Online Learning to Cache and Recommend in the Next Generation Cellular Networks

An efficient caching can be achieved by predicting the popularity of the files accurately. It is well known that the popularity of a file can be nudged by using recommendation, and hence it can be estimated accurately leading to an efficient caching strategy. Motivated by this, in this paper, we con...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Krishnendu, S, Bharath, B. N, Bhatia, Vimal
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Krishnendu, S
Bharath, B. N
Bhatia, Vimal
description An efficient caching can be achieved by predicting the popularity of the files accurately. It is well known that the popularity of a file can be nudged by using recommendation, and hence it can be estimated accurately leading to an efficient caching strategy. Motivated by this, in this paper, we consider the problem of joint caching and recommendation in a 5G and beyond heterogeneous network. We model the influence of recommendation on demands by a Probability Transition Matrix (PTM). The proposed framework consists of estimating the PTM and use them to jointly recommend and cache the files. In particular, this paper considers two estimation methods namely a) Bayesian estimation and b) a genie aided Point estimation. An approximate high probability bound on the regret of both the estimation methods are provided. Using this result, we show that the approximate regret achieved by the genie aided Point estimation approach is $\mathcal{O}(T^{2/3} \sqrt{\log T})$ while the Bayesian estimation method achieves a much better scaling of $\mathcal{O}(\sqrt{T})$. These results are extended to a heterogeneous network consisting of M small base stations (sBSs) with a central macro base station. The estimates are available at multiple sBSs, and are combined using appropriate weights. Insights on the choice of these weights are provided by using the derived approximate regret bound in the multiple sBS case. Finally, simulation results confirm the superiority of the proposed algorithms in terms of average cache hit rate, delay and throughput.
doi_str_mv 10.48550/arxiv.2210.07747
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_07747</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_07747</sourcerecordid><originalsourceid>FETCH-LOGICAL-a677-c3e258cf8fb5fb19b3fd0650c63de3a6c22c998e8456a6994498e1ea4dfc1fac3</originalsourceid><addsrcrecordid>eNotj8tKxDAUhrNxIaMP4Mq8QMc29yyl6CgUCzL7cpqeaDBNJRN1fHvr6Oq_wQ8fIVdNvRVGyvoG8jF8bhlbi1proc9J36cYEtIOIaeQXmhZaAvuFSmkiT6jW-YZVxcSLWv5hMdCd5gwQwlLoi3G-BEhr0P5WvLb4YKceYgHvPzXDdnf3-3bh6rrd4_tbVeB0rpyHJk0zhs_Sj82duR-qpWsneITclCOMWetQSOkAmWtEGtoEMTkXePB8Q25_rs9EQ3vOcyQv4dfsuFExn8AsU5JfQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Online Learning to Cache and Recommend in the Next Generation Cellular Networks</title><source>arXiv.org</source><creator>Krishnendu, S ; Bharath, B. N ; Bhatia, Vimal</creator><creatorcontrib>Krishnendu, S ; Bharath, B. N ; Bhatia, Vimal</creatorcontrib><description>An efficient caching can be achieved by predicting the popularity of the files accurately. It is well known that the popularity of a file can be nudged by using recommendation, and hence it can be estimated accurately leading to an efficient caching strategy. Motivated by this, in this paper, we consider the problem of joint caching and recommendation in a 5G and beyond heterogeneous network. We model the influence of recommendation on demands by a Probability Transition Matrix (PTM). The proposed framework consists of estimating the PTM and use them to jointly recommend and cache the files. In particular, this paper considers two estimation methods namely a) Bayesian estimation and b) a genie aided Point estimation. An approximate high probability bound on the regret of both the estimation methods are provided. Using this result, we show that the approximate regret achieved by the genie aided Point estimation approach is $\mathcal{O}(T^{2/3} \sqrt{\log T})$ while the Bayesian estimation method achieves a much better scaling of $\mathcal{O}(\sqrt{T})$. These results are extended to a heterogeneous network consisting of M small base stations (sBSs) with a central macro base station. The estimates are available at multiple sBSs, and are combined using appropriate weights. Insights on the choice of these weights are provided by using the derived approximate regret bound in the multiple sBS case. Finally, simulation results confirm the superiority of the proposed algorithms in terms of average cache hit rate, delay and throughput.</description><identifier>DOI: 10.48550/arxiv.2210.07747</identifier><language>eng</language><subject>Computer Science - Information Theory ; Mathematics - Information Theory</subject><creationdate>2022-10</creationdate><rights>http://creativecommons.org/licenses/by-nc-sa/4.