Online Learning Models for Content Popularity Prediction in Wireless Edge Caching

Navneet Garg; Mathini Sellathurai; Bharath Bettagere; Vimal Bhatia; Tharmalingam Ratnarajah

doi:10.1109/IEEECONF44664.2019.9048682

Online Learning Models for Content Popularity Prediction in Wireless Edge Caching

Navneet Garg, Mathini Sellathurai, Bharath Bettagere, Vimal Bhatia, Tharmalingam Ratnarajah

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In the geographical edge caching, where base stations (BSs) and users are distributed as Poisson point process (PPP) and the caching performance is measured using average success probability (ASP), we consider the content popularity (CP) prediction problem to maximize the ASP. Two online learning (OL) models are proposed based on weighted-follow-the-leader (FTL) and weighted-follow-the-regularized-leader (FoReL). Regret analysis concludes that OL methods results in sub-linear MSE regret and linear ASP regret. With MovieLens dataset, simulations verify that the FTL yields better MSE regret while FoReL has lower ASP regret.

Original language	English
Title of host publication	53rd Asilomar Conference on Signals, Systems, and Computers 2019
Publisher	IEEE
Pages	337-341
Number of pages	5
ISBN (Electronic)	9781728143002
DOIs	https://doi.org/10.1109/IEEECONF44664.2019.9048682
Publication status	Published - 30 Mar 2020
Event	53rd Asilomar Conference on Circuits, Systems and Computers 2019 - Pacific Grove, United States Duration: 3 Nov 2019 → 6 Nov 2019

Conference

Conference	53rd Asilomar Conference on Circuits, Systems and Computers 2019
Abbreviated title	ACSSC 2019
Country/Territory	United States
City	Pacific Grove
Period	3/11/19 → 6/11/19

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Access to Document

10.1109/IEEECONF44664.2019.9048682

Cite this

@inproceedings{4e6dd001010544d4b56ba8d9319e75b2,

title = "Online Learning Models for Content Popularity Prediction in Wireless Edge Caching",

abstract = "In the geographical edge caching, where base stations (BSs) and users are distributed as Poisson point process (PPP) and the caching performance is measured using average success probability (ASP), we consider the content popularity (CP) prediction problem to maximize the ASP. Two online learning (OL) models are proposed based on weighted-follow-the-leader (FTL) and weighted-follow-the-regularized-leader (FoReL). Regret analysis concludes that OL methods results in sub-linear MSE regret and linear ASP regret. With MovieLens dataset, simulations verify that the FTL yields better MSE regret while FoReL has lower ASP regret.",

author = "Navneet Garg and Mathini Sellathurai and Bharath Bettagere and Vimal Bhatia and Tharmalingam Ratnarajah",

note = "Funding Information: This work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) under grants EP/P009549/1, EP/P009670/1; UK-India Education and Research Initiative Thematic Partnerships under grants Publisher Copyright: {\textcopyright} 2019 IEEE.; 53rd Asilomar Conference on Circuits, Systems and Computers 2019, ACSSC 2019 ; Conference date: 03-11-2019 Through 06-11-2019",

year = "2020",

month = mar,

day = "30",

doi = "10.1109/IEEECONF44664.2019.9048682",

language = "English",

pages = "337--341",

booktitle = "53rd Asilomar Conference on Signals, Systems, and Computers 2019",

publisher = "IEEE",

address = "United States",

}

Garg, N, Sellathurai, M, Bettagere, B, Bhatia, V & Ratnarajah, T 2020, Online Learning Models for Content Popularity Prediction in Wireless Edge Caching. in 53rd Asilomar Conference on Signals, Systems, and Computers 2019. IEEE, pp. 337-341, 53rd Asilomar Conference on Circuits, Systems and Computers 2019, Pacific Grove, California, United States, 3/11/19. https://doi.org/10.1109/IEEECONF44664.2019.9048682

TY - GEN

T1 - Online Learning Models for Content Popularity Prediction in Wireless Edge Caching

AU - Garg, Navneet

AU - Sellathurai, Mathini

AU - Bettagere, Bharath

AU - Bhatia, Vimal

AU - Ratnarajah, Tharmalingam

N1 - Funding Information: This work was supported by the UK Engineering and Physical Sciences Research Council (EPSRC) under grants EP/P009549/1, EP/P009670/1; UK-India Education and Research Initiative Thematic Partnerships under grants Publisher Copyright: © 2019 IEEE.

PY - 2020/3/30

Y1 - 2020/3/30

N2 - In the geographical edge caching, where base stations (BSs) and users are distributed as Poisson point process (PPP) and the caching performance is measured using average success probability (ASP), we consider the content popularity (CP) prediction problem to maximize the ASP. Two online learning (OL) models are proposed based on weighted-follow-the-leader (FTL) and weighted-follow-the-regularized-leader (FoReL). Regret analysis concludes that OL methods results in sub-linear MSE regret and linear ASP regret. With MovieLens dataset, simulations verify that the FTL yields better MSE regret while FoReL has lower ASP regret.

AB - In the geographical edge caching, where base stations (BSs) and users are distributed as Poisson point process (PPP) and the caching performance is measured using average success probability (ASP), we consider the content popularity (CP) prediction problem to maximize the ASP. Two online learning (OL) models are proposed based on weighted-follow-the-leader (FTL) and weighted-follow-the-regularized-leader (FoReL). Regret analysis concludes that OL methods results in sub-linear MSE regret and linear ASP regret. With MovieLens dataset, simulations verify that the FTL yields better MSE regret while FoReL has lower ASP regret.

UR - http://www.scopus.com/inward/record.url?scp=85083341848&partnerID=8YFLogxK

U2 - 10.1109/IEEECONF44664.2019.9048682

DO - 10.1109/IEEECONF44664.2019.9048682

M3 - Conference contribution

AN - SCOPUS:85083341848

SP - 337

EP - 341

BT - 53rd Asilomar Conference on Signals, Systems, and Computers 2019

PB - IEEE

T2 - 53rd Asilomar Conference on Circuits, Systems and Computers 2019

Y2 - 3 November 2019 through 6 November 2019

ER -

Online Learning Models for Content Popularity Prediction in Wireless Edge Caching

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this