Learning-augmented Online Minimization of Age of Information and Transmission Costs

We consider a discrete-time system where a resource-constrained source (e.g., a small sensor) transmits its time-sensitive data to a destination over a time-varying wireless channel. Each transmission incurs a fixed transmission cost (e.g., energy cost), and no transmission results in a staleness co...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE Conference on Computer Communications workshops (Online) s. 01 - 08
Hlavní autori: Liu, Zhongdong, Zhang, Keyuan, Li, Bin, Sun, Yin, Hou, Y. Thomas, Ji, Bo
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 20.05.2024
Predmet:
ISSN:2833-0587
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract We consider a discrete-time system where a resource-constrained source (e.g., a small sensor) transmits its time-sensitive data to a destination over a time-varying wireless channel. Each transmission incurs a fixed transmission cost (e.g., energy cost), and no transmission results in a staleness cost represented by the Age-of-Information. The source must balance the tradeoff between transmission and staleness costs. To address this challenge, we develop a robust online algorithm to minimize the sum of transmission and staleness costs, ensuring a worst-case performance guarantee. While online algorithms are robust, they are usually overly conservative and may have a poor average performance in typical scenarios. In contrast, by leveraging historical data and prediction models, machine learning (ML) algorithms perform well in average cases. However, they typically lack worst-case performance guarantees. To achieve the best of both worlds, we design a learning-augmented online algorithm that exhibits two desired properties: (i) consistency: closely approximating the optimal offline algorithm when the ML prediction is accurate and trusted; (ii) robustness: ensuring worst-case performance guarantee even ML predictions are inaccurate. Finally, we perform extensive simulations to show that our online algorithm performs well empirically and that our learning-auamented algorithm achieves both consistency and robustness.
AbstractList We consider a discrete-time system where a resource-constrained source (e.g., a small sensor) transmits its time-sensitive data to a destination over a time-varying wireless channel. Each transmission incurs a fixed transmission cost (e.g., energy cost), and no transmission results in a staleness cost represented by the Age-of-Information. The source must balance the tradeoff between transmission and staleness costs. To address this challenge, we develop a robust online algorithm to minimize the sum of transmission and staleness costs, ensuring a worst-case performance guarantee. While online algorithms are robust, they are usually overly conservative and may have a poor average performance in typical scenarios. In contrast, by leveraging historical data and prediction models, machine learning (ML) algorithms perform well in average cases. However, they typically lack worst-case performance guarantees. To achieve the best of both worlds, we design a learning-augmented online algorithm that exhibits two desired properties: (i) consistency: closely approximating the optimal offline algorithm when the ML prediction is accurate and trusted; (ii) robustness: ensuring worst-case performance guarantee even ML predictions are inaccurate. Finally, we perform extensive simulations to show that our online algorithm performs well empirically and that our learning-auamented algorithm achieves both consistency and robustness.
Author Ji, Bo
Zhang, Keyuan
Li, Bin
Sun, Yin
Liu, Zhongdong
Hou, Y. Thomas
Author_xml – sequence: 1
  givenname: Zhongdong
  surname: Liu
  fullname: Liu, Zhongdong
  email: zhongdong@vt.edu
  organization: Virginia Tech,Department of Computer Science,Blacksburg,VA
– sequence: 2
  givenname: Keyuan
  surname: Zhang
  fullname: Zhang, Keyuan
  email: keyuanz@vt.edu
  organization: Virginia Tech,Department of Computer Science,Blacksburg,VA
– sequence: 3
  givenname: Bin
  surname: Li
  fullname: Li, Bin
  email: binli@psu.edu
  organization: Pennsylvania State University,Department of Electrical Engineering,University Park,PA
– sequence: 4
  givenname: Yin
  surname: Sun
  fullname: Sun, Yin
  email: yzs0078@auburn.edu
  organization: Auburn University,Department of Electrical and Computer Engineering,,Auburn,AL
– sequence: 5
  givenname: Y. Thomas
  surname: Hou
  fullname: Hou, Y. Thomas
  email: thou@vt.edu
  organization: Virginia Tech,Bradley Department of Electrical and Computer Engineering,Blacksburg,VA
– sequence: 6
  givenname: Bo
  surname: Ji
  fullname: Ji, Bo
  email: boji@vt.edu
  organization: Virginia Tech,Department of Computer Science,Blacksburg,VA
BookMark eNo1kLFOwzAURQ0CiVL6BwwZWVLes5PYHquI0oqWILWIsXLi58qocVAcBvh6qArTkc5wdXSv2UXoAjF2hzBFBH2_fJ5XZbV-e9osXjYFKgVTDjybIhQclBJnbKKlViIHobJM5udsxJUQKeRKXrFJjO8AIDiiFHLENisyffBhn5rPfUthIJtU4eADJWsffOu_zeC7kHQume3piGVwXd-erAk22fYmxNbHeBRlF4d4wy6dOUSa_HHMXucP23KRrqrHZTlbpZ5nakjRutrK3ypd2KZWqG0tHABqkA2Rghozso1reGOwzjEvjHGSlCYpqECJYsxuT7ueiHYfvW9N_7X7_0H8AK6sV_o
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/INFOCOMWKSHPS61880.2024.10620883
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE/IET Electronic Library
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9798350384475
EISSN 2833-0587
EndPage 08
ExternalDocumentID 10620883
Genre orig-research
GrantInformation_xml – fundername: NSF
  grantid: CNS-2106427,CNS-2239677
  funderid: 10.13039/100000001
GroupedDBID 6IE
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i248t-1dfbd758796dcb819db3f001907cee80b14edcfc2ca1b5156aaf7e89e73e61713
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001300418400168&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:32:02 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i248t-1dfbd758796dcb819db3f001907cee80b14edcfc2ca1b5156aaf7e89e73e61713
PageCount 8
ParticipantIDs ieee_primary_10620883
PublicationCentury 2000
PublicationDate 2024-May-20
PublicationDateYYYYMMDD 2024-05-20
PublicationDate_xml – month: 05
  year: 2024
  text: 2024-May-20
  day: 20
PublicationDecade 2020
PublicationTitle IEEE Conference on Computer Communications workshops (Online)
PublicationTitleAbbrev INFOCOM WKSHPS
PublicationYear 2024
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211737
Score 1.9071063
Snippet We consider a discrete-time system where a resource-constrained source (e.g., a small sensor) transmits its time-sensitive data to a destination over a...
