Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning

Simple item page
dc.catalogadorjca
dc.contributor.authorSanabria Quispe, Pablo
dc.contributor.authorTapia, Tomás Felipe
dc.contributor.authorToro Icarte, Rodrigo
dc.contributor.authorNeyem, Andres
dc.date.accessioned2024-03-27T13:32:08Z
dc.date.available2024-03-27T13:32:08Z
dc.date.issued2022
dc.description.abstractDue to mobile and IoT devices’ ubiquity and their ever-growing processing potential, Dew computing environments have been emerging topics for researchers. These environments allow resource-constrained devices to contribute computing power to others in a local network. One major challenge in these environments is task scheduling: that is, how to distribute jobs across devices available in the network. In this paper, we propose to distribute jobs in Dew environments using artificial intelligence (AI). Specifically, we show that an AI agent, known as Proximal Policy Optimization (PPO), can learn to distribute jobs in a simulated Dew environment better than existing methods—even when tested over job sequences that are five times longer than the sequences used during the training. We found that using our technique, we can gain up to 77% in performance compared with using human-designed heuristics.
dc.fechaingreso.objetodigital2024-11-14
dc.fuente.origenORCID
dc.identifier.doi10.3390/app12147137
dc.identifier.urihttps://doi.org/10.3390/app12147137
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/84802
dc.information.autorucActividades Universitarias-Dri; Sanabria Quispe, Pablo; 0000-0001-6493-3895; 212656
dc.issue.numero14
dc.language.isoen
dc.nota.accesocontenido completo
dc.revistaApplied Sciences
dc.rightsacceso abierto
dc.subjectDew computing
dc.subjectReinforcement learning
dc.subjectScheduling algorithms
dc.subject.ddc000
dc.subject.deweyCiencias de la computaciónes_ES
dc.subject.ods09 Industry, innovation and infrastructure
dc.subject.odspa09 Industria, innovación e infraestructura
dc.titleSolving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning
dc.typeartículo
dc.volumen12
sipa.codpersvinculados212656
sipa.trazabilidadORCID;2024-03-25
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Solving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning.pdf
Size:
961.51 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Artículos de revistas