Joint Self-Organizing Maps and Knowledge-Distillation-Based Communication-Efficient Federated Learning for Resource-Constrained UAV-IoT Systems

The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fib...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE internet of things journal 2024-05, Vol.11 (9), p.15504-15522
Hauptverfasser: Gad, Gad, Farrag, Aya, Aboulfotouh, Ahmed, Bedda, Khaled, Fadlullah, Zubair Md, Fouda, Mostafa M.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 15522
container_issue 9
container_start_page 15504
container_title IEEE internet of things journal
container_volume 11
creator Gad, Gad
Farrag, Aya
Aboulfotouh, Ahmed
Bedda, Khaled
Fadlullah, Zubair Md
Fouda, Mostafa M.
description The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fiber connections in vast landscapes with sparse populations. The constrained energy of UAVs results in limited coverage area and flight time, which in turn reduces the potential of UAVs to provide task-oriented wireless communication links. In this article, we explore path optimization and transmission organization algorithms to minimize flight time and extend the range of UAVs performing collaborative federated learning (FL) among geographically dispersed nodes communicating through wireless connections offered by UAVs coupled with device-to-device (D2D) networks. The UAV orchestrates FL between spatially scattered homes via long-range radio wireless communication. We formulate the drone path optimization as a traveling salesman problem (TSP) and employ self-organizing maps (SOM) for path planning. Additionally, knowledge distillation (KD)-based FL is used to reduce communication overhead for the resource-constrained UAV-IoT system. Experimental results demonstrate SOM's ability to represent the topological structure of nodes and produce a cost-efficient Hamiltonian cycle, from which the drone path is derived. Our results demonstrate the communication efficiency and utility of KD-based FL compared to model-based FL methods. The proposed hybrid solution enables energy-constrained UAVs to perform FL over large areas leveraging a shared data set for KD and a SOM-based path optimization algorithm.
doi_str_mv 10.1109/JIOT.2023.3349295
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_10379499</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10379499</ieee_id><sourcerecordid>3046911684</sourcerecordid><originalsourceid>FETCH-LOGICAL-c294t-25d02a5ff2aacb53f196328530d925a7da31db5b9890868cb53b8622911be6e73</originalsourceid><addsrcrecordid>eNpNkN1OAjEQhTdGEwnyACZebOJ1sT_710tEUBBDIuDtprs7JSVLi-0Sgy_hK9vNcsHVTCbfOTNzguCe4CEhmD_NZ8v1kGLKhoxFnPL4KuhRRlMUJQm9vuhvg4FzO4yxl8WEJ73gb26UbsIV1BIt7VZo9av0NvwQBxcKXYXv2vzUUG0BvSjXqLoWjTIaPQsHVTg2-_1Rq7KbTaRUpQLvNoUKrGg8sQBhdWsojQ0_wZmjLQGNjXaNFUp7YjP6QjOzDlcn18De3QU3UtQOBufaDzbTyXr8hhbL19l4tEAl5VGDaFxhKmIpqRBlETPpn2E0ixmuOI1FWglGqiIueMZxlmQtUmQJpZyQAhJIWT947HwP1nwfwTX5zt-m_cqc4SjxXJJFniIdVVrjnAWZH6zaC3vKCc7b6PM2-ryNPj9H7zUPnUYBwAXPUh5xzv4BIzmBKQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3046911684</pqid></control><display><type>article</type><title>Joint Self-Organizing Maps and Knowledge-Distillation-Based Communication-Efficient Federated Learning for Resource-Constrained UAV-IoT Systems</title><source>IEEE Electronic Library (IEL)</source><creator>Gad, Gad ; Farrag, Aya ; Aboulfotouh, Ahmed ; Bedda, Khaled ; Fadlullah, Zubair Md ; Fouda, Mostafa M.</creator><creatorcontrib>Gad, Gad ; Farrag, Aya ; Aboulfotouh, Ahmed ; Bedda, Khaled ; Fadlullah, Zubair Md ; Fouda, Mostafa M.