SourceID ieee
SourceType Publisher
StartPage 01
SubjectTerms Age-of-Information
Approximation algorithms
Costs
learning-augmented algorithm
Machine learning algorithms
Minimization
online algorithm
Prediction algorithms
transmission cost
Wireless communication
Wireless sensor networks
Title Learning-augmented Online Minimization of Age of Information and Transmission Costs
URI https://ieeexplore.ieee.org/document/10620883
WOSCitedRecordID wos001300418400168&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV05T8MwFH6iFUKwcBVxywMDi4sTR3Y8ooqqCPWQCqJb5StVBpKqTfn92G5aYGBgsuXhyfKz_Q77-x7AnRYpodpYrBKpsbvwFFY6iTFhRCduDyiRqlBsgg8G6WQiRjVYPWBhrLXh85lt-254yzelXvlUmTvhLHangjagwTlfg7W2CRXqQhlO-R7c1zyaD8-D7rAz7L-_jHujMfPEYy4ejJP2RsyvgirBnnQP_zmTI2h9I_PQaGtzjmHHFidw8INU8BTGNWXqDMvVLFBuGrQmFEX9vMg_auAlKjP0OLO-qSFJYVQWBgX75fTvE2moUy6rZQveuk-vnR6uSyfgPE7SCkcmU8aFAlwwo5Wz-kbRzLtzhLsZpkRFiTU607GWkXIuDZMy4zYVllPrfJqInkGzKAt7DkgKpiMpuBWSJVw6aZwYGXmMuA-n0gto-fWZztfsGNPN0lz-MX4F-14L_gU-JtfQrBYrewO7-rPKl4vboNMvciai3Q
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JTwIxFH5RNC4XN4y7PXjwUp2lTqdHQyQQYCABIzfSbcgcnDEw-Ptty4B68OCpTQ_Ny-vylvb7HsCdZLEXSqWxIFxic-EJLCQJsBd5kpg9IFgsXLEJmiTxeMwGFVjdYWG01u7zmX6wXfeWrwq5sKkyc8KjwJyKcBO2nggJ_CVca51SCU0wQ0O6A_cVk-ZjO2n2G_3eW2fYGgwjSz1mIsKAPKwm-lVSxVmU5sE_ZTmE-jc2Dw3WVucINnR-DPs_aAVPYFiRpk4xX0wd6aZCS0pR1Mvy7L2CXqIiRc9TbZsKlORGea6Qs2BmB9hUGmoU83Jeh9fmy6jRwlXxBJwFJC6xr1KhTDBAWaSkMHZfiTC1Dp1HjYSxJ3yilUxlILkvjFMTcZ5SHTNNQ228Gj88hVpe5PoMEGeR9DmjmvGIUG5mo57ivkWJ24AqPoe61c_kY8mPMVmp5uKP8VvYbY163Um3nXQuYc-uiH2PD7wrqJWzhb6GbflZZvPZjVvfLxnPpiQ
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=IEEE+Conference+on+Computer+Communications+workshops+%28Online%29&rft.atitle=Learning-augmented+Online+Minimization+of+Age+of+Information+and+Transmission+Costs&rft.au=Liu%2C+Zhongdong&rft.au=Zhang%2C+Keyuan&rft.au=Li%2C+Bin&rft.au=Sun%2C+Yin&rft.date=2024-05-20&rft.pub=IEEE&rft.eissn=2833-0587&rft.spage=01&rft.epage=08&rft_id=info:doi/10.1109%2FINFOCOMWKSHPS61880.2024.10620883&rft.externalDocID=10620883