Poster Abstract: Mobile Application Partitioning for Improving Energy Efficient

For resource-constraint devices, it is possible to save energy of mobile devices by offloading its computation to a remote server. Traditionally, the application partitioning is the key element of computation offloading. However, making a good partitioning needs to tradeoff the communication cost and computational cost. To address this problem, we propose Energy-Aware Dynamic Application Partitioning (EDAP). It first constructs the Weight Object Relation Graph (WORG) for a given java application program by using the static analysis and dynamic profiling techniques. Then, we transform the WORG into Energy Graph (EG) to minimize the energy consumption. By using the network flow theory, the optimization problem of energy consumption is transformed into the optimal bipartition problem of a flow network which can be partitioned by the max-flow min-cut algorithm.