Predictive Caching via Learning Temporal Distribution of Content Requests

Hoon Geun Song; Seong Ho Chae; Won Yong Shin; Sang Woon Jeon

doi:10.1109/LCOMM.2019.2941202

Predictive Caching via Learning Temporal Distribution of Content Requests

Hoon Geun Song, Seong Ho Chae, Won Yong Shin, Sang Woon Jeon

Department of Computational Science and Engineering

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Abstract

In this letter, dynamic content placement of a local cache server that can store a subset of content objects in its cache memory is studied. Contrary to the conventional model in which content placement is optimized based on the time-invariant popularity distribution of content objects, we consider a general time-varying popularity distribution and such a probabilistic distribution is unknown for content placement. A novel learning method for predicting the temporal distribution of future content requests is presented, which utilizes the request histories of content objects whose lifespans are expired. Then we introduce the so-called predictive caching strategy in which content placement is periodically updated based on the estimated future content requests for each update period. Numerical evaluation is performed using real-world datasets reflecting the inherent nature of temporal dynamics, demonstrating that the proposed predictive caching outperforms the conventional online caching strategies.

Original language	English
Article number	8836639
Pages (from-to)	2335-2339
Number of pages	5
Journal	IEEE Communications Letters
Volume	23
Issue number	12
DOIs	https://doi.org/10.1109/LCOMM.2019.2941202
Publication status	Published - 2019 Dec

Bibliographical note

Funding Information:
Manuscript received June 12, 2019; revised August 5, 2019 and September 1, 2019; accepted September 8, 2019. Date of publication September 13, 2019; date of current version December 10, 2019. This work was supported in part by the Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean Government (18ZF1100, Wireless Transmission Technology in Multi-point to Multi-point Communications) and the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF2017R1D1A1A09000835). The associate editor coordinating the review of this letter and approving it for publication was N.-S. Vo. (Corresponding author: Sang-Woon Jeon.) H.-G. Song is with the Department of Electronic, Electrical, Control and Instrumentation Engineering, Hanyang University, Ansan 15588, South Korea (e-mail: hgsong@hanyang.ac.kr).

Publisher Copyright:
© 1997-2012 IEEE.

All Science Journal Classification (ASJC) codes

Modelling and Simulation
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/LCOMM.2019.2941202

Cite this

@article{9a2f7f642927401fa685f9f6c56413ed,

title = "Predictive Caching via Learning Temporal Distribution of Content Requests",

abstract = "In this letter, dynamic content placement of a local cache server that can store a subset of content objects in its cache memory is studied. Contrary to the conventional model in which content placement is optimized based on the time-invariant popularity distribution of content objects, we consider a general time-varying popularity distribution and such a probabilistic distribution is unknown for content placement. A novel learning method for predicting the temporal distribution of future content requests is presented, which utilizes the request histories of content objects whose lifespans are expired. Then we introduce the so-called predictive caching strategy in which content placement is periodically updated based on the estimated future content requests for each update period. Numerical evaluation is performed using real-world datasets reflecting the inherent nature of temporal dynamics, demonstrating that the proposed predictive caching outperforms the conventional online caching strategies.",

author = "Song, {Hoon Geun} and Chae, {Seong Ho} and Shin, {Won Yong} and Jeon, {Sang Woon}",

note = "Funding Information: Manuscript received June 12, 2019; revised August 5, 2019 and September 1, 2019; accepted September 8, 2019. Date of publication September 13, 2019; date of current version December 10, 2019. This work was supported in part by the Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean Government (18ZF1100, Wireless Transmission Technology in Multi-point to Multi-point Communications) and the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF2017R1D1A1A09000835). The associate editor coordinating the review of this letter and approving it for publication was N.-S. Vo. (Corresponding author: Sang-Woon Jeon.) H.-G. Song is with the Department of Electronic, Electrical, Control and Instrumentation Engineering, Hanyang University, Ansan 15588, South Korea (e-mail: hgsong@hanyang.ac.kr). Publisher Copyright: {\textcopyright} 1997-2012 IEEE.",

year = "2019",

month = dec,

doi = "10.1109/LCOMM.2019.2941202",

language = "English",

volume = "23",

pages = "2335--2339",

journal = "IEEE Communications Letters",

issn = "1089-7798",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - Predictive Caching via Learning Temporal Distribution of Content Requests

AU - Song, Hoon Geun

AU - Chae, Seong Ho

AU - Shin, Won Yong

AU - Jeon, Sang Woon

N1 - Funding Information: Manuscript received June 12, 2019; revised August 5, 2019 and September 1, 2019; accepted September 8, 2019. Date of publication September 13, 2019; date of current version December 10, 2019. This work was supported in part by the Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean Government (18ZF1100, Wireless Transmission Technology in Multi-point to Multi-point Communications) and the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF2017R1D1A1A09000835). The associate editor coordinating the review of this letter and approving it for publication was N.-S. Vo. (Corresponding author: Sang-Woon Jeon.) H.-G. Song is with the Department of Electronic, Electrical, Control and Instrumentation Engineering, Hanyang University, Ansan 15588, South Korea (e-mail: hgsong@hanyang.ac.kr). Publisher Copyright: © 1997-2012 IEEE.

PY - 2019/12

Y1 - 2019/12

N2 - In this letter, dynamic content placement of a local cache server that can store a subset of content objects in its cache memory is studied. Contrary to the conventional model in which content placement is optimized based on the time-invariant popularity distribution of content objects, we consider a general time-varying popularity distribution and such a probabilistic distribution is unknown for content placement. A novel learning method for predicting the temporal distribution of future content requests is presented, which utilizes the request histories of content objects whose lifespans are expired. Then we introduce the so-called predictive caching strategy in which content placement is periodically updated based on the estimated future content requests for each update period. Numerical evaluation is performed using real-world datasets reflecting the inherent nature of temporal dynamics, demonstrating that the proposed predictive caching outperforms the conventional online caching strategies.

AB - In this letter, dynamic content placement of a local cache server that can store a subset of content objects in its cache memory is studied. Contrary to the conventional model in which content placement is optimized based on the time-invariant popularity distribution of content objects, we consider a general time-varying popularity distribution and such a probabilistic distribution is unknown for content placement. A novel learning method for predicting the temporal distribution of future content requests is presented, which utilizes the request histories of content objects whose lifespans are expired. Then we introduce the so-called predictive caching strategy in which content placement is periodically updated based on the estimated future content requests for each update period. Numerical evaluation is performed using real-world datasets reflecting the inherent nature of temporal dynamics, demonstrating that the proposed predictive caching outperforms the conventional online caching strategies.

UR - http://www.scopus.com/inward/record.url?scp=85076679280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076679280&partnerID=8YFLogxK

U2 - 10.1109/LCOMM.2019.2941202

DO - 10.1109/LCOMM.2019.2941202

M3 - Article

AN - SCOPUS:85076679280

SN - 1089-7798

VL - 23

SP - 2335

EP - 2339

JO - IEEE Communications Letters

JF - IEEE Communications Letters

IS - 12

M1 - 8836639

ER -

Predictive Caching via Learning Temporal Distribution of Content Requests

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this