Deep Learning Predictive Band Switching in Wireless Networks

In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission,...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on wireless communications 2021-01, Vol.20 (1), p.96-109
Hauptverfasser: Mismar, Faris B., Alammouri, Ahmad, Alkhateeb, Ahmed, Andrews, Jeffrey G., Evans, Brian L.
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 109
container_issue 1
container_start_page 96
container_title IEEE transactions on wireless communications
container_volume 20
creator Mismar, Faris B.
Alammouri, Ahmad
Alkhateeb, Ahmed
Andrews, Jeffrey G.
Evans, Brian L.
description In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the data rate. We propose an online-learning based band switching approach that does not require any measurement gap. Our proposed classifier-based band switching policy instead exploits spatial and spectral correlation between radio frequency signals in different bands based on knowledge of the UE location. We focus on switching between a lower (e.g., 3.5 GHz) band and a millimeter wave band (e.g., 28 GHz), and design and evaluate two classification models that are trained on a ray-tracing dataset. A key insight is that measurement gaps are overkill, in that only the relative order of the bands is necessary for band selection, rather than a full channel estimate. Our proposed machine learning-based policies achieve roughly 30% improvement in mean effective rates over those of the industry standard policy, while achieving misclassification errors well below 0.5% and maintaining resilience against blockage uncertainty.
doi_str_mv 10.1109/TWC.2020.3023397
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_9199558</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9199558</ieee_id><sourcerecordid>2478148097</sourcerecordid><originalsourceid>FETCH-LOGICAL-c291t-291d998ac4a91fdc21bf36a2ec07089d49c22dea07174e7b88cd21479ad985c53</originalsourceid><addsrcrecordid>eNo9kE1LAzEQhoMoWKt3wcuC562ZJLtJwIvWTygqWOkxpMmsptbdmmwt_nt3afEyMzDPOwMPIadARwBUX0xn4xGjjI44ZZxruUcGUBQqZ0yo_X7mZQ5MlofkKKUFpSDLohiQyxvEVTZBG-tQv2cvEX1wbfjB7NrWPnvdhNZ99JtQZ7MQcYkpZU_Ybpr4mY7JQWWXCU92fUje7m6n44d88nz_OL6a5I5paPOueK2VdcJqqLxjMK94aRk6KqnSXmjHmEdLJUiBcq6U8wyE1NZrVbiCD8n59u4qNt9rTK1ZNOtYdy8NE1KBUFTLjqJbysUmpYiVWcXwZeOvAWp6R6ZzZHpHZueoi5xtIwER_3ENWnfq-B-kxmFW</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2478148097</pqid></control><display><type>article</type><title>Deep Learning Predictive Band Switching in Wireless Networks</title><source>IEEE Electronic Library (IEL)</source><creator>Mismar, Faris B. ; Alammouri, Ahmad ; Alkhateeb, Ahmed ; Andrews, Jeffrey G. ; Evans, Brian L.</creator><creatorcontrib>Mismar, Faris B. ; Alammouri, Ahmad ; Alkhateeb, Ahmed ; Andrews, Jeffrey G. ; Evans, Brian L.</creatorcontrib><description>In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the data rate. We propose an online-learning based band switching approach that does not require any measurement gap. Our proposed classifier-based band switching policy instead exploits spatial and spectral correlation between radio frequency signals in different bands based on knowledge of the UE location. We focus on switching between a lower (e.g., 3.5 GHz) band and a millimeter wave band (e.g., 28 GHz), and design and evaluate two classification models that are trained on a ray-tracing dataset. A key insight is that measurement gaps are overkill, in that only the relative order of the bands is necessary for band selection, rather than a full channel estimate. Our proposed machine learning-based policies achieve roughly 30% improvement in mean effective rates over those of the industry standard policy, while achieving misclassification errors well below 0.5% and maintaining resilience against blockage uncertainty.