Efficiency Optimization Method of Wireless Federated Learning Considering Computational Capability and Channel State

Due to the explosive growth in the variety of smart mobile terminals in wireless networks, the increasing computing capability of mobile chips, and the public's growing concern for personal privacy, it is a better solution to decentralize the deep learning framework for mobile services that can...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (International Conference on Communication Technology. Online) s. 788 - 793
Hlavní autori: Pang, Guohao, Li, Fengguo, Zhu, Xiaorong
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 20.10.2023
Predmet:
ISSN:2576-7828
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Due to the explosive growth in the variety of smart mobile terminals in wireless networks, the increasing computing capability of mobile chips, and the public's growing concern for personal privacy, it is a better solution to decentralize the deep learning framework for mobile services that can enhance user experience to the mobile terminal layer. In this paper, we study the joint optimization problem of processor performance and channel state in a non-independent distribution scenario (non-IID), while considering the user's device experience problem to improve the battery efficiency of the terminal device (TD) as much as possible and maximize the efficiency of the federated learning (FL) system while ensuring low local upload latency. To improve the efficiency of wireless federated learning (WFL), we propose a specific and complete scheduling strategy involving both computational and communication aspects. First, we model the total problem and decouple it into several sub-problems to solve according to the nature of the variables. Then, we propose a Reduced Load algorithm (RL) to solve the task allocation problem and a dynamic bandwidth allocation strategy to solve the bandwidth allocation problem. Simulation results show that the proposed scheduling strategy can achieve higher learning performance with lower training latency and is capable of adaptively adjusting the bandwidth allocation to decrease upload latency.
AbstractList Due to the explosive growth in the variety of smart mobile terminals in wireless networks, the increasing computing capability of mobile chips, and the public's growing concern for personal privacy, it is a better solution to decentralize the deep learning framework for mobile services that can enhance user experience to the mobile terminal layer. In this paper, we study the joint optimization problem of processor performance and channel state in a non-independent distribution scenario (non-IID), while considering the user's device experience problem to improve the battery efficiency of the terminal device (TD) as much as possible and maximize the efficiency of the federated learning (FL) system while ensuring low local upload latency. To improve the efficiency of wireless federated learning (WFL), we propose a specific and complete scheduling strategy involving both computational and communication aspects. First, we model the total problem and decouple it into several sub-problems to solve according to the nature of the variables. Then, we propose a Reduced Load algorithm (RL) to solve the task allocation problem and a dynamic bandwidth allocation strategy to solve the bandwidth allocation problem. Simulation results show that the proposed scheduling strategy can achieve higher learning performance with lower training latency and is capable of adaptively adjusting the bandwidth allocation to decrease upload latency.
Author Li, Fengguo
Pang, Guohao
Zhu, Xiaorong
Author_xml – sequence: 1
  givenname: Guohao
  orcidid: 0009-0002-0329-3753
  surname: Pang
  fullname: Pang, Guohao
  email: 1363300749@qq.com
  organization: College of Portland Nanjing University of Posts and Telecommunications,Nanjing,China
– sequence: 2
  givenname: Fengguo
  surname: Li
  fullname: Li, Fengguo
  email: lifengguo@sd.chinamobile.com
  organization: China Mobile Company,Shandong,China
– sequence: 3
  givenname: Xiaorong
  surname: Zhu
  fullname: Zhu, Xiaorong
  email: xrzhu@njupt.edu.cn
  organization: College of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications,Nanjing,China
BookMark eNo1kMFOwzAQRA0CiVL6B0j4B1Jsb7aJjyhqS6WiHijiWDn2mhqlTpSYQ_l6KgqnGY3ezGFu2VVsIzH2IMVUSqEfV1W1RQ04myqhYCpFLjVifsEmutAloACFGvUlGyksZllRqvKGTYbhUwgBstRa6BFLc--DDRTtkW-6FA7h26TQRv5Cad863nr-HnpqaBj4ghz1JpHjazJ9DPGDV20cwik9-0P3lX7bpuGV6UwdmpCO3ETHq72JkRr-egLojl170ww0-dMxe1vMt9Vztt4sV9XTOgtS6pShRSwBEKgunLFC-cLUFoA0Kg8WCHWtagmly513xrnc27wu0dhCOKscjNn9eTcQ0a7rw8H0x93_UfADKu1iRQ
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICCT59356.2023.10419554
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore Digital Library
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350325959
EISSN 2576-7828
EndPage 793
ExternalDocumentID 10419554
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of China
  grantid: 92067101
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i119t-5c5583353eb7dac02f7abc33e952f3c3e59b2b138d4dfdadd4fc4b85ac70dc2d3
IEDL.DBID RIE
IngestDate Wed Aug 27 02:09:31 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-5c5583353eb7dac02f7abc33e952f3c3e59b2b138d4dfdadd4fc4b85ac70dc2d3
ORCID 0009-0002-0329-3753
PageCount 6
ParticipantIDs ieee_primary_10419554
PublicationCentury 2000
PublicationDate 2023-Oct.-20
PublicationDateYYYYMMDD 2023-10-20
PublicationDate_xml – month: 10
  year: 2023
  text: 2023-Oct.-20
  day: 20
PublicationDecade 2020
PublicationTitle Proceedings (International Conference on Communication Technology. Online)
PublicationTitleAbbrev ICCT
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003189909
Score 1.848101
Snippet Due to the explosive growth in the variety of smart mobile terminals in wireless networks, the increasing computing capability of mobile chips, and the...
