Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency

Catherine D. Schuman; Steven R. Young; J. Parker Mitchell; J. Travis Johnston; Derek Rose; Bryan P. Maldonado; Brian C. Kaul

doi:10.1109/IGSC51522.2020.9291228

Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency

Catherine D. Schuman, Steven R. Young, J. Parker Mitchell, J. Travis Johnston, Derek Rose, Bryan P. Maldonado, Brian C. Kaul

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

Neuromorphic computing offers one path forward for AI at the edge. However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial. In this work, we present a complete pipeline for neuromorphic computing at the edge, including a small, inexpensive, low-power, FPGA-based neuromorphic hardware platform, a training algorithm for designing spiking neural networks for neuromorphic hardware, and a software framework for connecting those components. We demonstrate this pipeline on a real-world application, engine control for a spark-ignition internal combustion engine. We illustrate how we connect engine simulations with neuromorphic hardware simulations and training software to produce hardware-compatible spiking neural networks that perform engine control to improve fuel efficiency. We present initial results on the performance of these spiking neural networks and illustrate that they outperform open-loop engine control. We also give size, weight, and power estimates for a deployed solution of this type.

Original language	English
Title of host publication	2020 11th International Green and Sustainable Computing Workshops, IGSC 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665415521
DOIs	https://doi.org/10.1109/IGSC51522.2020.9291228
State	Published - Oct 19 2020
Event	11th International Green and Sustainable Computing Workshops, IGSC 2020 - Pullman, United States Duration: Oct 19 2020 → Oct 22 2020

Publication series

Name	2020 11th International Green and Sustainable Computing Workshops, IGSC 2020

Conference

Conference	11th International Green and Sustainable Computing Workshops, IGSC 2020
Country/Territory	United States
City	Pullman
Period	10/19/20 → 10/22/20

Funding

This research was supported in part by the DOE Office of Energy Efficiency and Renewable Energy (EERE), Vehicle Technologies Office, under the guidance of Gurpreet Singh and Michael Weismiller, and used resources at the National Transportation Research Center, a DOE-EERE User Facility at Oak Ridge National Laboratory. This research used resources of the Compute and Data Environment for Science (CADES) at the Oak Ridge National Laboratory, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-000R22725. We would like to thank Chris Layton for his support in our utilization of CADES Cloud. This material is based upon work supported in part by the U.S. Department of Energy, Office of Science, Office of Advanced Scientific Computing Research, under contract number DE-AC05-000R22725, and in part by the Laboratory Directed Research and Development Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC. Notice: This manuscript has been authored in part by UT-Battelle, LLC under Contract No, DE-AC05-000R22725 with the U,S, Department of Energy, The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a non-exclusive, paid-Up, irrevocable, world-wide license to publish or reproduce the published form of this manuscript, or allow others to do so, for United States Government purposes, The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan (http://energy,gov/downloads/doe-publicaccess-plan),

Funders	Funder number
CADES
DOE Public Access Plan
DOE-EERE
Data Environment for Science
United States Government
U.S. Department of Energy
Office of Science
Office of Energy Efficiency and Renewable Energy
Advanced Scientific Computing Research	DE-AC05-000R22725
Oak Ridge National Laboratory
UT-Battelle

Keywords

FPGA
engine control unit
internal combustion engine
neuromorphic

Access to Document

10.1109/IGSC51522.2020.9291228

Cite this

Schuman, C. D., Young, S. R., Mitchell, J. P., Johnston, J. T., Rose, D., Maldonado, B. P., & Kaul, B. C. (2020). Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency. In 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020 Article 9291228 (2020 11th International Green and Sustainable Computing Workshops, IGSC 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGSC51522.2020.9291228

Schuman, Catherine D. ; Young, Steven R. ; Mitchell, J. Parker et al. / Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency. 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 11th International Green and Sustainable Computing Workshops, IGSC 2020).

