An Efficient Stochastic Gradient Descent Algorithm to Maximize the Coverage of Cellular Networks

Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and tilts of antennas is focused and the existing approaches are mainly gradient-free methods. A standard gradient descent algorithm and its impro...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on wireless communications Vol. 18; no. 7; pp. 3424 - 3436
Main Authors:	Liu, Yaxi, Huangfu, Wei, Zhang, Haijun, Long, Keping
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.07.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Antennas Azimuth Base stations Cellular communication Cellular network Cellular networks computational complexity coverage optimization gradient descent Heuristic methods Linear programming Machine learning algorithms Optimization stochastic gradient descent
ISSN:	1536-1276, 1558-2248
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and tilts of antennas is focused and the existing approaches are mainly gradient-free methods. A standard gradient descent algorithm and its improved version, namely a Stochastic Gradient Descent (SGD) algorithm are proposed on the basis of a novel coverage indicator, named as the soft coverage indicator, to approximate the hard version of the original coverage indicator. We prove that the gradient vector is sparse, which accelerates gradient calculation, due to the number limitation of base stations within a specific distance from a given sampling point even if there are many decision variables of azimuths and tilts. Also, the SGD algorithm only requires a small amount of computation based on cheap estimates of the gradients, and thus is applicable to large-scale networks in an efficient manner. The experiments show that the proposed approaches perform well both in their near-optimal solutions and in their computation efficiency compared with the meta-heuristic algorithms. The extensibility and practicality of the proposed algorithms are also discussed.
AbstractList	Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and tilts of antennas is focused and the existing approaches are mainly gradient-free methods. A standard gradient descent algorithm and its improved version, namely a Stochastic Gradient Descent (SGD) algorithm are proposed on the basis of a novel coverage indicator, named as the soft coverage indicator, to approximate the hard version of the original coverage indicator. We prove that the gradient vector is sparse, which accelerates gradient calculation, due to the number limitation of base stations within a specific distance from a given sampling point even if there are many decision variables of azimuths and tilts. Also, the SGD algorithm only requires a small amount of computation based on cheap estimates of the gradients, and thus is applicable to large-scale networks in an efficient manner. The experiments show that the proposed approaches perform well both in their near-optimal solutions and in their computation efficiency compared with the meta-heuristic algorithms. The extensibility and practicality of the proposed algorithms are also discussed.
Author	Zhang, Haijun Liu, Yaxi Huangfu, Wei Long, Keping
Author_xml	– sequence: 1 givenname: Yaxi orcidid: 0000-0001-5012-8502 surname: Liu fullname: Liu, Yaxi email: yaxi.ustb@gmail.com organization: Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China – sequence: 2 givenname: Wei orcidid: 0000-0003-2887-8395 surname: Huangfu fullname: Huangfu, Wei email: huangfuwei@ustb.edu.cn organization: Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China – sequence: 3 givenname: Haijun orcidid: 0000-0002-0236-6482 surname: Zhang fullname: Zhang, Haijun email: haijunzhang@ieee.org organization: Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China – sequence: 4 givenname: Keping surname: Long fullname: Long, Keping email: longkeping@ustb.edu.cn organization: Beijing Advanced Innovation Center for Materials Genome Engineering, Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services, Institute of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China