SourceID ieee
SourceType Publisher
StartPage 788
SubjectTerms Channel allocation
Delays
Federated learning
Load modeling
parallel and distributed algorithms
Processor scheduling
resource allocation
Resource management
Schedules
scheduling policies
Task analysis
wireless communication
Title Efficiency Optimization Method of Wireless Federated Learning Considering Computational Capability and Channel State
URI https://ieeexplore.ieee.org/document/10419554
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZoxQALryLe8sCa0thxbc9RK5CgdCioWxWfz6hSSVFJkfj32G5aYGBgs6xEiuzk7nz5HoRcC1CAhWZBt1UlGQOTKMcxSTkCQmrQxZ7u870cDNR4rIc1WT1yYRAxgs-wHYbxX76dwzK0yvwXnqXa578GaUgpV2StTUPFv5w-suoaw5V29M1dno-E5iIgERhvr-_-5aMS00h_758PsE9a34Q8OtykmgOyheUh2f2hJXhEql4UgwhMSvro48BrTbCkD9Ejms4dDUjXmY9stB8UJHyRaWktr_pC18adq3Fweqi7hDT36TQiaD9pUVoa6AglzmisUlvkqd8b5bdJbamQTNNUV4kAEWlWHI20BXSYk4UBzlEL5jhwFNowk3JlM-usj32Zg8woUYDsWGCWH5NmOS_xhFBt_KHcdaVV1l8CsrAGedeCRaWlryNOSSss4ORtpZoxWa_d2R_z52QnbFPIC6xzQZrVYomXZBs-qun74iru9Rf8L671
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NT8IwFG8UTdSLXxi_7cHrcG1X1p4XCERADmi4kbV9NSY4DA4T_3vbMlAPHrw1zZYs7fbe69vvA6FbroWGXFKv2yqihGoVCcsgIgw0aKLAhp7uUy8dDMR4LIcVWT1wYQAggM-g4YfhX76Z6YVvlbkvPCHS5b9NtMWThJIlXWvdUnGvp4utskJxkVjedbNsxCXjHotAWWN1_y8nlZBI2vv_fIQDVP-m5OHhOtkcog0ojtDeDzXBY1S2ghyE51LiBxcJXiuKJe4Hl2g8s9hjXacutuG215BwZabBlcDqM15Zdy7H3uuh6hPizCXUgKH9xHlhsCckFDDFoU6to8d2a5R1ospUIXohRJYR1zwQrRio1OQ6pjbNlWYMJKeWaQZcKqoIEyYx1rjol1idKMFzncZGU8NOUK2YFXCKsFTuWG6bqRHGXaLT3ChgTaMNCJm6SuIM1f0CTt6WuhmT1dqd_zF_g3Y6o35v0usO7i_Qrt8ynyVofIlq5XwBV2hbf5Qv7_PrsO9fPu-yPA
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28International+Conference+on+Communication+Technology.+Online%29&rft.atitle=Efficiency+Optimization+Method+of+Wireless+Federated+Learning+Considering+Computational+Capability+and+Channel+State&rft.au=Pang%2C+Guohao&rft.au=Li%2C+Fengguo&rft.au=Zhu%2C+Xiaorong&rft.date=2023-10-20&rft.pub=IEEE&rft.eissn=2576-7828&rft.spage=788&rft.epage=793&rft_id=info:doi/10.1109%2FICCT59356.2023.10419554&rft.externalDocID=10419554