TY - GEN
T1 - Energy-Efficient Mapping for a Network of DNN Models at the Edge
AU - Ghasemi, Mehdi
AU - Heidari, Soroush
AU - Kim, Young Geun
AU - Lamb, Aaron
AU - Wu, Carole-Jean
AU - Vrudhula, Sarma
N1 - Funding Information:
ACKNOWLEDGEMENT This research was supported in part by NSF Grant #2008244, and by the Center for Embedded Systems, NSF Grant #1361926.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/8
Y1 - 2021/8
N2 - This paper describes a novel framework for executing a network of trained deep neural network (DNN) models on commercial-off-the-shelf devices that are deployed in an IoT environment. The scenario consists of two devices connected by a wireless network: a user-end device (U), which is a low-end, energy and performance-limited processor, and a cloudlet (C), which is a substantially higher performance and energy-unconstrained processor. The goal is to distribute the computation of the DNN models between U and C to minimize the energy consumption of U while taking into account the variability in the wireless channel delay and the performance overhead of executing models in parallel. The proposed framework was implemented using an NVIDIA Jetson Nano for U and a Dell workstation with Titan Xp GPU as C. Experiments demonstrate significant improvements both in terms of energy consumption of U and processing delay.
AB - This paper describes a novel framework for executing a network of trained deep neural network (DNN) models on commercial-off-the-shelf devices that are deployed in an IoT environment. The scenario consists of two devices connected by a wireless network: a user-end device (U), which is a low-end, energy and performance-limited processor, and a cloudlet (C), which is a substantially higher performance and energy-unconstrained processor. The goal is to distribute the computation of the DNN models between U and C to minimize the energy consumption of U while taking into account the variability in the wireless channel delay and the performance overhead of executing models in parallel. The proposed framework was implemented using an NVIDIA Jetson Nano for U and a Dell workstation with Titan Xp GPU as C. Experiments demonstrate significant improvements both in terms of energy consumption of U and processing delay.
KW - deep neural networks
KW - edge computing
KW - energy
UR - http://www.scopus.com/inward/record.url?scp=85117589691&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85117589691&partnerID=8YFLogxK
U2 - 10.1109/SMARTCOMP52413.2021.00024
DO - 10.1109/SMARTCOMP52413.2021.00024
M3 - Conference contribution
AN - SCOPUS:85117589691
T3 - Proceedings - 2021 IEEE International Conference on Smart Computing, SMARTCOMP 2021
SP - 25
EP - 30
BT - Proceedings - 2021 IEEE International Conference on Smart Computing, SMARTCOMP 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th IEEE International Conference on Smart Computing, SMARTCOMP 2021
Y2 - 23 August 2021 through 27 August 2021
ER -