MDP based optimal policy for collaborative processing using mobile cloud computing

Abstract

Mobile cloud computing is a powerful technology that integrates cloud computing with modern mobile devices. One of the realized benefits of this methodology is that various computation tasks may be temporarily offloaded to mobile devices that belong to users' who are willing to share their resources. In this process, the problem of optimally and fairly allocating compute tasks to various mobile devices must be solved while considering dynamic conditions such as battery life, response delay, and power consumption. This study presents a new solution to this problem using a combination of Markov Decision Processes (MDPs) and lookup tables in order to help guide mobile devices in accepting or rejecting such requests. To achieve a more perfect collaboration between devices requesting aid and those and providing help, an environment is considered in which persuading cooperation will be achieved through reward calculation and credit exchange.