Efficient Last-Mile Link Adaptation in Next-Gen Wireless Heterogeneous Networks

The forthcoming generations of wireless networks have a high demand for reliable and enhanced data rate transmissions which are crucial for emerging smart cities. Thus, there is a need to develop efficient Link Adaptation (LA) for the last hop between end-users and the base stations in order to miti...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International Conference on Communication Systems and Networks (Online) S. 31 - 36
Hauptverfasser: Pati, Preeti Samhita, Sahoo, Shubham Somnath, Singhal, Chetna, Datta, Raja
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 04.01.2022
Schlagworte:
ISSN:2155-2509
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract The forthcoming generations of wireless networks have a high demand for reliable and enhanced data rate transmissions which are crucial for emerging smart cities. Thus, there is a need to develop efficient Link Adaptation (LA) for the last hop between end-users and the base stations in order to mitigate the severe interference resulting from the dense heterogeneous networks. We develop a Machine Learning (ML) based last-mile link adaptation method for a 5G wireless communication network. Dynamic selection of MCS for Resource Block (RB) allocation is efficient in terms of better network throughput and reduced BER which is verified through simulations for 5G New Radio (NR). We assume perfect channel estimation in our analysis. We have used a Deep Neural Network (DNN) model that dynamically selects the appropriate Modulation and Coding Scheme (MCS) ensuring 10 percent Bit Error Rate (BER) and maximizes the system spectral efficiency. Further, we evaluate the Signal to Interference and Noise Ratio (SINR) corresponding to varied channel states for different frequencies of operation and the DNN model selects the Channel Quality Indicator (CQI) corresponding to the optimal MCS available at the corresponding base stations for the end -users. This results in seamless connectivity for mobile users adapting to the last-mile link efficiently and achieving a higher downlink network throughput.
AbstractList The forthcoming generations of wireless networks have a high demand for reliable and enhanced data rate transmissions which are crucial for emerging smart cities. Thus, there is a need to develop efficient Link Adaptation (LA) for the last hop between end-users and the base stations in order to mitigate the severe interference resulting from the dense heterogeneous networks. We develop a Machine Learning (ML) based last-mile link adaptation method for a 5G wireless communication network. Dynamic selection of MCS for Resource Block (RB) allocation is efficient in terms of better network throughput and reduced BER which is verified through simulations for 5G New Radio (NR). We assume perfect channel estimation in our analysis. We have used a Deep Neural Network (DNN) model that dynamically selects the appropriate Modulation and Coding Scheme (MCS) ensuring 10 percent Bit Error Rate (BER) and maximizes the system spectral efficiency. Further, we evaluate the Signal to Interference and Noise Ratio (SINR) corresponding to varied channel states for different frequencies of operation and the DNN model selects the Channel Quality Indicator (CQI) corresponding to the optimal MCS available at the corresponding base stations for the end -users. This results in seamless connectivity for mobile users adapting to the last-mile link efficiently and achieving a higher downlink network throughput.
Author Singhal, Chetna
Sahoo, Shubham Somnath
Pati, Preeti Samhita
Datta, Raja
Author_xml – sequence: 1
  givenname: Preeti Samhita
  surname: Pati
  fullname: Pati, Preeti Samhita
  email: preetispati@iitkgp.ac.in
  organization: Indian Institute of Technology,Dept. of Electronics and Electrical Communication Engineering,Kharagpur,India
– sequence: 2
  givenname: Shubham Somnath
  surname: Sahoo
  fullname: Sahoo, Shubham Somnath
  email: shubhamsomnath@iitkgp.ac.in
  organization: Indian Institute of Technology,Dept. of Electronics and Electrical Communication Engineering,Kharagpur,India
– sequence: 3
  givenname: Chetna
  surname: Singhal
  fullname: Singhal, Chetna
  email: chetna@ece.iitkgp.ac.in
  organization: Indian Institute of Technology,Dept. of Electronics and Electrical Communication Engineering,Kharagpur,India
– sequence: 4
  givenname: Raja
  surname: Datta
  fullname: Datta, Raja
  email: rajadatta@e.iitkgp.ac.in
  organization: Indian Institute of Technology,Dept. of Electronics and Electrical Communication Engineering,Kharagpur,India
BookMark eNotkEFLwzAYhqMoOGd_gZfgvTVfmqTNcZS6Cd162MTjyNqvElfT0UR0_96CO72HFx7e570nN25wSMgTsASA6eeiXm835W4rUwUy4YzzRCuVS5ZekUhnOSglBQcm4JrMOEgZc8n0HYm8_2SMpZBrmfIZqcuus41FF2hlfIjXtkdaWXeki9acggl2cNQ6usHfEC_R0Xc7Yo_e0xUGHIcPdDh8-6kPP8N49A_ktjO9x-iSc_L2Uu6KVVzVy9diUcUWIA-x4C0XTaawbRVroMuVlFojGj0N67I258APWpgGD4Y1UuiGKwbYKjEZSYHpnDz-cy0i7k-j_TLjeX-5IP0DEV5TLg
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/COMSNETS53615.2022.9668503
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 9781665421041
1665421045
EISSN 2155-2509
EndPage 36
ExternalDocumentID 9668503
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
ID FETCH-LOGICAL-i118t-42d24c76edd60c1f865599eea9189f7d8212b94aceba0c549c2601ed6404154e3
IEDL.DBID RIE
IngestDate Wed Aug 27 03:03:04 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i118t-42d24c76edd60c1f865599eea9189f7d8212b94aceba0c549c2601ed6404154e3
PageCount 6
ParticipantIDs ieee_primary_9668503
PublicationCentury 2000
PublicationDate 2022-Jan.-4
PublicationDateYYYYMMDD 2022-01-04
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-Jan.-4
  day: 04
PublicationDecade 2020
PublicationTitle International Conference on Communication Systems and Networks (Online)
PublicationTitleAbbrev COMSNETS
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003189532
Score 2.1753814
Snippet The forthcoming generations of wireless networks have a high demand for reliable and enhanced data rate transmissions which are crucial for emerging smart...
