| dc.description.abstract | 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. | |
