SmartFogLB: balanceamento de carga na computação em névoa

• Ano de defesa: 2020
• Autor(a) principal: Pereira, Éder Paulo
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal de Santa Maria; Brasil; Ciência da Computação; UFSM; Programa de Pós-Graduação em Ciência da Computação; Centro de Tecnologia
• Palavras-chave em Português: Computação em névoa; Internet das coisas; Balanceamento de carga; Fog computing; Internet of things; Load balancing; CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO
• Link de acesso: http://repositorio.ufsm.br/handle/1/22269

FogComputingischaracterizedasanextensionofCloudComputingtotheedgeofthe network.Suchaparadigm,therefore,doesnotexcludetheCloud,butcomplementsit,filling gapssuchaslowerresponsetimeandalsolessuseofinternetlinks.Thisparadigmmeetsthe needs imposedbytheInternetofThingsapplications,whichoftenhaverestrictionsonlow processing times,privacy,priority,bandwidth,amongothers. Considering thegrowinganddiversedemandforInternetofThingsapplications,the nodes thatcomposetheFogComputingtendtobeoverloaded,giventhelargenumberofsmart things requiringcomputationalcapabilities,suchasprocessing,storage,networking,among others. Consequently,overloadedcomputationalnodescompromisetheresponsetimesofIoT applications thathaverestrictionsfortheshortestpossibletime.Inthissense,themainchal- lenge toprovidetheshortestresponsetimeforsuchapplicationsisthedistributionoftasks between thefognodes.However,theavailabilityofcomputationalresourcesinthefogmustbe considered sinceitischaracterizedasadynamicenvironmenttoperformloadbalancinginthis newcomputingparadigm. Toalleviatetheresponsetimeproblem,thisworkpresentsaloadbalancingapproach that aimstoreducetheprocessingtimeofthetasksinthefognodes.Thedistributionoftasks between theNodesoftheFogwascarriedoutthroughdynamicloadbalancinginrealtime, whose contributionisthereforetheloadbalancingalgorithmthattakesintoaccountthedynam- ics andcomputationalheterogeneityoftheenvironment,aswellasthesuddenchangesinthe indexesuseofcomputationalresources,whichassociatestasksmoreappropriately. Toprovetheeffectivenessoftheproposedsolution,asimulationenvironmentwasor- ganized,wherethisworkwascomparedwithsomeloadbalancingapproaches,suchasRound- Robin andalsowithoutabalancer.Theresultsshowthathighprioritytasksconsumetheshort- est possibleresponsetimeintheenvironment,eitherinprocessingorinthequeue,whichbrings out theeffectivenessoftheproposedsolution.Thepriority-basedqueuingmechanismproved to beanimportantcomponentofthesolution,whichanalyzesandreorganizesthetaskqueue based onitspriorities.