BookMark	eNp9kD1PwzAQhi0EEm1hR2KxxJxiO07ijFUoBanAQBFjcMy5dUnjYrt8_XoSWjEwML2n0_vcSU8f7Te2AYROKBlSSvLz2WMxZITmQ5ZTTjjZQz2aJCJijIv9bo7TiLIsPUR975eE0CxNkh56GjV4rLVRBpqA74NVC-mDUXji5PPP7gK86nJUz60zYbHCweIb-WFW5gtwWAAu7Bs4OQdsNS6grje1dPgWwrt1L_4IHWhZezje5QA9XI5nxVU0vZtcF6NppOIkC1GeqUrTOJOUK60pS1JOgAOrFMslBQKEp0ylMReZJFSJikkltI5FRXMlaRoP0Nn27trZ1w34UC7txjXty5KxVkQiYtG1yLalnPXegS7Xzqyk-ywpKTuPZeux7DyWO48tkv5BlAkyGNsEJ039H3i6BQ0A_P4RGRE5z-Nv2DGB1w
CODEN	ITWCAX
CitedBy_id	crossref_primary_10_1016_j_heliyon_2021_e06948 crossref_primary_10_1016_j_jhydrol_2022_128567 crossref_primary_10_1088_1742_6596_1998_1_012008 crossref_primary_10_3390_technologies13030105 crossref_primary_10_1049_cth2_12670 crossref_primary_10_1016_j_bspc_2024_106457 crossref_primary_10_1109_ACCESS_2024_3356049 crossref_primary_10_1016_j_cose_2021_102177 crossref_primary_10_1007_s11432_020_2927_2 crossref_primary_10_3390_s21227540 crossref_primary_10_1109_JSEN_2024_3479733 crossref_primary_10_1109_TWC_2024_3407837 crossref_primary_10_1016_j_jer_2024_04_020 crossref_primary_10_1109_ACCESS_2020_3033325 crossref_primary_10_1109_TCOMM_2023_3296753 crossref_primary_10_1109_TAP_2022_3175214 crossref_primary_10_1007_s11042_023_14634_4 crossref_primary_10_1109_TWC_2024_3454106 crossref_primary_10_1109_TWC_2023_3326209 crossref_primary_10_1109_TVT_2022_3191882 crossref_primary_10_1109_JSYST_2020_2990320 crossref_primary_10_1109_TWC_2020_3021419 crossref_primary_10_1109_TVT_2023_3259435 crossref_primary_10_1109_TNSM_2023_3262401 crossref_primary_10_1109_TMC_2025_3542434 crossref_primary_10_1016_j_sigpro_2020_107803 crossref_primary_10_1109_ACCESS_2021_3066499 crossref_primary_10_32604_cmc_2022_019443 crossref_primary_10_1007_s11042_023_17507_y crossref_primary_10_1109_TNSE_2021_3049262 crossref_primary_10_1109_TVT_2022_3202041 crossref_primary_10_1109_TWC_2025_3551316 crossref_primary_10_1007_s13410_024_01437_y
Cites_doi	10.1137/16M1061308 10.1109/TVT.2011.2163326 10.1155/WCN.2005.816 10.1155/2017/4380676 10.1155/2012/878595 10.1109/MNET.2014.6963804 10.1007/s11276-008-0155-9 10.1002/ett.2957 10.1109/MCOM.2017.1600940 10.1109/MITP.2017.9 10.1109/WOCN.2017.8065843 10.1016/S0893-6080(98)00116-6 10.1016/S1005-8885(15)60683-5 10.1016/j.dam.2004.07.005 10.1109/VETECS.2005.1543252 10.1109/VTCFall.2017.8288237 10.1109/PIMRC.2010.5671622 10.1109/MCOM.2014.6979983 10.1109/TVT.2015.2419079 10.1016/0925-2312(93)90006-O 10.1109/LWC.2014.2327228 10.1016/0009-2614(85)80574-1 10.1109/TVT.2016.2605380 10.1109/VTCFall.2014.6965924 10.1007/s11276-010-0299-2 10.1109/NTICT.2017.7976145 10.1016/j.comcom.2017.09.002 10.1007/s11277-016-3849-9 10.1109/TWC.2017.2786255 10.1109/TVT.2018.2846655 10.1109/MWC.2006.275194
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TWC.2019.2914040
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-2248
EndPage	3436
ExternalDocumentID	10_1109_TWC_2019_2914040 8708949
Genre	orig-research
GrantInformation_xml	– fundername: Joint Foundation of the Ministry of Education (MoE) and China Mobile Group grantid: MCM20160103; MCM20170108 – fundername: Fundamental Research Funds for the Central Universities grantid: RC1631 – fundername: National Natural Science Foundation of China grantid: 61822104; 61370191 funderid: 10.13039/501100001809
