Deadline-credit aware heuristic for dynamic resource provisioning in virtualised cloud environment

摘要

Cloud computing as a paradigm has led to its adoption in large-scale parallel processing and distributed computing. Resource selection places momentous challenges before consumers and service providers. As a remedy brokers stipulates resource provisioning options to match the submitted requests by facilitating a standardised management interface across global boundaries. Keeping in consideration, a DSufferage algorithm is proposed and implemented at platform level which is an improvisation in the existing sufferage heuristic. Deadline parameter has been inculcated to assign precedence levels to the jobs to be submitted to the machines. The novelty of the current research study is that the heuristic is centred towards both user and providers goals. The efficacy of the algorithm has been verified using CloudSim tool and is concluded that it is proficient enough to allocate resources to users tasks with in constraints of deadline, resource utilisation maximisation and SLA violation avoidance.