@inproceedings{CAD4X-C-2013,

author = {Xue Lin and Yanzhi Wang and Siyu Yue and Naehyuck Chang and Massoud Pedram},

title = {A Framework of Concurrent Task Scheduling and Dynamic Voltage and Frequency Scaling in Real-Time Embedded Systems with Energy Harvesting},

booktitle = {Proceedings of Proceedings of IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED)},

year = {2013},

pages  = {70-75},

location = {Beijing, China},

month = {September},

note = {},

abstract = {Energy harvesting is a promising method to overcome energy limitation in traditional battery-powered embedded systems. In this paper, we investigate the question of efficient global control of a real-time embedded system with energy harvesting (RTES-EH) in order to achieve full energy autonomy (i.e., perpetual, battery-free operation.) More precisely, the energy harvesting module comprises a PV panel for energy harvesting and a supercapacitor for energy storage. The global controller performs optimal operating point tracking for the PV panel, state-of-charge management for the supercapacitor, and energy-harvesting-aware real-time task scheduling with dynamic voltage and frequency scaling (DVFS) in the embedded load device (e.g., a sensor node.) To perform robust optimization of the system performance and availability, the proposed global controller accounts for the dynamic V-I characteristics of the PV panel, terminal voltage variation and self-leakage of the supercapacitor as a function of its state-of-charge, as well as power losses in the converters. The global controller employs a cascaded feedback control structure wherein an inner control loop determines the V-I operating point of the PV panel (and hence the input current of the supercapacitor), and an outer supervisory control loop performs real-time task scheduling and sets the voltage and frequency level in the embedded load device so as to keep the state-of-charge of the supercapacitor in a desirable range. Experimental results show that the proposed global controller lowers the task instance drop rate by up to 60% compared with baseline controllers within the same service time.},

keywords = {System level power management, DC-DC conversion, Analysis/design - Algorithmic level},

}