An Energy-Efficient and Deadline-Aware Task Offloading Strategy Based on Channel Constraint for Mobile Cloud Workflows

• Main Authors: Yingjie Wang, Lei Wu, Xiusheng Yuan, Xiao Liu, Xuejun Li
• Format: Article
• Language: English
• Published: IEEE 2019-01-01
• Series: IEEE Access
• Subjects: Mobile cloud computing; task offloading; channel constraint; energy consumption
• Online Access: https://ieeexplore.ieee.org/document/8723368/

Energy efficiency is a fundamental problem due to the fact that numerous tasks are running on mobile devices with limited resources. Mobile cloud computing (MCC) technology can offload computation-intensive tasks from mobile devices onto powerful cloud servers, which can significantly reduce the energy consumption of mobile devices and thus enhance their capabilities. In MCC, mobile devices transmit data through the wireless channel. However, since the state of the channel is dynamic, offloading at a low transmission rate will result in the serious waste of time and energy, which further degrades the quality of service (QoS). To address this problem, this paper proposes an energy-efficient and deadline-aware task offloading strategy based on the channel constraint, with the goal of minimizing the energy consumption of mobile devices while satisfying the deadlines constraints of mobile cloud workflows. Specifically, we first formulate a task offloading decision model that combines the channel state with task attributes such as the workload and the size of the data transmission to determine whether the task needs to be offloaded or not. Afterward, we apply it to a new adaptive inertia weight-based particle swarm optimization (NAIWPSO) algorithm to create our channel constraint-based strategy (CC-NAIWPSO), which can obtain a near-optimal offloading plan that can consume less energy while meeting the deadlines. The experimental results show that our proposed task offloading strategy can outperform other strategies with respect to the energy consumption of mobile devices, the execution time of mobile cloud workflows, and the running time of algorithms.