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IES IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D RIG
ID	FETCH-LOGICAL-c357t-97cbf137a14cff125640e4e2bc29a1e0e0462c63487a01c8b2ac8ff38b19ca163
IEDL.DBID	RIE
ISICitedReferencesCount	46
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000475339700007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1536-1276
IngestDate	Fri Jul 25 12:18:34 EDT 2025 Sat Nov 29 06:23:47 EST 2025 Tue Nov 18 22:18:28 EST 2025 Wed Aug 27 05:49:37 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c357t-97cbf137a14cff125640e4e2bc29a1e0e0462c63487a01c8b2ac8ff38b19ca163
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0236-6482 0000-0003-2887-8395 0000-0001-5012-8502
PQID	2255858386
PQPubID	105736
PageCount	13
ParticipantIDs	proquest_journals_2255858386 crossref_primary_10_1109_TWC_2019_2914040 ieee_primary_8708949 crossref_citationtrail_10_1109_TWC_2019_2914040
PublicationCentury	2000
PublicationDate	2019-July 2019-7-00 20190701
PublicationDateYYYYMMDD	2019-07-01
PublicationDate_xml	– month: 07 year: 2019 text: 2019-July
PublicationDecade	2010
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on wireless communications
PublicationTitleAbbrev	TWC
PublicationYear	2019
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 kingma (ref34) 2014 ref13 ref37 ref15 sousa (ref12) 2018; 3 ref14 ref31 ref11 tieleman (ref33) 2012; 4 ref32 ref10 ref2 ref1 ref17 ref16 abadi (ref39) 2016 ref19 ref24 ref23 ref26 ref25 ref20 ref22 ref21 (ref30) 2017 ref28 ref27 luketi? (ref18) 2011 ref29 ref8 ref7 ref9 sutskever (ref38) 2013 ge (ref36) 2015 ref4 ref3 ref6 ref5
References_xml	– ident: ref31 doi: 10.1137/16M1061308 – ident: ref10 doi: 10.1109/TVT.2011.2163326 – volume: 3 start-page: 12 year: 2018 ident: ref12 article-title: Self-optimization of low coverage and high interference in real 3G/4G radio access networks publication-title: Inst Eng Lisbon Academic J Electron Telecommun Comput – start-page: 265 year: 2016 ident: ref39 article-title: Tensorflow: A system for large-scale machine learning publication-title: Proc Symp Operating Syst Design Implementation – year: 2017 ident: ref30 publication-title: Further Advancements for E-UTRA Physical Layer Aspects – ident: ref22 doi: 10.1155/WCN.2005.816 – start-page: 1139 year: 2013 ident: ref38 article-title: On the importance of initialization and momentum in deep learning publication-title: Proc Int Conf Mach Learn – ident: ref27 doi: 10.1155/2017/4380676 – ident: ref19 doi: 10.1155/2012/878595 – ident: ref16 doi: 10.1109/MNET.2014.6963804 – start-page: 797 year: 2015 ident: ref36 article-title: Escaping from saddle points-Online stochastic gradient for tensor decomposition publication-title: Proc 28th Conf Learn Theory – ident: ref24 doi: 10.1007/s11276-008-0155-9 – ident: ref29 doi: 10.1002/ett.2957 – ident: ref17 doi: 10.1109/MCOM.2017.1600940 – ident: ref1 doi: 10.1109/MITP.2017.9 – ident: ref5 doi: 10.1109/WOCN.2017.8065843 – start-page: 612 year: 2011 ident: ref18 article-title: Optimization of coverage and capacity of self-organizing network in LTE publication-title: Proc 34th Int Conv MIPRO – ident: ref32 doi: 10.1016/S0893-6080(98)00116-6 – ident: ref11 doi: 10.1016/S1005-8885(15)60683-5 – year: 2014 ident: ref34 publication-title: Adam A method for stochastic optimization – ident: ref6 doi: 10.1016/j.dam.2004.07.005 – ident: ref35 doi: 10.1109/VETECS.2005.1543252 – ident: ref20 doi: 10.1109/VTCFall.2017.8288237 – ident: ref8 doi: 10.1109/PIMRC.2010.5671622 – ident: ref2 doi: 10.1109/MCOM.2014.6979983 – ident: ref14 doi: 10.1109/TVT.2015.2419079 – ident: ref15 doi: 10.1016/0925-2312(93)90006-O – ident: ref13 doi: 10.1109/LWC.2014.2327228 – ident: ref37 doi: 10.1016/0009-2614(85)80574-1 – ident: ref9 doi: 10.1109/TVT.2016.2605380 – volume: 4 start-page: 26 year: 2012 ident: ref33 article-title: RMSprop: Divide the gradient by a running average of its recent magnitude publication-title: Neural Networks and Machine Learning – ident: ref26 doi: 10.1109/VTCFall.2014.6965924 – ident: ref25 doi: 10.1007/s11276-010-0299-2 – ident: ref3 doi: 10.1109/NTICT.2017.7976145 – ident: ref4 doi: 10.1016/j.comcom.2017.09.002 – ident: ref7 doi: 10.1007/s11277-016-3849-9 – ident: ref21 doi: 10.1109/TWC.2017.2786255 – ident: ref28 doi: 10.1109/TVT.2018.2846655 – ident: ref23 doi: 10.1109/MWC.2006.275194
SSID	ssj0017655
Score	2.4845195
Snippet	Network coverage and capacity optimization is an important operational task in cellular networks. The network coverage maximization by adjusting azimuths and...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	3424
SubjectTerms	Algorithms Antennas Azimuth Base stations Cellular communication Cellular network Cellular networks computational complexity coverage optimization gradient descent Heuristic methods Linear programming Machine learning algorithms Optimization stochastic gradient descent
Title	An Efficient Stochastic Gradient Descent Algorithm to Maximize the Coverage of Cellular Networks
URI	https://ieeexplore.ieee.org/document/8708949 https://www.proquest.com/docview/2255858386
Volume	18
WOSCitedRecordID	wos000475339700007&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
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-2248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017655 issn: 1536-1276 databaseCode: RIE dateStart: 20020101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NT9wwEB0B6qE9QClULKXIBy6VGjZ2QmwfV8tHD3SFVKpyC_ZkDCstG7QbUNVfX9sJUasipN5y8ESRxx7PxG_eAzgQ2h7xKhOJsw6T3BIl2hJPiGdFlaKxuY0krudyMlFXV_piBT73vTBEFMFndBge411-VeND-FU29GtL6VyvwqqURdur1d8YyCIqnPoNHHRlZH8lmerh5Y9xwHDpQ6EDmUz61xEUNVX-CcTxdDnd-L_vegvrXRbJRq3bN2GF5u_gzR_cgltwPZqzk8gP4W3Zt6bGWxM4mdnZIqK8GnbcMjmx0eymXkyb2zvW1Oyr-Tm9m_4i5hNDNg74Th9wWO3YmGazAFllkxY4vtyG76cnl-MvSSenkGB2JJtES7SOZ9LwHJ3ziU2Rp5STsCi04ZRS6FPFIvMljEk5KisMKucyZblG4_O297A2r-e0A0whWmFFpQtX5S4LeuW-LOKFMApTJ8UAhk8zXGLHNR4kL2ZlrDlSXXqflMEnZeeTAXzqLe5bno0Xxm4FH_TjuukfwN6TE8tuIy5LH658QaQyVew-b_UBXod3twjcPVhrFg_0EV7hYzNdLvbjGvsNz-nPjQ
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Rb9MwED6NgQQ8jME20bExP_CCRFbbcRP7seo2hugqJIrYW7Av9lapa1CbIbRfj-1kEdMmJN7y4FMin32-i7_7PoB3XJkBK1OeOOMwEcbaRBnLEsvSrKSojTCRxHWcTyby_Fx9WYMPXS-MtTaCz-xheIx3-WWF1-FXWd-vLamEegSPB0Jw2nRrdXcGeRY1Tv0WDsoyeXcpSVV_-n0UUFzqkKtAJ0PvHEJRVeVeKI7ny8mL__uyTdho80gybBz_Etbs4hU8_4tdcAt-DBfkODJEeFvyta7wUgdWZvJxGXFeNTlquJzIcH5RLWf15RWpK3Kmf8-uZjeW-NSQjALC04ccUjkysvN5AK2SSQMdX23Dt5Pj6eg0aQUVEkwHeZ2oHI1jaa6ZQOd8apMJaoXlBrnSzFIbOlUxS30RoylDabhG6VwqDVOofea2A-uLamFfA5GIhhteqsyVwqVBsdwXRizjWiJ1Oe9B_3aGC2zZxoPoxbyIVQdVhfdJEXxStD7pwfvO4mfDtPGPsVvBB924dvp7sHfrxKLdiqvCByxfEslUZrsPWx3A09Pp2bgYf5p8fgPPwnsaPO4erNfLa7sPT_BXPVst38b19gfFQNLU
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%3Ajournal&rft.genre=article&rft.atitle=An+Efficient+Stochastic+Gradient+Descent+Algorithm+to+Maximize+the+Coverage+of+Cellular+Networks&rft.jtitle=IEEE+transactions+on+wireless+communications&rft.au=Liu%2C+Yaxi&rft.au=Huangfu%2C+Wei&rft.au=Zhang%2C+Haijun&rft.au=Long%2C+Keping&rft.date=2019-07-01&rft.pub=IEEE&rft.issn=1536-1276&rft.volume=18&rft.issue=7&rft.spage=3424&rft.epage=3436&rft_id=info:doi/10.1109%2FTWC.2019.2914040&rft.externalDocID=8708949
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1276&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1276&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1276&client=summon