UC Irvine

Recent advances in Internet of Things (IoT) technologies have enabled the use of wearables for remote patient monitoring. Wearable sensors capture the patient’s vital signs, and provide alerts or diagnosis based on the collected data. Unfortunately, wearables typically have limited energy and computational capacity, making their use challenging for healthcare applications where monitoring must continue uninterrupted for a long time, without the need to charge or change the battery. Fog computing can alleviate this problem by offloading computationally intensive tasks from the sensor layer to higher layers, thereby not only meeting the sensors’ limited computational capacity but also enabling the use of local closed-loop energy optimization algorithms to increase the battery life. Furthermore, the patient’s contextual information - including health and activity status - can be exploited to guide energy optimization algorithms more effectively. By incorporating the patient’s contextual information, a desired quality of experience can be achieved by creating a dynamic balance between energy-efficiency and measurement accuracy. We present a runtime distributed control-based solution to find the most energy-efficient system state for a given context while keeping the accuracy of the decision-making process over a certain threshold. Our optimization algorithm resides in the fog layer to avoid imposing computational overheads to the sensor layer. Our solution can be extended to reduce the probability of errors in the data collection process to ensure the accuracy of the results. The implementation of our fog-assisted control solution on a remote monitoring system shows a significant improvement in energy efficiency with a bounded loss in accuracy.