Stackelberg Game Based Resource Allocation Algorithm for Federated Learning in MEC Systems

Introducing Federated Learning (FL) into the mo- bile edge computing (MEC) system can effectively deal with delay-sensitive tasks and protect end devices (EDs) data privacy. In the process of participating in FL, the EDs will carry out a large number of local iterations and multiple rounds of commun...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 6th World Conference on Computing and Communication Technologies (WCCCT) S. 7 - 12
Hauptverfasser: Tang, Xiongyan, Wang, Yue, Huang, Rong, Chen, Gao, Wang, Liwen
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 06.01.2023
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Introducing Federated Learning (FL) into the mo- bile edge computing (MEC) system can effectively deal with delay-sensitive tasks and protect end devices (EDs) data privacy. In the process of participating in FL, the EDs will carry out a large number of local iterations and multiple rounds of communication with the MEC server to achieve a target model accuracy. These will bring delay and energy cost which may reduce EDs' willingness to participate. In this paper, a resource allocation algorithm considering EDs incentives is proposed. We model the resource allocation of the MEC server and EDs as a two-layer Stackelberg game model and design two-layer utility functions. In EDs layer, we provide rewards to incentive EDs to contribute computing resource to achieve higher local model accuracy and weigh it against energy consumption of ED. In MEC server layer, the tradeoff between global model accuracy and system delay is conducted. We take utilities maximization as the optimization objective, and optimize the number of local iterations and bandwidth of EDs to achieve joint computing and communication resource allocation in the MEC system. Then, according to the solution of the optimization problems, we propose a resource allocation algorithm. Finally, the simulation results show that the proposed algorithm is superior to the benchmark schemes in reducing EDs' energy consumption and system delay, which can achieve the purpose of encouraging EDs to participate.
AbstractList Introducing Federated Learning (FL) into the mo- bile edge computing (MEC) system can effectively deal with delay-sensitive tasks and protect end devices (EDs) data privacy. In the process of participating in FL, the EDs will carry out a large number of local iterations and multiple rounds of communication with the MEC server to achieve a target model accuracy. These will bring delay and energy cost which may reduce EDs' willingness to participate. In this paper, a resource allocation algorithm considering EDs incentives is proposed. We model the resource allocation of the MEC server and EDs as a two-layer Stackelberg game model and design two-layer utility functions. In EDs layer, we provide rewards to incentive EDs to contribute computing resource to achieve higher local model accuracy and weigh it against energy consumption of ED. In MEC server layer, the tradeoff between global model accuracy and system delay is conducted. We take utilities maximization as the optimization objective, and optimize the number of local iterations and bandwidth of EDs to achieve joint computing and communication resource allocation in the MEC system. Then, according to the solution of the optimization problems, we propose a resource allocation algorithm. Finally, the simulation results show that the proposed algorithm is superior to the benchmark schemes in reducing EDs' energy consumption and system delay, which can achieve the purpose of encouraging EDs to participate.
Author Tang, Xiongyan
Wang, Yue
Chen, Gao
Huang, Rong
Wang, Liwen
Author_xml – sequence: 1
  givenname: Xiongyan
  surname: Tang
  fullname: Tang, Xiongyan
  email: tangxy@chinaunicom.cn
  organization: China Unicom Research Institute,Beijing,China
– sequence: 2
  givenname: Yue
  surname: Wang
  fullname: Wang, Yue
  email: ywang2018@bupt.edu.cn
  organization: Beijing University of Posts and Telecommunications,School of Information and Communication Engineering,Beijing,China
– sequence: 3
  givenname: Rong
  surname: Huang
  fullname: Huang, Rong
  email: huangr27@chinaunicom.cn
  organization: China Unicom Research Institute,Beijing,China
– sequence: 4
  givenname: Gao
  surname: Chen
  fullname: Chen, Gao
  email: cheng96@chinaunicom.cn
  organization: China Unicom Research Institute,Beijing,China
– sequence: 5
  givenname: Liwen
  surname: Wang
  fullname: Wang, Liwen
  email: wanglw97@chinaunicom.cn
  organization: China Unicom Research Institute,Beijing,China
BookMark eNo1j81KxDAcxCPoQdd9Aw95ga35aL6Oa9ldhYrgrgheljT5twbbRNJ62Le3og4M8zsMA3OFzmOKgBCmpKCUmNvXqqoOQiohCkYYLyghglHFztDSKE2lFKWkpVSX6G0_WfcBfQO5wzs7AL6zI3j8DGP6yg7wuu-Ts1NIccYu5TC9D7hNGW_BQ7bT3K3B5hhih0PEj5sK70_jBMN4jS5a24-w_MsFetluDtX9qn7aPVTrehUoNdPKaKdpQ_WPlBQtQCkId7qlUmlujNWt14J7ORtI451RjhFOmGm1Lz3hC3TzuxsA4PiZw2Dz6fh_mX8DNR5Qew
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/WCCCT56755.2023.10052172
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Xplore Digital Library
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
EISBN 9781665461467
1665461462
EndPage 12
ExternalDocumentID 10052172
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i119t-98c81b188888765fee4503c8f1678399a8fd853d653de0bdc97c203029f8d4d03
IEDL.DBID RIE
IngestDate Thu Jan 18 11:14:34 EST 2024
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-98c81b188888765fee4503c8f1678399a8fd853d653de0bdc97c203029f8d4d03
PageCount 6
ParticipantIDs ieee_primary_10052172
PublicationCentury 2000
PublicationDate 2023-Jan.-6
PublicationDateYYYYMMDD 2023-01-06
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-Jan.-6
  day: 06
PublicationDecade 2020
PublicationTitle 2023 6th World Conference on Computing and Communication Technologies (WCCCT)
PublicationTitleAbbrev WCCCT
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8405058
Snippet Introducing Federated Learning (FL) into the mo- bile edge computing (MEC) system can effectively deal with delay-sensitive tasks and protect end devices (EDs)...