</creatorcontrib><description>The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fiber connections in vast landscapes with sparse populations. The constrained energy of UAVs results in limited coverage area and flight time, which in turn reduces the potential of UAVs to provide task-oriented wireless communication links. In this article, we explore path optimization and transmission organization algorithms to minimize flight time and extend the range of UAVs performing collaborative federated learning (FL) among geographically dispersed nodes communicating through wireless connections offered by UAVs coupled with device-to-device (D2D) networks. The UAV orchestrates FL between spatially scattered homes via long-range radio wireless communication. We formulate the drone path optimization as a traveling salesman problem (TSP) and employ self-organizing maps (SOM) for path planning. Additionally, knowledge distillation (KD)-based FL is used to reduce communication overhead for the resource-constrained UAV-IoT system. Experimental results demonstrate SOM's ability to represent the topological structure of nodes and produce a cost-efficient Hamiltonian cycle, from which the drone path is derived. Our results demonstrate the communication efficiency and utility of KD-based FL compared to model-based FL methods. The proposed hybrid solution enables energy-constrained UAVs to perform FL over large areas leveraging a shared data set for KD and a SOM-based path optimization algorithm.</description><identifier>ISSN: 2327-4662</identifier><identifier>EISSN: 2327-4662</identifier><identifier>DOI: 10.1109/JIOT.2023.3349295</identifier><identifier>CODEN: IITJAU</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Autonomous aerial vehicles ; Distillation ; Drones ; Federated learning ; Federated learning (FL) ; Flight time ; human activity recognition (HAR) ; Internet of Things ; knowledge distillation (KD) ; Machine learning ; Monitoring ; Nodes ; Optical fibers ; Optimization ; Path planning ; Radio equipment ; Self organizing maps ; Self-organizing feature maps ; self-organizing map (SOM) ; Traveling salesman problem ; unmanned aerial vehicle (UAV) path optimization ; Unmanned aerial vehicles ; Wireless communications</subject><ispartof>IEEE internet of things journal, 2024-05, Vol.11 (9), p.15504-15522</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c294t-25d02a5ff2aacb53f196328530d925a7da31db5b9890868cb53b8622911be6e73</citedby><cites>FETCH-LOGICAL-c294t-25d02a5ff2aacb53f196328530d925a7da31db5b9890868cb53b8622911be6e73</cites><orcidid>0000-0002-4785-2425 ; 0000-0001-6350-9742 ; 0000-0003-1790-8640 ; 0000-0001-9177-9950</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10379499$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10379499$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Gad, Gad</creatorcontrib><creatorcontrib>Farrag, Aya</creatorcontrib><creatorcontrib>Aboulfotouh, Ahmed</creatorcontrib><creatorcontrib>Bedda, Khaled</creatorcontrib><creatorcontrib>Fadlullah, Zubair Md</creatorcontrib><creatorcontrib>Fouda, Mostafa M.</creatorcontrib><title>Joint Self-Organizing Maps and Knowledge-Distillation-Based Communication-Efficient Federated Learning for Resource-Constrained UAV-IoT Systems</title><title>IEEE internet of things journal</title><addtitle>JIoT</addtitle><description>The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fiber connections in vast landscapes with sparse populations. The constrained energy of UAVs results in limited coverage area and flight time, which in turn reduces the potential of UAVs to provide task-oriented wireless communication links. In this article, we explore path optimization and transmission organization algorithms to minimize flight time and extend the range of UAVs performing collaborative federated learning (FL) among geographically dispersed nodes communicating through wireless connections offered by UAVs coupled with device-to-device (D2D) networks. The UAV orchestrates FL between spatially scattered homes via long-range radio wireless communication. We formulate the drone path optimization as a traveling salesman problem (TSP) and employ self-organizing maps (SOM) for path planning. Additionally, knowledge distillation (KD)-based FL is used to reduce communication overhead for the resource-constrained UAV-IoT system. Experimental results demonstrate SOM's ability to represent the topological structure of nodes and produce a cost-efficient Hamiltonian cycle, from which the drone path is derived. Our results demonstrate the communication efficiency and utility of KD-based FL compared to model-based FL methods. The proposed hybrid solution enables energy-constrained UAVs to perform FL over large areas leveraging a shared data set for KD and a SOM-based path optimization algorithm.