Task Offloading with Execution Cost Minimization in Heterogeneous Mobile Cloud Computing

Mobile cloud computing (MCC) can significantly enhance computation capability and save energy of smart mobile devices (SMDs) by offloading remoteable tasks from resources-constrained SMDs onto the resource-rich cloud. However, it remains a challenge issue how to appropriately partition applications and select the suitable cloud to offload the task under the constraints of execution cost including completion time of the application and energy consumption of SMDs. To address such a challenge, in this paper, we first formulate the partitioning and cloud selection problem into execution cost minimization problem. To solve the optimization problem, we then propose a system framework for adaptive partitioning and dynamic selective offloading. Based on the framework, we design an optimal cloud selection algorithm with execution cost minimization which consists of offloading judgement and cloud selection. Finally, our experimental results in a real testbed demonstrate that our framework can effectively reduce the execution cost compared with other frameworks.