Performance Tuning of 5G WSN and IOT Using Machine Learning Based Efficient Technique

Abstract

Wireless isensor inetwork (WSN) isystems iare itypically icomposed iof ithousands iof isensors ithat iare ipowered iby ilimited ienergy iresources. iTo iextend ithe inetworks ilongevity, iclustering itechniques ihave ibeen iintroduced ito ienhance ienergy iefficiency. The iExisting iprotocols iare ianalyzed ifrom ia iquality iof iservice i(QoS) iperspective iincluding ithree icommon iobjectives, ithose iare ienergy iefficiency, ireliable icommunication iand ilatency iawareness. iUnderstanding ithe iuser’s irequirements iis icritical iin iintelligent isystems ifor ithe ipurpose iof ienabling ithe iability iof isupporting idiverse iscenarios. iUser iawareness ior iuser-oriented idesign iis ione iremaining ichallenging iproblem iin iclustering. iTherefore, ithe ipotential ichallenges iof iimplementing iclustering ischemes ito iInternet iof iThings i(IoT) isystems iin inetworks. iAs ithe icurrent istudies ifor iWSNs iare iconducted ieither iin ihomogeneous ior ilow-level iheterogeneous inetworks, ithey iare inot iideal ior ieven inot iable ito ifunction iin ihighly idynamic iIoT isystems iwith ia ilarge irange iof iuser iscenarios. iMoreover, iwhen i5G iis ifinally irealized, ithe iproblem iwill ibecome imore icomplex ithan ithat iin itraditional isimplified iWSNs. iBut iwhen iWSN igrows, ithe ivolume iof idata ito ibe igathered iprocessed iand idisseminated iby ithe isensor inodes iincreases ilargely. iProcessing iand itransmitting isuch ia ilarge iamount iof idata iis iimpractical ibecause iof ithe ilimited ienergy iof ithe isensors. iThus, ithere iis ia ineed ifor iapplying iMachine iLearning i(ML) ialgorithms iin iWSNs. iSeveral ichallenges irelated ito iapplying iclustering itechniques ito iIoT ineed ito ibe ianalyzed ialong iwith imachine ilearning itechniques ito ioptimize ithe iperformance iof iWSN. iThis iresearch istudy ifocused ito idesign ian ienergy iefficient itechnique iwhich ican ireduce ithe ienergy iconsumption iand iprolong ithe ilifetime iof inetwork icommunication.

Introduction

The Internet of Things (IoT) is an emerging technology connecting billions of intelligent devices worldwide to exchange data and improve various sectors like healthcare, smart cities, agriculture, and transportation. IoT enables autonomous machine-to-machine communication, reducing the need for human intervention. It relies on sensors, RFID tags, and embedded systems to collect and transmit data over the Internet, creating smarter and more efficient environments.

Wireless Sensor Networks (WSNs) serve as a critical link between physical and virtual worlds in IoT, enabling real-time monitoring and data transfer in applications such as intelligent cities and vehicle networks. IoT and WSN convergence supports secure, efficient communication for dynamic and large-scale systems.

However, there are significant research challenges including:

• Managing diverse IoT devices with varying capabilities and hardware limitations,

• Addressing energy consumption and communication costs in 5G-enabled networks,

• Improving user-centric service quality by tailoring to user profiles and network conditions,

• Handling device mobility and network reliability in dynamic environments.

Artificial Neural Networks (ANNs), inspired by the human brain, are applied in IoT to process complex data patterns for classification and prediction, helping optimize network performance and decision-making.

Energy management remains critical in IoT and WSNs, with machine learning methods used to enhance routing efficiency, reduce delays, and extend network lifetime.

The proposed methodology involves simulating IoT networks with algorithms like PDORP, LEACH, ACO, and GA to optimize routing, trust management, and connectivity among nodes, addressing problems of aggressive nodes and ensuring reliable data transmission.