SourceID ieee
SourceType Publisher
StartPage 31
SubjectTerms Adaptation models
Base stations
Bit error rate
Bit Error Rate(BER)
Channel Quality Indicator (CQI)
Deep Neural Network (DNN)
Interference
Link Adaptation (LA)
Modulation and Coding Scheme(MCS)
Network Throughput
Neural networks
Signal to Interference and Noise Ratio (SINR)
Spectral efficiency
Wireless networks
Title Efficient Last-Mile Link Adaptation in Next-Gen Wireless Heterogeneous Networks
URI https://ieeexplore.ieee.org/document/9668503
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Pa8IwFA5Odtgu-6Fjv8lhx0VrmqbJcYjOw6yCDrxJmryCMFqx7f7-JbG4DXbZLTQklJekr9_L-76H0JMMlNICGOFBqAnLeEaEMoKEKszSTIOkXPtiE3GSiNVKzlvo-cCFAQCffAY91_R3-abQtQuV9e2vuYictOdRHPM9V-sQT7F7U0YhbXRFB4HsD2fTRTJaLqLQem2LBCntNRP8qqTiHcn47H-vcI6634w8PD_4mgvUgvwSnf4QE-yg2cirQdjh-E2VFZna844d1MQvRm33N-54k-PEYd1XyLFLfP2wHzo8cSkxhd1JUNSl7feJ4WUXvY9Hy-GENOUSyMaihIowaijTMQdjeKAHmaOcSgmgpDVNFhthvVQqmdKQqkBbXKidnBgYzhxNn0F4hdp5kcM1wgE3wkghjBOviUykUspApcFA2Wmlljeo40yz3u4VMdaNVW7_fnyHTpz1feCC3aN2tavhAR3rz2pT7h79Mn4BMIKewg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3Pa8IwFH7INth22Q8d-70cdly0tmlNjkN0jmkVdOBN0uQVhNGKrfv7l8TiNthlt9DQEF7Svnwv7_sewKPwpFQcGY28QFGWRinlUnMayCBNUoXCj5QrNtGJYz6fi0kNnnZcGER0yWfYtE13l69ztbGhspY5mvPQSnvu28pZFVtrF1Exu1OEgV8pi7Y90eqOR9O4N5uGgfHbBgv6frMa4lctFedK-if_m8QpNL45eWSy8zZnUMPsHI5_yAnWYdxzehDmdTKURUlH5osnFmySZy1X2zt3ssxIbNHuC2bEpr5-mF8dGdikmNzsJcw3hel3qeFFA977vVl3QKuCCXRpcEJJma99pjoRah15qp1a0qkQiFIY06QdzY2fSgSTChPpKYMMlRUUQx0xS9RnGFzAXpZneAnEizTXgnNt5WtCHcrEZygTry3NsEKJK6hb0yxWW02MRWWV678fP8DhYDYaLoav8dsNHNmVcGEMdgt75XqDd3CgPstlsb53S_oFpv6iCw
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%3Abook&rft.genre=proceeding&rft.title=International+Conference+on+Communication+Systems+and+Networks+%28Online%29&rft.atitle=Efficient+Last-Mile+Link+Adaptation+in+Next-Gen+Wireless+Heterogeneous+Networks&rft.au=Pati%2C+Preeti+Samhita&rft.au=Sahoo%2C+Shubham+Somnath&rft.au=Singhal%2C+Chetna&rft.au=Datta%2C+Raja&rft.date=2022-01-04&rft.pub=IEEE&rft.eissn=2155-2509&rft.spage=31&rft.epage=36&rft_id=info:doi/10.1109%2FCOMSNETS53615.2022.9668503&rft.externalDocID=9668503