An Enhancement of a Scheduling Approach for an Opportunistic Environment

Opportunistic grid computing is an interesting paradigm when it is necessary to obtain high performance computing with low cost investment. On the other hand, advance reservation is very useful when QoS and efficient scheduling are desired in a multi-scheduling environment. However, it is not conventional to use advance reservation with opportunistic grid computing due to instability of the environment. In this article, we propose a new advanced reservation approach which offers to a user the possibility to select resources in advance for a future utilization in opportunistic grid computing. Therefore, the main goal of this proposal is to offer a best effort feature to a user since these types of environments, it is not possible to provide QoS, because there is no guarantees of resources availability. In addition, we propose the insertion of a mechanism which searches for free time interval and allocates rejected reservations at period of time available closest to the requested. Preliminary results shows the success of the proposal through a case study.