</description><subject>Algorithms</subject><subject>Autonomous aerial vehicles</subject><subject>Distillation</subject><subject>Drones</subject><subject>Federated learning</subject><subject>Federated learning (FL)</subject><subject>Flight time</subject><subject>human activity recognition (HAR)</subject><subject>Internet of Things</subject><subject>knowledge distillation (KD)</subject><subject>Machine learning</subject><subject>Monitoring</subject><subject>Nodes</subject><subject>Optical fibers</subject><subject>Optimization</subject><subject>Path planning</subject><subject>Radio equipment</subject><subject>Self organizing maps</subject><subject>Self-organizing feature maps</subject><subject>self-organizing map (SOM)</subject><subject>Traveling salesman problem</subject><subject>unmanned aerial vehicle (UAV) path optimization</subject><subject>Unmanned aerial vehicles</subject><subject>Wireless communications</subject><issn>2327-4662</issn><issn>2327-4662</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkN1OAjEQhTdGEwnyACZebOJ1sT_710tEUBBDIuDtprs7JSVLi-0Sgy_hK9vNcsHVTCbfOTNzguCe4CEhmD_NZ8v1kGLKhoxFnPL4KuhRRlMUJQm9vuhvg4FzO4yxl8WEJ73gb26UbsIV1BIt7VZo9av0NvwQBxcKXYXv2vzUUG0BvSjXqLoWjTIaPQsHVTg2-_1Rq7KbTaRUpQLvNoUKrGg8sQBhdWsojQ0_wZmjLQGNjXaNFUp7YjP6QjOzDlcn18De3QU3UtQOBufaDzbTyXr8hhbL19l4tEAl5VGDaFxhKmIpqRBlETPpn2E0ixmuOI1FWglGqiIueMZxlmQtUmQJpZyQAhJIWT947HwP1nwfwTX5zt-m_cqc4SjxXJJFniIdVVrjnAWZH6zaC3vKCc7b6PM2-ryNPj9H7zUPnUYBwAXPUh5xzv4BIzmBKQ</recordid><startdate>20240501</startdate><enddate>20240501</enddate><creator>Gad, Gad</creator><creator>Farrag, Aya</creator><creator>Aboulfotouh, Ahmed</creator><creator>Bedda, Khaled</creator><creator>Fadlullah, Zubair Md</creator><creator>Fouda, Mostafa M.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-4785-2425</orcidid><orcidid>https://orcid.org/0000-0001-6350-9742</orcidid><orcidid>https://orcid.org/0000-0003-1790-8640</orcidid><orcidid>https://orcid.org/0000-0001-9177-9950</orcidid></search><sort><creationdate>20240501</creationdate><title>Joint Self-Organizing Maps and Knowledge-Distillation-Based Communication-Efficient Federated Learning for Resource-Constrained UAV-IoT Systems</title><author>Gad, Gad ; Farrag, Aya ; Aboulfotouh, Ahmed ; Bedda, Khaled ; Fadlullah, Zubair Md ; Fouda, Mostafa M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c294t-25d02a5ff2aacb53f196328530d925a7da31db5b9890868cb53b8622911be6e73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Autonomous aerial vehicles</topic><topic>Distillation</topic><topic>Drones</topic><topic>Federated learning</topic><topic>Federated learning (FL)</topic><topic>Flight time</topic><topic>human activity recognition (HAR)</topic><topic>Internet of Things</topic><topic>knowledge distillation (KD)</topic><topic>Machine learning</topic><topic>Monitoring</topic><topic>Nodes</topic><topic>Optical fibers</topic><topic>Optimization</topic><topic>Path planning</topic><topic>Radio equipment</topic><topic>Self organizing maps</topic><topic>Self-organizing feature maps</topic><topic>self-organizing map (SOM)</topic><topic>Traveling salesman problem</topic><topic>unmanned aerial vehicle (UAV) path optimization</topic><topic>Unmanned aerial vehicles</topic><topic>Wireless communications</topic><toplevel>online_resources</toplevel><creatorcontrib>Gad, Gad</creatorcontrib><creatorcontrib>Farrag, Aya</creatorcontrib><creatorcontrib>Aboulfotouh, Ahmed</creatorcontrib><creatorcontrib>Bedda, Khaled</creatorcontrib><creatorcontrib>Fadlullah, Zubair Md</creatorcontrib><creatorcontrib>Fouda, Mostafa M.