REAP: Runtime Energy-Accuracy Optimization for Energy Harvesting IoT Devices
For energy harvesting IoT devices, this work provides a practical runtime optimization to simultaneously improve accuracy and active time under tight energy constraints.
This paper tackles runtime energy-accuracy optimization for energy harvesting IoT devices used in health monitoring and activity recognition. The proposed technique achieves 46% higher expected accuracy and 66% longer active time compared to the highest performance design point.
The use of wearable and mobile devices for health monitoring and activity recognition applications is increasing rapidly. These devices need to maximize their accuracy and active time under a tight energy budget imposed by battery and small form-factor constraints. This paper considers energy harvesting devices that run on a limited energy budget to recognize user activities over a given period. We propose a technique to co-optimize the accuracy and active time by utilizing multiple design points with different energy-accuracy trade-offs. The proposed technique switches between these design points at runtime to maximize a generalized objective function under tight harvested energy budget constraints. We evaluate the proposed approach experimentally using a custom hardware prototype and fourteen user studies. The proposed approach achieves both 46% higher expected accuracy and 66% longer active time compared to the highest performance design point.