TY - GEN
T1 - Optimizing Intelligent Edge-clouds with Partitioning, Compression and Speculative Inference
AU - Fang, Shiwei
AU - Huang, Jin
AU - Samplawski, Colin
AU - Ganesan, Deepak
AU - Marlin, Benjamin
AU - Abdelzaher, Tarek
AU - Wigness, Maggie B.
N1 - Funding Information:
ACKNOWLEDGMENTS The research reported in this paper was sponsored by the CCDC Army Research Laboratory (ARL) under Cooperative Agreement W911NF-17-2-0196 ARL IoBT CRA. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the ARL or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Internet of Battlefield Things (IoBTs) are well positioned to take advantage of recent technology trends that have led to the development of low-power neural accelerators and low-cost high-performance sensors. However, a key challenge that needs to be dealt with is that despite all the advancements, edge devices remain resource-constrained, thus prohibiting complex deep neural networks from deploying and deriving actionable insights from various sensors. Furthermore, deploying sophisticated sensors in a distributed manner to improve decision-making also poses an extra challenge of coordinating and exchanging data between the nodes and server. We propose an architecture that abstracts away these thorny deployment considerations from an end-user (such as a commander or warfighter). Our architecture can automatically compile and deploy the inference model into a set of distributed nodes and server while taking into consideration of the resource availability, variation, and uncertainties.
AB - Internet of Battlefield Things (IoBTs) are well positioned to take advantage of recent technology trends that have led to the development of low-power neural accelerators and low-cost high-performance sensors. However, a key challenge that needs to be dealt with is that despite all the advancements, edge devices remain resource-constrained, thus prohibiting complex deep neural networks from deploying and deriving actionable insights from various sensors. Furthermore, deploying sophisticated sensors in a distributed manner to improve decision-making also poses an extra challenge of coordinating and exchanging data between the nodes and server. We propose an architecture that abstracts away these thorny deployment considerations from an end-user (such as a commander or warfighter). Our architecture can automatically compile and deploy the inference model into a set of distributed nodes and server while taking into consideration of the resource availability, variation, and uncertainties.
UR - http://www.scopus.com/inward/record.url?scp=85124153290&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85124153290&partnerID=8YFLogxK
U2 - 10.1109/MILCOM52596.2021.9653126
DO - 10.1109/MILCOM52596.2021.9653126
M3 - Conference contribution
AN - SCOPUS:85124153290
T3 - Proceedings - IEEE Military Communications Conference MILCOM
SP - 892
EP - 897
BT - MILCOM 2021 - 2021 IEEE Military Communications Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Military Communications Conference, MILCOM 2021
Y2 - 29 November 2021 through 2 December 2021
ER -