcid.org/0000-0003-3221-6714Mai Ohta3Takeo Fujii4https://orcid.org/0000-0002-7886-5560Advanced Wireless and Communication Research Center, The University of Electro-Communications, Tokyo, JapanAdvanced Wireless and Communication Research Center, The University of Electro-Communications, Tokyo, JapanDepartment of Electrical and Computer Engineering, Shinshu University, Nagano, JapanDepartment of Electronics Engineering and Computer Science, Fukuoka University, Fukuoka, JapanAdvanced Wireless and Communication Research Center, The University of Electro-Communications, Tokyo, JapanOwing to the recent research and development on the Internet-of-Things (IoT) and machine-to-machine (M2M) communication, wireless sensor networks have attracted considerable attention. Among these networks, low power wide area networks (LPWANs), which realize low power, low data rate, and wide communication area, are most commonly used for long-range communication. These networks adopt asynchronous random-access protocols, such as the pure ALOHA protocol in the medium access control (MAC) layer. Thus, there is a high possibility that multiple nodes transmit packets simultaneously on the same frequency channel, resulting in packet collisions. Carrier-sense multiple access/collision avoidance (CSMA/CA) and centralized resource allocation are effective for avoiding packet collisions. However, these schemes increase the energy consumption of battery-powered LPWAN nodes. In addition, LPWAN has a large coverage area; hence, there is a high possibility that the carrier sense will not work successfully. Thus, this paper proposes a simple but effective machine-learning-based scheme that tackles the packet collision problem by offsetting the transmission timings and avoiding unnecessary packet transmission in an autonomous decentralized manner. Each LPWAN node adjusts the transmission probability and timing using the Q-learning technique. The proposed scheme provides effective packet collision avoidance for LPWAN nodes without the need for an additional control signal. The computer simulation results show that the proposed scheme can improve the average packet delivery ratio (PDR) by 60% compared to the pure ALOHA protocol.https://ieeexplore.ieee.org/document/9467365/Internet of Things (IoT)LoRaWANlow power wide area networks (LPWAN)machine learningresource allocation |
spellingShingle | Aoto Kaburaki Koichi Adachi Osamu Takyu Mai Ohta Takeo Fujii Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN IEEE Access Internet of Things (IoT) LoRaWAN low power wide area networks (LPWAN) machine learning resource allocation |
title | Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN |
title_full | Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN |
title_fullStr | Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN |
title_full_unstemmed | Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN |
title_short | Autonomous Decentralized Traffic Control Using Q-Learning in LPWAN |
title_sort | autonomous decentralized traffic control using q learning in lpwan |
topic | Internet of Things (IoT) LoRaWAN low power wide area networks (LPWAN) machine learning resource allocation |
url | https://ieeexplore.ieee.org/document/9467365/ |
work_keys_str_mv | AT aotokaburaki autonomousdecentralizedtrafficcontrolusingqlearninginlpwan AT koichiadachi autonomousdecentralizedtrafficcontrolusingqlearninginlpwan AT osamutakyu autonomousdecentralizedtrafficcontrolusingqlearninginlpwan AT maiohta autonomousdecentralizedtrafficcontrolusingqlearninginlpwan AT takeofujii autonomousdecentralizedtrafficcontrolusingqlearninginlpwan |