Development and evaluation of optimization algorithms for the fulfillment of cloud service level agreements

Author(s)

Leonildo José de Melo de Azevedo

• Document type: Master's Dissertation
• Press: São Carlos.
• Institution: Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB)
• Defense date: 2018-03-12

Examining board members

Júlio Cezar Estrella; Luiz Fernando Bittencourt; Sarita Mazzini Bruschi; Renato Tinós

• Advisor: Júlio Cezar Estrella; Cláudio Fabiano Motta Toledo

Abstract

Currently the access to a cloud computing environment is provided on demand, which allows providers to offer elasticity services to customers. Although the cloud allows an abstraction of the infrastructure behavior of the service providers (logical and physical), the fulfillment of the Service Level Agreements (SLAs) is challenging, because according with the demand and system configuration, the providers cannot ensure the customers requirements. There is a necessity of mechanisms that consider load balancing algorithms to provide an efficient load distribution in the available resources. However, the papers available in the literature do not efficiently address the problem of resource equation considering the customers requirements, because they consider a limited set of objectives to be analysed and fulfilled. Therefore, this master project aims to develop and evaluate algorithms available in the literature that address the combinatorial optimization and the multi-objective approach to handle the computational resources during the execution time, trying to optimize the efficient use of the resources available in the infrastructure and fulfill the service level agreements defined between the clients and providers. (AU)

• FAPESP's process: 15/11623-4 - Development and evaluation of optimization algorithms for the performance of cloud service level agreements
• Grantee: Leonildo José de Melo de Azevedo
• Support Opportunities: Scholarships in Brazil - Master