Conclusion

Low ibattery ilife ion iWSNS iis ia iunique iissue. iIn ithe ipast, ivarious iclustering itechniques ihave ibeen iproposed i ito isolve ithis iproblem, ifocusing ion i idata itransmission ifrom icluster iheads ito i ibase istations. iGrid-based iclustering iin iWSN isolves ienergy ibalance iproblems iby ieliminating ienergy iconsumption iand iincreasing iload iand ienergy iconsumption ibetween iall inodes iin ithe isystem. iGrid iarchitecture ioffers iexcellent ireliability iand iinexpensive icost ifor ilong itransmission itimes. iAfter iconFigureuring ithe inetwork iin iboth iways, iit iwas iobserved ithat iusing ia isingle iCH iwould iimprove ienergy iefficiency ion iall igrills. iAt ithe isame itime, iit ideals iwith iload icompensation, iclustering ioverhead iand ienergy iefficiency. iThroughput, iPDR, iand ilatency iare imeasured ito itest ithe isuccess iof ithe iproposed iclustering-based irouting isystem. iIn ithe iperformance iassessment, ithe iproposed iwork iincreases ithroughput iby i3% ito i4%, iand i idecrease iin icommunication ilatency iby i4% ito i5% icompared ito itwo irouting ialgorithms ibased ion iPDR, iand iclustering. iThis iconclusion iis isupported iby ithe ioptimal iCH iselection iapproach iused iin ithe iroute idiscovery istage iof ithe iproposed iprocedure. iBetter inetwork iperformance, isuch ias ithroughput, iPDR, iand islight ilatency, iindicates ithe ieffectiveness iof ithe iproposed iwork. iIn ithis istudy, iwe iprovided ia imethod ifor iselecting icluster iheads ibased ion inode icosine isimilarity iand iselected ineuronal inetwork-based ireinforcement ilearning istrategies ito ioptimize inetwork i iselection. iAdditionally, iartificial ineural inetworks iwere iused ito imaintain ithe iroute. iThis iresearch ielement iwas ilargely ioverlooked iin iprevious istudies. iThroughput, iPDR, iand inetwork ienergy iconsumption iwere imeasured ito iassess i iperformance. iRL-based iAnn-Technik iwas icompared ito iRL-based iSVM iand iRL-based iNB iapproaches. iThe iresults ishowed ithat ithe iproposed iapproach ioutperformed iSVM iand iNB. iThis iindicates ithat i iroutes iare iin ifact iwell ioptimized iand imaintained iby iexisting itechnology. i