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,780,885</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.07747$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.07747$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Krishnendu, S</creatorcontrib><creatorcontrib>Bharath, B. N</creatorcontrib><creatorcontrib>Bhatia, Vimal</creatorcontrib><title>Online Learning to Cache and Recommend in the Next Generation Cellular Networks</title><description>An efficient caching can be achieved by predicting the popularity of the files accurately. It is well known that the popularity of a file can be nudged by using recommendation, and hence it can be estimated accurately leading to an efficient caching strategy. Motivated by this, in this paper, we consider the problem of joint caching and recommendation in a 5G and beyond heterogeneous network. We model the influence of recommendation on demands by a Probability Transition Matrix (PTM). The proposed framework consists of estimating the PTM and use them to jointly recommend and cache the files. In particular, this paper considers two estimation methods namely a) Bayesian estimation and b) a genie aided Point estimation. An approximate high probability bound on the regret of both the estimation methods are provided. Using this result, we show that the approximate regret achieved by the genie aided Point estimation approach is $\mathcal{O}(T^{2/3} \sqrt{\log T})$ while the Bayesian estimation method achieves a much better scaling of $\mathcal{O}(\sqrt{T})$. These results are extended to a heterogeneous network consisting of M small base stations (sBSs) with a central macro base station. The estimates are available at multiple sBSs, and are combined using appropriate weights. Insights on the choice of these weights are provided by using the derived approximate regret bound in the multiple sBS case. Finally, simulation results confirm the superiority of the proposed algorithms in terms of average cache hit rate, delay and throughput.</description><subject>Computer Science - Information Theory</subject><subject>Mathematics - Information Theory</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj8tKxDAUhrNxIaMP4Mq8QMc29yyl6CgUCzL7cpqeaDBNJRN1fHvr6Oq_wQ8fIVdNvRVGyvoG8jF8bhlbi1proc9J36cYEtIOIaeQXmhZaAvuFSmkiT6jW-YZVxcSLWv5hMdCd5gwQwlLoi3G-BEhr0P5WvLb4YKceYgHvPzXDdnf3-3bh6rrd4_tbVeB0rpyHJk0zhs_Sj82duR-qpWsneITclCOMWetQSOkAmWtEGtoEMTkXePB8Q25_rs9EQ3vOcyQv4dfsuFExn8AsU5JfQ</recordid><startdate>20221014</startdate><enddate>20221014</enddate><creator>Krishnendu, S</creator><creator>Bharath, B. N</creator><creator>Bhatia, Vimal</creator><scope>AKY</scope><scope>AKZ</scope><scope>GOX</scope></search><sort><creationdate>20221014</creationdate><title>Online Learning to Cache and Recommend in the Next Generation Cellular Networks</title><author>Krishnendu, S ; Bharath, B. N ; Bhatia, Vimal</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a677-c3e258cf8fb5fb19b3fd0650c63de3a6c22c998e8456a6994498e1ea4dfc1fac3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Information Theory</topic><topic>Mathematics - Information Theory</topic><toplevel>online_resources</toplevel><creatorcontrib>Krishnendu, S</creatorcontrib><creatorcontrib>Bharath, B. N</creatorcontrib><creatorcontrib>Bhatia, Vimal</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv Mathematics</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Krishnendu, S</au><au>Bharath, B. N</au><au>Bhatia, Vimal</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Online Learning to Cache and Recommend in the Next Generation Cellular Networks</atitle><date>2022-10-14</date><risdate>2022</risdate><abstract>An efficient caching can be achieved by predicting the popularity of the files accurately. It is well known that the popularity of a file can be nudged by using recommendation, and hence it can be estimated accurately leading to an efficient caching strategy. Motivated by this, in this paper, we consider the problem of joint caching and recommendation in a 5G and beyond heterogeneous network. We model the influence of recommendation on demands by a Probability Transition Matrix (PTM). The proposed framework consists of estimating the PTM and use them to jointly recommend and cache the files. In particular, this paper considers two estimation methods namely a) Bayesian estimation and b) a genie aided Point estimation. An approximate high probability bound on the regret of both the estimation methods are provided. Using this result, we show that the approximate regret achieved by the genie aided Point estimation approach is $\mathcal{O}(T^{2/3} \sqrt{\log T})$ while the Bayesian estimation method achieves a much better scaling of $\mathcal{O}(\sqrt{T})$. These results are extended to a heterogeneous network consisting of M small base stations (sBSs) with a central macro base station. The estimates are available at multiple sBSs, and are combined using appropriate weights. Insights on the choice of these weights are provided by using the derived approximate regret bound in the multiple sBS case. Finally, simulation results confirm the superiority of the proposed algorithms in terms of average cache hit rate, delay and throughput.</abstract><doi>10.48550/arxiv.2210.07747</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.07747
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_07747
source arXiv.org
subjects Computer Science - Information Theory
Mathematics - Information Theory
title Online Learning to Cache and Recommend in the Next Generation Cellular Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-26T04%3A30%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Online%20Learning%20to%20Cache%20and%20Recommend%20in%20the%20Next%20Generation%20Cellular%20Networks&rft.au=Krishnendu,%20S&rft.date=2022-10-14&rft_id=info:doi/10.48550/arxiv.2210.07747&rft_dat=%3Carxiv_GOX%3E2210_07747%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true