Balancing distributed analytics' energy consumption using physics-inspired models

Brent Kraczek, Theodoros Salonidis, Prithwish Basu, Sayed Saghaian, Ali Sydney, Bongjun Ko, Thomas F. La Porta, Kevin Chan, James Lambert

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

With the rise of small, networked sensors, the volume of data generated increasingly require curation by AI to analyze which events are of sufficient importance to report to human operators. We consider the ultimate limit of edge computing, when it is impractical to employ external resources for the curation, but individual devices have insufficient computing resources to perform the analytics themselves. In a previous paper we introduced a decenralized method that distributes the analytics over the network of devices, employing simulated annealing, based on physics-inspired Metropolis Monte Carlo. If the present paper we discuss the capability of this method to balance the energy consumption of the placement on a network of heterogeneous resources. We introduce the balanced utilization index (BUI), an adaptation of Jain's Fairness Index, to measure this balance.

Original languageEnglish (US)
Title of host publicationDisruptive Technologies in Information Sciences
EditorsMisty Blowers, Russell D. Hall, Venkateswara R. Dasari
PublisherSPIE
ISBN (Electronic)9781510618152
DOIs
StatePublished - Jan 1 2018
EventDisruptive Technologies in Information Sciences 2018 - Orlando, United States
Duration: Apr 17 2018Apr 18 2018

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10652
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherDisruptive Technologies in Information Sciences 2018
CountryUnited States
CityOrlando
Period4/17/184/18/18

Fingerprint

energy consumption
Simulated annealing
Balancing
Energy Consumption
resources
Energy utilization
Physics
physics
Resources
Sensors
Computing
simulated annealing
Fairness
Simulated Annealing
Placement
Model
Sufficient
operators
Sensor
sensors

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Kraczek, B., Salonidis, T., Basu, P., Saghaian, S., Sydney, A., Ko, B., ... Lambert, J. (2018). Balancing distributed analytics' energy consumption using physics-inspired models. In M. Blowers, R. D. Hall, & V. R. Dasari (Eds.), Disruptive Technologies in Information Sciences [1065206] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10652). SPIE. https://doi.org/10.1117/12.2304485
Kraczek, Brent ; Salonidis, Theodoros ; Basu, Prithwish ; Saghaian, Sayed ; Sydney, Ali ; Ko, Bongjun ; La Porta, Thomas F. ; Chan, Kevin ; Lambert, James. / Balancing distributed analytics' energy consumption using physics-inspired models. Disruptive Technologies in Information Sciences. editor / Misty Blowers ; Russell D. Hall ; Venkateswara R. Dasari. SPIE, 2018. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{d414df6446b944db95eca528a00afbd8,
title = "Balancing distributed analytics' energy consumption using physics-inspired models",
abstract = "With the rise of small, networked sensors, the volume of data generated increasingly require curation by AI to analyze which events are of sufficient importance to report to human operators. We consider the ultimate limit of edge computing, when it is impractical to employ external resources for the curation, but individual devices have insufficient computing resources to perform the analytics themselves. In a previous paper we introduced a decenralized method that distributes the analytics over the network of devices, employing simulated annealing, based on physics-inspired Metropolis Monte Carlo. If the present paper we discuss the capability of this method to balance the energy consumption of the placement on a network of heterogeneous resources. We introduce the balanced utilization index (BUI), an adaptation of Jain's Fairness Index, to measure this balance.",
author = "Brent Kraczek and Theodoros Salonidis and Prithwish Basu and Sayed Saghaian and Ali Sydney and Bongjun Ko and {La Porta}, {Thomas F.} and Kevin Chan and James Lambert",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2304485",
language = "English (US)",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Misty Blowers and Hall, {Russell D.} and Dasari, {Venkateswara R.}",
booktitle = "Disruptive Technologies in Information Sciences",
address = "United States",

}

Kraczek, B, Salonidis, T, Basu, P, Saghaian, S, Sydney, A, Ko, B, La Porta, TF, Chan, K & Lambert, J 2018, Balancing distributed analytics' energy consumption using physics-inspired models. in M Blowers, RD Hall & VR Dasari (eds), Disruptive Technologies in Information Sciences., 1065206, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10652, SPIE, Disruptive Technologies in Information Sciences 2018, Orlando, United States, 4/17/18. https://doi.org/10.1117/12.2304485

Balancing distributed analytics' energy consumption using physics-inspired models. / Kraczek, Brent; Salonidis, Theodoros; Basu, Prithwish; Saghaian, Sayed; Sydney, Ali; Ko, Bongjun; La Porta, Thomas F.; Chan, Kevin; Lambert, James.

Disruptive Technologies in Information Sciences. ed. / Misty Blowers; Russell D. Hall; Venkateswara R. Dasari. SPIE, 2018. 1065206 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10652).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Balancing distributed analytics' energy consumption using physics-inspired models

AU - Kraczek, Brent

AU - Salonidis, Theodoros

AU - Basu, Prithwish

AU - Saghaian, Sayed

AU - Sydney, Ali

AU - Ko, Bongjun

AU - La Porta, Thomas F.

AU - Chan, Kevin

AU - Lambert, James

PY - 2018/1/1

Y1 - 2018/1/1

N2 - With the rise of small, networked sensors, the volume of data generated increasingly require curation by AI to analyze which events are of sufficient importance to report to human operators. We consider the ultimate limit of edge computing, when it is impractical to employ external resources for the curation, but individual devices have insufficient computing resources to perform the analytics themselves. In a previous paper we introduced a decenralized method that distributes the analytics over the network of devices, employing simulated annealing, based on physics-inspired Metropolis Monte Carlo. If the present paper we discuss the capability of this method to balance the energy consumption of the placement on a network of heterogeneous resources. We introduce the balanced utilization index (BUI), an adaptation of Jain's Fairness Index, to measure this balance.

AB - With the rise of small, networked sensors, the volume of data generated increasingly require curation by AI to analyze which events are of sufficient importance to report to human operators. We consider the ultimate limit of edge computing, when it is impractical to employ external resources for the curation, but individual devices have insufficient computing resources to perform the analytics themselves. In a previous paper we introduced a decenralized method that distributes the analytics over the network of devices, employing simulated annealing, based on physics-inspired Metropolis Monte Carlo. If the present paper we discuss the capability of this method to balance the energy consumption of the placement on a network of heterogeneous resources. We introduce the balanced utilization index (BUI), an adaptation of Jain's Fairness Index, to measure this balance.

UR - http://www.scopus.com/inward/record.url?scp=85049225449&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049225449&partnerID=8YFLogxK

U2 - 10.1117/12.2304485

DO - 10.1117/12.2304485

M3 - Conference contribution

AN - SCOPUS:85049225449

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Disruptive Technologies in Information Sciences

A2 - Blowers, Misty

A2 - Hall, Russell D.

A2 - Dasari, Venkateswara R.

PB - SPIE

ER -

Kraczek B, Salonidis T, Basu P, Saghaian S, Sydney A, Ko B et al. Balancing distributed analytics' energy consumption using physics-inspired models. In Blowers M, Hall RD, Dasari VR, editors, Disruptive Technologies in Information Sciences. SPIE. 2018. 1065206. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2304485