An optimal control policy in a mobile cloud computing system based on stochastic data

The emerging mobile cloud computing (MCC) paradigm has the potential to extend the capabilities of battery-powered mobile devices. Lots of research work have been conducted for improving the performance and reducing the power consumption for the mobile devices in the MCC paradigm. Different from the previous work, we investigate the effect of the inter-charging interval (ICI) length on the mobile device control decisions, including the offloading decision of each service request and the CPU operating frequency for processing local requests. Generally, the length of an ICI is uncertain to the mobile device controller and only stochastic data are known. We first define the expected “performance sum” as the objective function, which essentially captures a desirable trade-off between performance and power consumption of the mobile device and accounts for the ICI length uncertainty. We prove that the best-suited control decisions should change as time elapses to take into account the effect of ICI length variations. We propose a dynamic programming algorithm, which can derive the optimal control policy of the mobile device to maximize the expected performance sum.