Advanced adaptive probabilities and energy aware algorithm for scheduling tasks in MCC

Today, Mobile Cloud Computing has been widely used and can send complex computations to the stronger server with more resources and get results from them to overcome the limitations of existing mobile devices, such as battery level, the amount of CPU and memory. Local mobile clouds, which consist of the mobile devices, are used as a suitable solution to support real-time applications, especially?. Due to share bandwidth and computing resources across all mobile devices, a task scheduling is required to ensure that multiple mobile devices can effectively assign works to local mobile clouds in such way that the time limitation is considered and the amount of remaining energy is estimated for reducing energy consumption. In this paper, we suggest energy-aware and adaptive task scheduler. The task scheduler discovers resources based on controlling messages periodically. This method, with an estimation of task completion time, calculates energy consumption and the amount of remaining energy in each processing node. Then, it schedules current work with a possible adaptive method at the processing node and sets time limitation in order to improve network efficiency under unpredictable conditions. The results of tests carried out on the proposed method compared to existing methods show that the proposed method has the lowest energy consumption per successful task. Moreover, the proposed method has scalability and high flexibility and can be deployed on any network.