The substantial number of wearable devices in the healthcare industry and the continuous growth of the market procreates the demand for computational offloading. Despite major development of wearable devices and offloading techniques, there are several concerns such as latency, battery power, and computation capability that requires significant development. In this paper, we focus on the fact that most smart wearable devices have Bluetooth pairing with smartphones, and Bluetooth communication is significantly energy-efficient compare to 3G/LTE or Wi-Fi. We propose a computation offloading technique that offloads from the smartphone to the cloud server considering the decision model of both wearable devices and smartphones. Mobile cloud computing can elevate the capacity of smartphones considering the battery state and efficient communications with the cloud. In our model, we increase the energy efficiency of smart devices. To accomplish this, a Dhrystone Millions of Instructions per Second (DMIPS)-based workload measurement model along with a computation offloading decision model were created. According to the performance evaluation, offloading from wearable devices to smartphones and offloading once to cloud server can reduce energy consumption significantly.

中文翻译：

---

智能设备能效计算卸载技术

医疗保健行业中大量可穿戴设备和市场的持续增长催生了对计算卸载的需求。尽管可穿戴设备和卸载技术取得了重大进展，但仍有一些问题需要大量开发，例如延迟、电池电量和计算能力。在本文中，我们关注的事实是，大多数智能可穿戴设备都具有与智能手机的蓝牙配对功能，并且与 3G/LTE 或 Wi-Fi 相比，蓝牙通信具有显着的节能效果。考虑到可穿戴设备和智能手机的决策模型，我们提出了一种从智能手机卸载到云服务器的计算卸载技术。考虑到电池状态和与云的高效通信，移动云计算可以提升智能手机的容量。在我们的模型中，我们提高了智能设备的能源效率。为了实现这一目标，创建了基于 Dhrystone 每秒百万条指令 (DMIPS) 的工作负载测量模型以及计算卸载决策模型。根据性能评估，从可穿戴设备卸载到智能手机，再卸载到云服务器可以显着降低能耗。