References

[1] Aditya, iV. iM. iV. iS., iDhuli, iS., iSashrika, iP. iL., iShivani, iK. iK., i& iJayanth, iT. i(2020, iSeptember). iCloseness icentrality ibased icluster ihead iselection ialgorithm ifor ilarge iscale iwsns. iIn i2020 i12th iInternational iConference ion iComputational iIntelligence iand iCommunication iNetworks i(CICN) i(pp. i107-111). iIEEE. i [2] Premkumar, iM., i& iSundararajan, iT. iV. iP. i(2020). iDLDM: iDeep ilearning-based idefense imechanism ifor idenial iof iservice iattacks iin iwireless isensor inetworks. iMicroprocessors iand iMicrosystems, i79, i103278. i [3] Kitaw, iB., iBayu, iF., i& iBirhanu, iG. i(2020). iEfficient-path iselection ischeme iusing ioptimized iadhoc ion idemand imultipath irouting iprotocol ifor iadhoc inetworks. iInternational iJournal iof iAdvanced iNetworking iand iApplications, i11(4), i4336-4344. i [4] Sureshkumar, iC., i& iSabena, iS. i(2020). iFuzzy-based isecure iauthentication iand iclustering ialgorithm ifor iimproving ithe ienergy iefficiency iin iwireless isensor inetworks. iWireless iPersonal iCommunications, i112(3), i1517-1536. i [5] Mehmood, iA., iLv, iZ., iLloret, iJ., i& iUmar, iM. iM. i(2017). iELDC: iAn iartificial ineural inetwork ibased ienergy-efficient iand irobust irouting ischeme ifor ipollution imonitoring iin iWSNs. iIEEE iTransactions ion iEmerging iTopics iin iComputing, i8(1), i106-114. i [6] Fattoum, iM., iJellali, iZ., i& iAtallah, iL. iN. i(2020, iJuly). iFuzzy ilogic-based itwo-level iclustering ifor idata iaggregation iin iWSN. iIn i2020 i17th iInternational iMulti-Conference ion iSystems, iSignals i& iDevices i(SSD) i(pp. i360-365). iIEEE. i [7] El iKhediri, iS., iFakhet, iW., iMoulahi, iT., iKhan, iR., iThaljaoui, iA., i& iKachouri, iA. i(2020). iImproved inode ilocalization iusing iK-means iclustering ifor iWireless iSensor iNetworks. iComputer iScience iReview, i37, i100284. i [8] Dao, iT. iK., iNguyen, iT. iT., iPan, iJ. iS., iQiao, iY. iU., i& iLai, iQ. iA. i(2020). iIdentification ifailure idata ifor icluster iheads iaggregation iin iWSN ibased ion iimproving iclassification iof iSVM. iIEEE iAccess, i8, i61070-61084. i [9] Pranathi, iT. iY. iS. iS., iDhuli, iS., iAditya, iV. iM. iV. iS., iCharisma, iB., i& iJayakrishna, iK. i(2020, iSeptember). iA ihybrid irouting iprotocol ifor irobust iwireless isensor inetworks. iIn i2020 i12th iInternational iConference ion iComputational iIntelligence iand iCommunication iNetworks i(CICN) i(pp. i102-106). iIEEE. i [10] El iKhediri, iS., iFakhet, iW., iMoulahi, iT., iKhan, iR., iThaljaoui, iA., i& iKachouri, iA. i(2020). iImproved inode ilocalization iusing iK-means iclustering ifor iWireless iSensor iNetworks. iComputer iScience iReview, i37, i100284. i [11] Shemim, iK. iF., i& iWitkowski, iU. i(2020, iDecember). iEnergy iEfficient iClustering iProtocols ifor iWSN: iPerformance iAnalysis iof iFL-EE-NC iwith iLEACH, iK iMeans-LEACH, iLEACH-FL iand iFL-EE/D iusing iNS-2. iIn i2020 i32nd iInternational iConference ion iMicroelectronics i(ICM) i(pp. i1-5). iIEEE. i [12] Al-Khayyat, iA. iT. iA., i& iIbrahim, iA. i(2020, iOctober). iEnergy ioptimization iin iwsn irouting iby iusing ithe iK-means iclustering ialgorithm iand iant icolony ialgorithm. iIn i2020 i4th iInternational iSymposium ion iMultidisciplinary iStudies iand iInnovative iTechnologies i(ISMSIT) i(pp. i1-4). iIEEE. i [13] Lata, iS., iMehfuz, iS., iUrooj, iS., i& iAlrowais, iF. i(2020). iFuzzy iclustering ialgorithm ifor ienhancing ireliability iand inetwork ilifetime iof iwireless isensor inetworks. iIEEE iAccess, i8, i66013-66024. i [14] Hassan, iA. iA. iH., iShah, iW. iM., iHabeb, iA. iH. iH., iOthman, iM. iF. iI., i& iAl-Mhiqani, iM. iN. i(2020). iAn iimproved ienergy-efficient iclustering iprotocol ito iprolong ithe ilifetime iof ithe iWSN-based iIoT. iIeee iAccess, i8, i200500-200517. i [15] Hassan, iA. iA. iH., iShah, iW. iM., iHabeb, iA. iH. iH., iOthman, iM. iF. iI., i& iAl-Mhiqani, iM. iN. i(2020). iAn iimproved ienergy-efficient iclustering iprotocol ito iprolong ithe ilifetime iof ithe iWSN-based iIoT. iIeee iAccess, i8, i200500-200517. i [16] Baradaran, iA. iA., i& iNavi, iK. i(2020). iHQCA-WSN: iHigh-quality iclustering ialgorithm iand ioptimal icluster ihead iselection iusing ifuzzy ilogic iin iwireless isensor inetworks. iFuzzy iSets iand iSystems, i389, i114-144. i [17] Mishra, iP. iK., i& iVerma, iS. iK. i(2020, iDecember). iOCSSP: iOptimal icluster isize iselection-based iclustering iprotocol iusing ifuzzy ilogic ifor iwireless isensor inetwork. iIn i2020 iIEEE iInternational iConference ion iAdvent iTrends iin iMultidisciplinary iResearch iand iInnovation