New technical paper titled “EVE: Environmental Adaptive Neural Network Models for Low-Power Energy Harvesting System” was published by researchers at UT San Antonio, University of Connecticut, and Lehigh University.
According to the abstract:
“This paper proposes EVE, an automated machine learning (autoML) co-exploration framework to search for desired multi-models with shared weights for energy harvesting IoT devices. Those shared models incur significantly reduced memory footprint with different levels of model sparsity, latency, and accuracy to adapt to the environmental changes. An efficient on-device implementation architecture is further developed to efficiently execute each model on device. A run-time model extraction algorithm is proposed that retrieves individual model with negligible overhead when a specific model mode is triggered. Experimental results show that the neural networks models generated by EVE is on average 2.5X times faster than the baseline models without pruning and shared weights.”
Find the technical paper here. Published July 2022.
Authors: Sahidul Islam, Shanglin Zhou, Ran Ran, Yufang Jin, Wujie Wen, Caiwen Ding, Mimi Xie
arXiv:2207.09258v1
Related Articles
Energy Harvesting Starting To Gain Traction
After years of research, chipmakers have started combining ultra low-power designs with advancements in harvesting technology.
Photovoltaic Cell Harvests Energy After Sun Goes Down
Stanford researchers report power generation from radiative cooling of a PV cell at night using a thermoelectric generator (TEG) module.
Energy Harvesting And Power Management For IoT Devices In The 5G Era
Prospective power harvesting scenarios of IoT devices in the 5G network
Leave a Reply