Scheduling Manager for Mobile Cloud Using Multi-Agents

Mobile Cloud Computing (MCC) is emerging as one of the most important branches of cloud computing. In MCC, a group of mobile devices connected via WLAN and cooperating to execute the user’s jobs and acting as a computing resource provider. However, unlike could computing (which use a powerful servers to execute the jobs) , mobile devices are not reliable to execute extensive jobs in the MCC due to its limitation of battery and connectivity. To overcome this limitation and keep the execution of the job up and running even if the mobile device leave the cloud, we need to reschedule the job and continue the execution on another available mobile device in the MCC. Firstly, the impact of job and node characteristic on the performance of the MCC will be discussed. Secondly, we introduce a new scheduling techniques used by the scheduling manager component in the MCC. At last, evaluate and compares our approach with similar approaches. All of these may contribute to make the MCC more efficient, reliable and feasible to be used as a powerful cloud platform to execute the user’s extensive jobs.