@inproceedings{f008058be34f460a8add06036887fe31,

title = "Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency",

abstract = "Neuromorphic computing offers one path forward for AI at the edge. However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial. In this work, we present a complete pipeline for neuromorphic computing at the edge, including a small, inexpensive, low-power, FPGA-based neuromorphic hardware platform, a training algorithm for designing spiking neural networks for neuromorphic hardware, and a software framework for connecting those components. We demonstrate this pipeline on a real-world application, engine control for a spark-ignition internal combustion engine. We illustrate how we connect engine simulations with neuromorphic hardware simulations and training software to produce hardware-compatible spiking neural networks that perform engine control to improve fuel efficiency. We present initial results on the performance of these spiking neural networks and illustrate that they outperform open-loop engine control. We also give size, weight, and power estimates for a deployed solution of this type.",

keywords = "FPGA, engine control unit, internal combustion engine, neuromorphic",

author = "Schuman, {Catherine D.} and Young, {Steven R.} and Mitchell, {J. Parker} and Johnston, {J. Travis} and Derek Rose and Maldonado, {Bryan P.} and Kaul, {Brian C.}",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 11th International Green and Sustainable Computing Workshops, IGSC 2020 ; Conference date: 19-10-2020 Through 22-10-2020",

year = "2020",

month = oct,

day = "19",

doi = "10.1109/IGSC51522.2020.9291228",

language = "English",

series = "2020 11th International Green and Sustainable Computing Workshops, IGSC 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 11th International Green and Sustainable Computing Workshops, IGSC 2020",

}

Schuman, CD, Young, SR, Mitchell, JP, Johnston, JT, Rose, D , Maldonado, BP & Kaul, BC 2020, Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency. in 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020., 9291228, 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020, Institute of Electrical and Electronics Engineers Inc., 11th International Green and Sustainable Computing Workshops, IGSC 2020, Pullman, United States, 10/19/20. https://doi.org/10.1109/IGSC51522.2020.9291228

Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency. / Schuman, Catherine D.; Young, Steven R.; Mitchell, J. Parker et al.
2020 11th International Green and Sustainable Computing Workshops, IGSC 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9291228 (2020 11th International Green and Sustainable Computing Workshops, IGSC 2020).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency

AU - Schuman, Catherine D.

AU - Young, Steven R.

AU - Mitchell, J. Parker

AU - Johnston, J. Travis

AU - Rose, Derek

AU - Maldonado, Bryan P.

AU - Kaul, Brian C.

PY - 2020/10/19

Y1 - 2020/10/19

N2 - Neuromorphic computing offers one path forward for AI at the edge. However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial. In this work, we present a complete pipeline for neuromorphic computing at the edge, including a small, inexpensive, low-power, FPGA-based neuromorphic hardware platform, a training algorithm for designing spiking neural networks for neuromorphic hardware, and a software framework for connecting those components. We demonstrate this pipeline on a real-world application, engine control for a spark-ignition internal combustion engine. We illustrate how we connect engine simulations with neuromorphic hardware simulations and training software to produce hardware-compatible spiking neural networks that perform engine control to improve fuel efficiency. We present initial results on the performance of these spiking neural networks and illustrate that they outperform open-loop engine control. We also give size, weight, and power estimates for a deployed solution of this type.

AB - Neuromorphic computing offers one path forward for AI at the edge. However, accessing and effectively utilizing a neuromorphic hardware platform is non-trivial. In this work, we present a complete pipeline for neuromorphic computing at the edge, including a small, inexpensive, low-power, FPGA-based neuromorphic hardware platform, a training algorithm for designing spiking neural networks for neuromorphic hardware, and a software framework for connecting those components. We demonstrate this pipeline on a real-world application, engine control for a spark-ignition internal combustion engine. We illustrate how we connect engine simulations with neuromorphic hardware simulations and training software to produce hardware-compatible spiking neural networks that perform engine control to improve fuel efficiency. We present initial results on the performance of these spiking neural networks and illustrate that they outperform open-loop engine control. We also give size, weight, and power estimates for a deployed solution of this type.

KW - FPGA

KW - engine control unit

KW - internal combustion engine

KW - neuromorphic

UR - http://www.scopus.com/inward/record.url?scp=85099401248&partnerID=8YFLogxK

U2 - 10.1109/IGSC51522.2020.9291228

DO - 10.1109/IGSC51522.2020.9291228

M3 - Conference contribution

AN - SCOPUS:85099401248

T3 - 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020

BT - 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Green and Sustainable Computing Workshops, IGSC 2020

Y2 - 19 October 2020 through 22 October 2020

ER -

Schuman CD, Young SR, Mitchell JP, Johnston JT, Rose D , Maldonado BP et al. Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency. In 2020 11th International Green and Sustainable Computing Workshops, IGSC 2020. Institute of Electrical and Electronics Engineers Inc. 2020. 9291228. (2020 11th International Green and Sustainable Computing Workshops, IGSC 2020). doi: 10.1109/IGSC51522.2020.9291228

Low Size, Weight, and Power Neuromorphic Computing to Improve Combustion Engine Efficiency

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this