An adaptive probabilistic scheduler for offloading time-constrained tasks in local mobile clouds

Mobile Cloud Computing (MCC) enables mobile devices to use resource providers other than mobile devices themselves to host the execution of mobile applications. Recent research shows that it is more suitable for mobile devices to offload complex real-time applications to the cloud formed by nearby mobile devices, referred to as the local mobile cloud, because of low communication latency. In this paper, we propose an adaptive probabilistic scheduler to schedule tasks from multiple source nodes to nearby processing nodes, satisfying the tasks´ time constraints while keeping energy consumption low. The proposed scheduler first estimates the task completion time and energy consumption at each participating processing node. Next, it schedules the current task to the energy efficient processing node in a probabilistic way. The effectiveness of the proposed scheduler is confirmed by simulation results.