A resource allocation scheme based on Semi-Markov Decision Process for dynamic vehicular clouds

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorFederal Institute of São Paulo (IFSP)-
Autor(es): dc.contributorUniversity of Ottawa-
Autor(es): dc.contributorUniversidade Federal de São Carlos (UFSCar)-
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.creatorMeneguette, Rodolfo I.-
Autor(es): dc.creatorBoukerche, Azzedine-
Autor(es): dc.creatorPimenta, Adinovam H.M.-
Autor(es): dc.creatorMeneguette, Messias [UNESP]-
Data de aceite: dc.date.accessioned2022-08-04T22:06:38Z-
Data de disponibilização: dc.date.available2022-08-04T22:06:38Z-
Data de envio: dc.date.issued2022-04-28-
Data de envio: dc.date.issued2022-04-28-
Data de envio: dc.date.issued2017-07-28-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.1109/ICC.2017.7996710-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/220906-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/220906-
Descrição: dc.descriptionCurrently, the number of resources within a vehicle is growing. The vehicle can provide its idle resources to other vehicles through a cloud. Thus, these vehicles can communicate with each other to dynamically create a vehicular cloud. Therefore, this vehicular cloud needs to adapt according to the number of available resources that the vehicle members in the cloud are sharing. In this kind of cloud, the control of allocated and shared resources becomes a challenge due to the high mobility of vehicles. With this challenge in mind, we propose an optimal resource allocation scheme in order to maximize the use of the available resources. The optimal problem to maximize the expected average reward system is formulated as a Semi-Markov Decision Process (SMDP). The SMDP problem is solved by an iterative algorithm. Numerical results have shown that the proposed scheme has a stable behavior independent of the frequency of requests or the amount of resources. Furthermore, the proposed solution keeps the block rate at 20%, priorizing the allocation that will maximize the utilization of the available resources.-
Descrição: dc.descriptionFederal Institute of São Paulo (IFSP)-
Descrição: dc.descriptionSchool of Electrical Engineering and Computer Science University of Ottawa-
Descrição: dc.descriptionDepartment of Computer Science Federal University of São Carlos-
Descrição: dc.descriptionUniv Estadual Paulista Departamento de Matemática e Computação-
Descrição: dc.descriptionUniv Estadual Paulista Departamento de Matemática e Computação-
Idioma: dc.languageen-
Relação: dc.relationIEEE International Conference on Communications-
???dc.source???: dc.sourceScopus-
Título: dc.titleA resource allocation scheme based on Semi-Markov Decision Process for dynamic vehicular clouds-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.