i(ICATMRI) i(pp. i1-4). iIEEE. i [18] Suriya iPraba, iT., iSethukarasi, iT., i& iVenkatesh, iV. i(2020). iKrill iherd ibased iTSP iapproach ifor imobile isink ipath ioptimization iin ilarge iscale iwireless isensor inetworks. iJournal iof iIntelligent i& iFuzzy iSystems, i38(5), i6571-6581. i [19] Maheshwari, iP., iSharma, iA. iK., i& iVerma, iK. i(2021). iEnergy iefficient icluster ibased irouting iprotocol ifor iWSN iusing ibutterfly ioptimization ialgorithm iand iant icolony ioptimization. iAd iHoc iNetworks, i110, i102317. i [20] Fanian, iF., iRafsanjani, iM. iK., i& iSaeid, iA. iB. i(2021). iFuzzy imulti-hop iclustering iprotocol: iSelection ifuzzy iinput iparameters iand irule ituning ifor iWSNs. iApplied iSoft iComputing, i99, i106923. i [21] Tanwar, iA., iSharma, iA. iK., i& iPandey, iR. iV. iS. i(2020). iFractional-grasshopper ioptimization ialgorithm ifor ithe isensor iactivation icontrol iin iwireless isensor inetworks. iWireless iPersonal iCommunications, i113, i399-422. i [22] Shah, iB., iAbbas, iA., iAli, iG., iIqbal, iF., iKhattak, iA. iM., iAlfandi, iO., i& iKim, iK. iI. i(2020). iGuaranteed ilifetime iprotocol ifor iIoT ibased iwireless isensor inetworks iwith imultiple iconstraints. iAd iHoc iNetworks, i104, i102158. i [23] Chithaluru, iP., iAl-Turjman, iF., iKumar, iM., i& iStephan, iT. i(2020). iI-AREOR: iAn ienergy-balanced iclustering iprotocol ifor iimplementing igreen iIoT iin ismart icities. iSustainable icities iand isociety, i61, i102254. i [24] Mishra, iP. iK., i& iVerma, iS. iK. i(2020, iDecember). iOCSSP: iOptimal icluster isize iselection-based iclustering iprotocol iusing ifuzzy ilogic ifor iwireless isensor inetwork. iIn i2020 iIEEE iInternational iConference ion iAdvent iTrends iin iMultidisciplinary iResearch iand iInnovation i(ICATMRI) i(pp. i1-4). iIEEE. i [25] Bharathi, iR., iAbirami, iT., iDhanasekaran, iS., iGupta, iD., iKhanna, iA., iElhoseny, iM., i& iShankar, iK. i(2020). iEnergy iefficient iclustering iwith idisease idiagnosis imodel ifor iIoT ibased isustainable ihealthcare isystems. iSustainable iComputing: iInformatics iand iSystems, i28, i100453. i [26] Ghosal, iA., iHalder, iS., i& iDas, iS. iK. i(2020). iDistributed ion-demand iclustering ialgorithm ifor ilifetime ioptimization iin iwireless isensor inetworks. iJournal iof iParallel iand iDistributed iComputing, i141, i129-142. i [27] Jabeur, iN., iYasar, iA. iU. iH., iShakshuki, iE., i& iHaddad, iH. i(2020). iToward ia ibio-inspired iadaptive ispatial iclustering iapproach ifor iIoT iapplications. iFuture iGeneration iComputer iSystems, i107, i736-744. i [28] Nivedhitha, iV., iSaminathan, iA. iG., i& iThirumurugan, iP. i(2020). iDMEERP: iA idynamic imulti-hop ienergy iefficient irouting iprotocol ifor iWSN. iMicroprocessors iand iMicrosystems, i79, i103291. i [29] Sood, iT., i& iSharma, iK. i(2022). iLUET: ia inovel ilines-of-uniformity ibased iclustering iprotocol ifor iheterogeneous-WSN ifor imultiple-applications. iJournal iof iKing iSaud iUniversity-Computer iand iInformation iSciences, i34(7), i4177-4190. i [30] Behera, iT. iM., iMohapatra, iS. iK., iSamal, iU. iC., iKhan, iM. iS., iDaneshmand, iM., i& iGandomi, iA. iH. i(2019). iI-SEP: iAn iimproved irouting iprotocol ifor iheterogeneous iWSN ifor iIoT-based ienvironmental imonitoring. iIEEE iInternet iof iThings iJournal, i7(1), i710-717. [31] Panchal, iA., i& iSingh, iR. iK. i(2021). iEHCR-FCM: iEnergy iefficient ihierarchical iclustering iand irouting iusing ifuzzy iC-means ifor iwireless isensor inetworks. iTelecommunication iSystems, i76(2), i251-263. i [32] Roy, iN. iR., i& iChandra, iP. i(2020). iThreshold isensitive iclustering iin iSEP. iSustainable iComputing: iInformatics iand iSystems, i25. [33] Roy, iN. iR., i& iT. iM. iBehera. i(2020). iDelay isensitive iclustering iin iSEP. iSustainable iComputing: iInformatics iand iSystems. [34] Daneshvar, iS. iM. iH., iMohajer, iP. iA. iA., i& iMazinani, iS. iM. i(2019). iEnergy-efficient irouting iin iWSN: iA icentralized icluster-based iapproach ivia igrey iwolf ioptimizer. iIEEE iAccess, i7, i170019-170031. i [35] Behera, iT. iM., iMohapatra, iS. iK., iSamal, iU. iC., iKhan, iM. iS., iDaneshmand, iM., i& iGandomi, iA. iH. i(2019). iResidual ienergy-based icluster-head iselection iin iWSNs ifor iIoT iapplication. iIEEE iInternet iof iThings iJournal, i6(3), i5132-5139. i [36] Lin, iD., i& iWang, iQ. i(2019). iAn ienergy-efficient iclustering ialgorithm icombined igame itheory iand idual-cluster-head imechanism ifor iWSNs. iIEEE iAccess, i7, i49894-49905. i

Copyright

Copyright © 2025 Dr. Gurinder Kaur Sodhi , Aabid Bashir Check. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.