Heuristics aware advance reservation and scheduling (HAARS) mechanism in hybrid (Grid/Cloud) environment

Abstract

Grid Resource Broker allocates the user job/application requests to Grid resources based upon the job/application requirements. In some cases, the broker could not be able to run the user application requests due to the non-availability of application execution environment and the required amount of nodes in the single Grid resource. To handle this situation resource broker should have the mechanism to coordinate and allocate the multiple Grid resources called co-allocation. However, the main challenge in the co-allocation mechanism is there is no guarantee in the availability of resources during the application execution that leads to the non-assimilability of the user required Quality of Service (QoS) parameters. In this research work, we have employed the Bipartite-based Heuristics Aware Advanced Reservation and Scheduling (HAARS) mechanism that select and reserve the resources from Grid/Cloud environment in an advance and near optimal manner. The proposed mechanism made use of the open-source software's such as PluS and Haizea for performing advance reservation in the Grid and Cloud environment. The proposed approach guarantees the availability of resources during the application execution, and also it achieves the user required Quality of Service (QoS) requirements.