</description><identifier>ISSN: 1536-1276</identifier><identifier>EISSN: 1558-2248</identifier><identifier>DOI: 10.1109/TWC.2020.3023397</identifier><identifier>CODEN: ITWCAX</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Artificial intelligence ; band switching ; Cellular communication ; Channel estimation ; Coherence ; Correlation ; Data transmission ; Deep learning ; Frequencies ; Frequency measurement ; Industry standards ; Machine learning ; millimeter wave (mmWave) ; Millimeter waves ; out-of-band estimation ; Radio signals ; Ray tracing ; Spectral correlation ; Switches ; Switching ; Training ; wireless communications ; Wireless networks</subject><ispartof>IEEE transactions on wireless communications, 2021-01, Vol.20 (1), p.96-109</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c291t-291d998ac4a91fdc21bf36a2ec07089d49c22dea07174e7b88cd21479ad985c53</citedby><cites>FETCH-LOGICAL-c291t-291d998ac4a91fdc21bf36a2ec07089d49c22dea07174e7b88cd21479ad985c53</cites><orcidid>0000-0002-8850-4718 ; 0000-0002-9529-304X ; 0000-0001-5648-1569 ; 0000-0002-9115-5088 ; 0000-0001-8513-1293</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9199558$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27903,27904,54736</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9199558$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Mismar, Faris B.</creatorcontrib><creatorcontrib>Alammouri, Ahmad</creatorcontrib><creatorcontrib>Alkhateeb, Ahmed</creatorcontrib><creatorcontrib>Andrews, Jeffrey G.</creatorcontrib><creatorcontrib>Evans, Brian L.</creatorcontrib><title>Deep Learning Predictive Band Switching in Wireless Networks</title><title>IEEE transactions on wireless communications</title><addtitle>TWC</addtitle><description>In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the data rate. We propose an online-learning based band switching approach that does not require any measurement gap. Our proposed classifier-based band switching policy instead exploits spatial and spectral correlation between radio frequency signals in different bands based on knowledge of the UE location. We focus on switching between a lower (e.g., 3.5 GHz) band and a millimeter wave band (e.g., 28 GHz), and design and evaluate two classification models that are trained on a ray-tracing dataset. A key insight is that measurement gaps are overkill, in that only the relative order of the bands is necessary for band selection, rather than a full channel estimate. Our proposed machine learning-based policies achieve roughly 30% improvement in mean effective rates over those of the industry standard policy, while achieving misclassification errors well below 0.5% and maintaining resilience against blockage uncertainty.</description><subject>Artificial intelligence</subject><subject>band switching</subject><subject>Cellular communication</subject><subject>Channel estimation</subject><subject>Coherence</subject><subject>Correlation</subject><subject>Data transmission</subject><subject>Deep learning</subject><subject>Frequencies</subject><subject>Frequency measurement</subject><subject>Industry standards</subject><subject>Machine learning</subject><subject>millimeter wave (mmWave)</subject><subject>Millimeter waves</subject><subject>out-of-band estimation</subject><subject>Radio signals</subject><subject>Ray tracing</subject><subject>Spectral correlation</subject><subject>Switches</subject><subject>Switching</subject><subject>Training</subject><subject>wireless communications</subject><subject>Wireless networks</subject><issn>1536-1276</issn><issn>1558-2248</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE1LAzEQhoMoWKt3wcuC562ZJLtJwIvWTygqWOkxpMmsptbdmmwt_nt3afEyMzDPOwMPIadARwBUX0xn4xGjjI44ZZxruUcGUBQqZ0yo_X7mZQ5MlofkKKUFpSDLohiQyxvEVTZBG-tQv2cvEX1wbfjB7NrWPnvdhNZ99JtQZ7MQcYkpZU_Ybpr4mY7JQWWXCU92fUje7m6n44d88nz_OL6a5I5paPOueK2VdcJqqLxjMK94aRk6KqnSXmjHmEdLJUiBcq6U8wyE1NZrVbiCD8n59u4qNt9rTK1ZNOtYdy8NE1KBUFTLjqJbysUmpYiVWcXwZeOvAWp6R6ZzZHpHZueoi5xtIwER_3ENWnfq-B-kxmFW</recordid><startdate>202101</startdate><enddate>202101</enddate><creator>Mismar, Faris B.</creator><creator>Alammouri, Ahmad</creator><creator>Alkhateeb, Ahmed</creator><creator>Andrews, Jeffrey G.</creator><creator>Evans, Brian L.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-8850-4718</orcidid><orcidid>https://orcid.org/0000-0002-9529-304X</orcidid><orcidid>https://orcid.org/0000-0001-5648-1569</orcidid><orcidid>https://orcid.org/0000-0002-9115-5088</orcidid><orcidid>https://orcid.org/0000-0001-8513-1293</orcidid></search><sort><creationdate>202101</creationdate><title>Deep Learning Predictive Band Switching in Wireless Networks</title><author>Mismar, Faris B. ; Alammouri, Ahmad ; Alkhateeb, Ahmed ; Andrews, Jeffrey G. ; Evans, Brian L.