Self-Aware Data Processing for Power Saving in Resource-Constrained IoT Cyber-Physical Systems

Abstract

Given the emergence of the Internet of Things (IoT) Cyber-Physical Systems (CPSs) and their omnipresence, reducing their power consumption is among the major design priorities. To reduce the power consumption of such systems, we propose the use of a signal-dependent sampling method in a bottom-up fashion, which can lead to up to a 94% reduction in the overall system power with negligible or no loss in performance. Moreover, the proposed technique provides further flexibility for self-aware CPSs to dynamically adjust the number of data samples that are needed for processing (and consequently reduce the power consumption) based on the application at hand and the desired trade-off between accuracy and power consumption. To show the merits of the proposed approach, we also present case studies in the context of an Electrocardiography (ECG) monitoring system as well as a greenhouse (temperature and relative humidity) monitoring system. We also discuss the trade-offs among the system configuration parameters, power consumption, and performance (accuracy). We show that the proposed method has a negligible overhead, which facilitates the real-time operation of the IoT CPS while achieving significant power savings (up to 94%). Even though we study the effects of using this method for two representative applications, the technique is general and can offer similar improvements for a wide range of CPSs and resource-constrained IoT systems.