RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks

Applications of wireless sensor networks have significantly increased in the modern era. These networks operate on a limited power supply in the form of batteries, which are normally difficult to replace on a frequent basis. In wireless sensor networks, sensor nodes alternate between sleep and activ...

Full description

Saved in:
Bibliographic Details
Main Authors: Owais Khan, Sana Ullah, Muzammil Khan, Han-Chieh Chao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Information
Subjects:
Online Access:https://www.mdpi.com/2078-2489/16/5/369
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126375574306816
author Owais Khan
Sana Ullah
Muzammil Khan
Han-Chieh Chao
author_facet Owais Khan
Sana Ullah
Muzammil Khan
Han-Chieh Chao
author_sort Owais Khan
collection DOAJ
description Applications of wireless sensor networks have significantly increased in the modern era. These networks operate on a limited power supply in the form of batteries, which are normally difficult to replace on a frequent basis. In wireless sensor networks, sensor nodes alternate between sleep and active states to conserve energy through different methods. Duty cycling is among the most commonly used methods. However, it suffers from problems like unnecessary idle listening, extra energy consumption, and packet drop rate. A Deep Reinforcement Learning-based B-MAC protocol called (RL-BMAC) has been proposed to address this issue. The proposed protocol deploys a deep reinforcement learning agent with fixed hyperparameters to optimize the duty cycling of the nodes. The reinforcement learning agent monitors essential parameters such as energy level, packet drop rate, neighboring nodes’ status, and preamble sampling. The agent stores the information as a representative state and adjusts the duty cycling of all nodes. The performance of RL-BMAC is compared to that of conventional B-MAC through extensive simulations. The results obtained from the simulations indicate that RL-BMAC outperforms B-MAC in terms of throughput by 58.5%, packet drop rate by 44.8%, energy efficiency by 35%, and latency by 26.93%
format Article
id doaj-art-eae382de0a594c76a02e0f20b6812c60
institution OA Journals
issn 2078-2489
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Information
spelling doaj-art-eae382de0a594c76a02e0f20b6812c602025-08-20T02:33:57ZengMDPI AGInformation2078-24892025-04-0116536910.3390/info16050369RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor NetworksOwais Khan0Sana Ullah1Muzammil Khan2Han-Chieh Chao3Department of Computer and Software Technology, University of Swat, Swat 19120, PakistanDepartment of Computer and Software Technology, University of Swat, Swat 19120, PakistanDepartment of Computer and Software Technology, University of Swat, Swat 19120, PakistanDepartment of Applied Informatics, Fo Guang University, Yilan 262307, TaiwanApplications of wireless sensor networks have significantly increased in the modern era. These networks operate on a limited power supply in the form of batteries, which are normally difficult to replace on a frequent basis. In wireless sensor networks, sensor nodes alternate between sleep and active states to conserve energy through different methods. Duty cycling is among the most commonly used methods. However, it suffers from problems like unnecessary idle listening, extra energy consumption, and packet drop rate. A Deep Reinforcement Learning-based B-MAC protocol called (RL-BMAC) has been proposed to address this issue. The proposed protocol deploys a deep reinforcement learning agent with fixed hyperparameters to optimize the duty cycling of the nodes. The reinforcement learning agent monitors essential parameters such as energy level, packet drop rate, neighboring nodes’ status, and preamble sampling. The agent stores the information as a representative state and adjusts the duty cycling of all nodes. The performance of RL-BMAC is compared to that of conventional B-MAC through extensive simulations. The results obtained from the simulations indicate that RL-BMAC outperforms B-MAC in terms of throughput by 58.5%, packet drop rate by 44.8%, energy efficiency by 35%, and latency by 26.93%https://www.mdpi.com/2078-2489/16/5/369wireless sensor networksmachine learningenergy optimizationdeep reinforcement learningMAC protocols
spellingShingle Owais Khan
Sana Ullah
Muzammil Khan
Han-Chieh Chao
RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks
Information
wireless sensor networks
machine learning
energy optimization
deep reinforcement learning
MAC protocols
title RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks
title_full RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks
title_fullStr RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks
title_full_unstemmed RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks
title_short RL-BMAC: An RL-Based MAC Protocol for Performance Optimization in Wireless Sensor Networks
title_sort rl bmac an rl based mac protocol for performance optimization in wireless sensor networks
topic wireless sensor networks
machine learning
energy optimization
deep reinforcement learning
MAC protocols
url https://www.mdpi.com/2078-2489/16/5/369
work_keys_str_mv AT owaiskhan rlbmacanrlbasedmacprotocolforperformanceoptimizationinwirelesssensornetworks
AT sanaullah rlbmacanrlbasedmacprotocolforperformanceoptimizationinwirelesssensornetworks
AT muzammilkhan rlbmacanrlbasedmacprotocolforperformanceoptimizationinwirelesssensornetworks
AT hanchiehchao rlbmacanrlbasedmacprotocolforperformanceoptimizationinwirelesssensornetworks