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE internet of things journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gad, Gad</au><au>Farrag, Aya</au><au>Aboulfotouh, Ahmed</au><au>Bedda, Khaled</au><au>Fadlullah, Zubair Md</au><au>Fouda, Mostafa M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Joint Self-Organizing Maps and Knowledge-Distillation-Based Communication-Efficient Federated Learning for Resource-Constrained UAV-IoT Systems</atitle><jtitle>IEEE internet of things journal</jtitle><stitle>JIoT</stitle><date>2024-05-01</date><risdate>2024</risdate><volume>11</volume><issue>9</issue><spage>15504</spage><epage>15522</epage><pages>15504-15522</pages><issn>2327-4662</issn><eissn>2327-4662</eissn><coden>IITJAU</coden><abstract>The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fiber connections in vast landscapes with sparse populations. The constrained energy of UAVs results in limited coverage area and flight time, which in turn reduces the potential of UAVs to provide task-oriented wireless communication links. In this article, we explore path optimization and transmission organization algorithms to minimize flight time and extend the range of UAVs performing collaborative federated learning (FL) among geographically dispersed nodes communicating through wireless connections offered by UAVs coupled with device-to-device (D2D) networks. The UAV orchestrates FL between spatially scattered homes via long-range radio wireless communication. We formulate the drone path optimization as a traveling salesman problem (TSP) and employ self-organizing maps (SOM) for path planning. Additionally, knowledge distillation (KD)-based FL is used to reduce communication overhead for the resource-constrained UAV-IoT system. Experimental results demonstrate SOM's ability to represent the topological structure of nodes and produce a cost-efficient Hamiltonian cycle, from which the drone path is derived. Our results demonstrate the communication efficiency and utility of KD-based FL compared to model-based FL methods. The proposed hybrid solution enables energy-constrained UAVs to perform FL over large areas leveraging a shared data set for KD and a SOM-based path optimization algorithm.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/JIOT.2023.3349295</doi><tpages>19</tpages><orcidid>https://orcid.org/0000-0002-4785-2425</orcidid><orcidid>https://orcid.org/0000-0001-6350-9742</orcidid><orcidid>https://orcid.org/0000-0003-1790-8640</orcidid><orcidid>https://orcid.org/0000-0001-9177-9950</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2327-4662
ispartof IEEE internet of things journal, 2024-05, Vol.11 (9), p.15504-15522
issn 2327-4662
2327-4662
language eng
recordid cdi_ieee_primary_10379499
source IEEE Electronic Library (IEL)
subjects Algorithms
Autonomous aerial vehicles
Distillation
Drones
Federated learning
Federated learning (FL)
Flight time
human activity recognition (HAR)
Internet of Things
knowledge distillation (KD)
Machine learning
Monitoring
Nodes
Optical fibers
Optimization
Path planning
Radio equipment
Self organizing maps
Self-organizing feature maps
self-organizing map (SOM)
Traveling salesman problem
unmanned aerial vehicle (UAV) path optimization
Unmanned aerial vehicles
Wireless communications
title Joint Self-Organizing Maps and Knowledge-Distillation-Based Communication-Efficient Federated Learning for Resource-Constrained UAV-IoT Systems
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A25%3A08IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Joint%20Self-Organizing%20Maps%20and%20Knowledge-Distillation-Based%20Communication-Efficient%20Federated%20Learning%20for%20Resource-Constrained%20UAV-IoT%20Systems&rft.jtitle=IEEE%20internet%20of%20things%20journal&rft.au=Gad,%20Gad&rft.date=2024-05-01&rft.volume=11&rft.issue=9&rft.spage=15504&rft.epage=15522&rft.pages=15504-15522&rft.issn=2327-4662&rft.eissn=2327-4662&rft.coden=IITJAU&rft_id=info:doi/10.1109/JIOT.2023.3349295&rft_dat=%3Cproquest_RIE%3E3046911684%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3046911684&rft_id=info:pmid/&rft_ieee_id=10379499&rfr_iscdi=true