SourceID ieee
SourceType Publisher
StartPage 7
SubjectTerms Computational modeling
Delays
Energy consumption
Federated learning
Games
incentive mechanism
mobile edge computing
resource allocation
Resource management
Simulation
Title Stackelberg Game Based Resource Allocation Algorithm for Federated Learning in MEC Systems
URI https://ieeexplore.ieee.org/document/10052172
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELWgYmACRBDf8sCa4DRxbI8QtTBA1aFAxVKlvkupRNOqtPx-zm4CYmAgUiQrihTpkst7Pvu9Y-wqVURCjaWPFySGaVw4D8giDiHB1Eo0Bry26vlB9Xp6ODT9WqzutTCI6DefYeSGfi0f5nbtSmWU4U5qquiPu61UthFrNbtzhLl-yfN8IIkBy8g1BY-a2381TvG40d375xP3WfCjwOP9b2w5YFtYHbJXYoaUdN6Vit8VM-S3hEHAmxI8v3l30ORCTcPJnOb9bzNOrJR3nWUEsUrgtZ_qhE8r_tjJee1YHrCnbmeQ34d1b4RwGsdmFRptiXDG2h0qkyViKkVidRkT-hDpKHQJhMSQ0YliDNYo26aEbptSQwoiOWKtal7hMePCghCWmKCg3ExlW1sBJSYFTYQsjMvihAUuMKPFxv5i1MTk9I_rZ2zXhd_XKbJz1lot13jBduznavqxvPQv7Qt6HJi_
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8NAEF2kCnpSseK3e_Caukl2m-xRQ2vFtvRQtXgp6c6kBmwqtfX3O7tNFA8eDASWQAjMZvLeTva9YexKRkRCtaGXFxR60k-tB2TqexCiNAq1BqeteupG_X48GulBKVZ3WhhEdJvPsGGH7l8-zM3Klsoow63UNKIv7qaSMhBruVa1P0fo6-ckSYaKOLBq2LbgjeqGX61THHK0d__5zD1W_9Hg8cE3uuyzDSwO2AtxQ0o750vF79IZ8ltCIeBVEZ7fvFlwssGm4XROK__XGSdeytvWNIJ4JfDSUXXK84L3WgkvPcvr7LHdGiYdr-yO4OW-r5eejg1RTj-2R9RUGaJUIjRx5hP-EO1I4wwIi6FJJ4oJGB2ZgFI60FkMEkR4yGrFvMAjxoUBIQxxQUHZKVUQGwEZhikthQxMsvSY1W1gxu9rA4xxFZOTP65fsu3OsNcdd-_7D6dsx06Fq1o0z1htuVjhOdsyn8v8Y3HhJvALnD2cBg
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=2023+6th+World+Conference+on+Computing+and+Communication+Technologies+%28WCCCT%29&rft.atitle=Stackelberg+Game+Based+Resource+Allocation+Algorithm+for+Federated+Learning+in+MEC+Systems&rft.au=Tang%2C+Xiongyan&rft.au=Wang%2C+Yue&rft.au=Huang%2C+Rong&rft.au=Chen%2C+Gao&rft.date=2023-01-06&rft.pub=IEEE&rft.spage=7&rft.epage=12&rft_id=info:doi/10.1109%2FWCCCT56755.2023.10052172&rft.externalDocID=10052172