Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks

<p dir="ltr">Hybrid radio frequency (RF) and visible light communication (VLC) networks can provide high throughput and energy efficiency with VLC access points (APs) while ensuring ubiquitous coverage with RF APs. Due to dynamic channel conditions and limited resources, the hybrid R...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Bekir Sait Ciftler (17541801) (author)
مؤلفون آخرون: Abdulmalik Alwarafy (17984104) (author), Mohamed Abdallah (3073191) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513507018407936
author Bekir Sait Ciftler (17541801)
author2 Abdulmalik Alwarafy (17984104)
Mohamed Abdallah (3073191)
author2_role author
author
author_facet Bekir Sait Ciftler (17541801)
Abdulmalik Alwarafy (17984104)
Mohamed Abdallah (3073191)
author_role author
dc.creator.none.fl_str_mv Bekir Sait Ciftler (17541801)
Abdulmalik Alwarafy (17984104)
Mohamed Abdallah (3073191)
dc.date.none.fl_str_mv 2021-12-31T21:00:00Z
dc.identifier.none.fl_str_mv 10.1109/jphot.2021.3139678
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Distributed_DRL-Based_Downlink_Power_Allocation_for_Hybrid_RF_VLC_Networks/26840920
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Communications engineering
Information and computing sciences
Machine learning
DRL
heuristic algorithms
hybrid RF/VLC networks
resource allocation
Resource management
Heuristic algorithms
Quality of service
Optimization
Hybrid power systems
Radio frequency
Optical filters
dc.title.none.fl_str_mv Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Hybrid radio frequency (RF) and visible light communication (VLC) networks can provide high throughput and energy efficiency with VLC access points (APs) while ensuring ubiquitous coverage with RF APs. Due to dynamic channel conditions and limited resources, the hybrid RF/VLC networks’ resource allocation problem is complex and challenging. Conventional resource allocation techniques fail to overcome these challenges. Heuristic methods can solve high complexity problems; however, they are not robust against changes such as dynamic channel conditions or alternating user requirements. Heuristic methods require centralized control for stability which adds communication overhead between APs. Deep Reinforcement Learning (DRL) based solutions can solve high complexity, dynamic channel conditions, and alternating user requirements while not requiring centralized control. In this paper, we formulate a distributed downlink power allocation problem to optimize the transmit power for users to reach target data rates in hybrid RF/VLC networks. Then, we propose a distributed DRL-based algorithm Deep Deterministic Policy Gradient (DDPG), to solve the formulated computationally-intensive problem. We implement a simulation environment to benchmark the proposed distributed DRL-based method against other methods such as Q-Learning (QL) and Deep Q-Networks (DQN), and centralized heuristic power allocation algorithms. Our simulation results show that the distributed DDPG-based algorithm learns to adapt against changes in the channel or user requirements, while centralized Genetic Algorithm and Particle Swarm Optimization-based algorithms fail to endure against these changes even with coordination between APs. Additionally, we quantify the performance of the DDPG-based algorithm to prevail amid DRL-based algorithms at the expense of higher implementation complexity.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Photonics Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jphot.2021.3139678" target="_blank">https://dx.doi.org/10.1109/jphot.2021.3139678</a></p>
eu_rights_str_mv openAccess
id Manara2_3e52488b263424d331100dea286cd297
identifier_str_mv 10.1109/jphot.2021.3139678
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/26840920
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC NetworksBekir Sait Ciftler (17541801)Abdulmalik Alwarafy (17984104)Mohamed Abdallah (3073191)EngineeringCommunications engineeringInformation and computing sciencesMachine learningDRLheuristic algorithmshybrid RF/VLC networksresource allocationResource managementHeuristic algorithmsQuality of serviceOptimizationHybrid power systemsRadio frequencyOptical filters<p dir="ltr">Hybrid radio frequency (RF) and visible light communication (VLC) networks can provide high throughput and energy efficiency with VLC access points (APs) while ensuring ubiquitous coverage with RF APs. Due to dynamic channel conditions and limited resources, the hybrid RF/VLC networks’ resource allocation problem is complex and challenging. Conventional resource allocation techniques fail to overcome these challenges. Heuristic methods can solve high complexity problems; however, they are not robust against changes such as dynamic channel conditions or alternating user requirements. Heuristic methods require centralized control for stability which adds communication overhead between APs. Deep Reinforcement Learning (DRL) based solutions can solve high complexity, dynamic channel conditions, and alternating user requirements while not requiring centralized control. In this paper, we formulate a distributed downlink power allocation problem to optimize the transmit power for users to reach target data rates in hybrid RF/VLC networks. Then, we propose a distributed DRL-based algorithm Deep Deterministic Policy Gradient (DDPG), to solve the formulated computationally-intensive problem. We implement a simulation environment to benchmark the proposed distributed DRL-based method against other methods such as Q-Learning (QL) and Deep Q-Networks (DQN), and centralized heuristic power allocation algorithms. Our simulation results show that the distributed DDPG-based algorithm learns to adapt against changes in the channel or user requirements, while centralized Genetic Algorithm and Particle Swarm Optimization-based algorithms fail to endure against these changes even with coordination between APs. Additionally, we quantify the performance of the DDPG-based algorithm to prevail amid DRL-based algorithms at the expense of higher implementation complexity.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Photonics Journal<br>License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/jphot.2021.3139678" target="_blank">https://dx.doi.org/10.1109/jphot.2021.3139678</a></p>2021-12-31T21:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/jphot.2021.3139678https://figshare.com/articles/journal_contribution/Distributed_DRL-Based_Downlink_Power_Allocation_for_Hybrid_RF_VLC_Networks/26840920CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/268409202021-12-31T21:00:00Z
spellingShingle Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
Bekir Sait Ciftler (17541801)
Engineering
Communications engineering
Information and computing sciences
Machine learning
DRL
heuristic algorithms
hybrid RF/VLC networks
resource allocation
Resource management
Heuristic algorithms
Quality of service
Optimization
Hybrid power systems
Radio frequency
Optical filters
status_str publishedVersion
title Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
title_full Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
title_fullStr Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
title_full_unstemmed Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
title_short Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
title_sort Distributed DRL-Based Downlink Power Allocation for Hybrid RF/VLC Networks
topic Engineering
Communications engineering
Information and computing sciences
Machine learning
DRL
heuristic algorithms
hybrid RF/VLC networks
resource allocation
Resource management
Heuristic algorithms
Quality of service
Optimization
Hybrid power systems
Radio frequency
Optical filters