Fine-Grained Task-Dependency Offloading in Mobile Cloud Computing

In mobile cloud computing, mobile devices such as smartphones, can reduce the energy consumption while achieving higher performances through offloading their computational workloads to the remote cloud. This gives rise to a fundamental and critical problem, i.e., how to schedule their workloads under the constraint of task dependency while strictly subject to the latency tolerance. In this paper, we attempt to solve this task scheduling problem in the scenario, where both the time and the energy consumed by computing and communication are sufficiently modeled. Since it is NP-hard to such a problem, we propose a greedy algorithm instead so as to obtain an approximate solution. Extensive simulations show that the performance of our proposed algorithm is approximately optimal.