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c291t-291d998ac4a91fdc21bf36a2ec07089d49c22dea07174e7b88cd21479ad985c53</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Artificial intelligence</topic><topic>band switching</topic><topic>Cellular communication</topic><topic>Channel estimation</topic><topic>Coherence</topic><topic>Correlation</topic><topic>Data transmission</topic><topic>Deep learning</topic><topic>Frequencies</topic><topic>Frequency measurement</topic><topic>Industry standards</topic><topic>Machine learning</topic><topic>millimeter wave (mmWave)</topic><topic>Millimeter waves</topic><topic>out-of-band estimation</topic><topic>Radio signals</topic><topic>Ray tracing</topic><topic>Spectral correlation</topic><topic>Switches</topic><topic>Switching</topic><topic>Training</topic><topic>wireless communications</topic><topic>Wireless networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Mismar, Faris B.</creatorcontrib><creatorcontrib>Alammouri, Ahmad</creatorcontrib><creatorcontrib>Alkhateeb, Ahmed</creatorcontrib><creatorcontrib>Andrews, Jeffrey G.</creatorcontrib><creatorcontrib>Evans, Brian L.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on wireless communications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Mismar, Faris B.</au><au>Alammouri, Ahmad</au><au>Alkhateeb, Ahmed</au><au>Andrews, Jeffrey G.</au><au>Evans, Brian L.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Deep Learning Predictive Band Switching in Wireless Networks</atitle><jtitle>IEEE transactions on wireless communications</jtitle><stitle>TWC</stitle><date>2021-01</date><risdate>2021</risdate><volume>20</volume><issue>1</issue><spage>96</spage><epage>109</epage><pages>96-109</pages><issn>1536-1276</issn><eissn>1558-2248</eissn><coden>ITWCAX</coden><abstract>In cellular systems, the user equipment (UE) can request a change in the frequency band when its rate drops below a threshold on the current band. The UE is then instructed by the base station (BS) to measure the quality of candidate bands, which requires a measurement gap in the data transmission, thus lowering the data rate. We propose an online-learning based band switching approach that does not require any measurement gap. Our proposed classifier-based band switching policy instead exploits spatial and spectral correlation between radio frequency signals in different bands based on knowledge of the UE location. We focus on switching between a lower (e.g., 3.5 GHz) band and a millimeter wave band (e.g., 28 GHz), and design and evaluate two classification models that are trained on a ray-tracing dataset. A key insight is that measurement gaps are overkill, in that only the relative order of the bands is necessary for band selection, rather than a full channel estimate. Our proposed machine learning-based policies achieve roughly 30% improvement in mean effective rates over those of the industry standard policy, while achieving misclassification errors well below 0.5% and maintaining resilience against blockage uncertainty.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TWC.2020.3023397</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0002-8850-4718</orcidid><orcidid>https://orcid.org/0000-0002-9529-304X</orcidid><orcidid>https://orcid.org/0000-0001-5648-1569</orcidid><orcidid>https://orcid.org/0000-0002-9115-5088</orcidid><orcidid>https://orcid.org/0000-0001-8513-1293</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1536-1276
ispartof IEEE transactions on wireless communications, 2021-01, Vol.20 (1), p.96-109
issn 1536-1276
1558-2248
language eng
recordid cdi_ieee_primary_9199558
source IEEE Electronic Library (IEL)
subjects Artificial intelligence
band switching
Cellular communication
Channel estimation
Coherence
Correlation
Data transmission
Deep learning
Frequencies
Frequency measurement
Industry standards
Machine learning
millimeter wave (mmWave)
Millimeter waves
out-of-band estimation
Radio signals
Ray tracing
Spectral correlation
Switches
Switching
Training
wireless communications
Wireless networks
title Deep Learning Predictive Band Switching in Wireless Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-27T10%3A59%3A05IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Deep%20Learning%20Predictive%20Band%20Switching%20in%20Wireless%20Networks&rft.jtitle=IEEE%20transactions%20on%20wireless%20communications&rft.au=Mismar,%20Faris%20B.&rft.date=2021-01&rft.volume=20&rft.issue=1&rft.spage=96&rft.epage=109&rft.pages=96-109&rft.issn=1536-1276&rft.eissn=1558-2248&rft.coden=ITWCAX&rft_id=info:doi/10.1109/TWC.2020.3023397&rft_dat=%3Cproquest_RIE%3E2478148097%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2478148097&rft_id=info:pmid/&rft_ieee_id=9199558&rfr_iscdi=true