TAAC: Task Allocation Meets Approximate Computing for Internet of Things

Wanli  Yu; Ardalan Najafi; Yarib Nevarez; Yanqiu Huang; Alberto  Garcia-Ortiz

doi:10.1109/ISCAS45731.2020.9180895

TAAC: Task Allocation Meets Approximate Computing for Internet of Things

Wanli Yu, Ardalan Najafi, Yarib Nevarez, Yanqiu Huang, Alberto Garcia-Ortiz

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

3 Citations (Scopus)

63 Downloads (Pure)

Abstract

Ultra-low-power operation, as required by Internet of Things (IoT) systems, requires to address energy consumption at all levels from circuit to system. Two of the promising solutions at circuit and system levels are approximate computing and energy aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. For the first time, this work proposes an optimal Task Allocation algorithm taking the Approximate Computing into account (TAAC) to fill this gap. The problem of tasks assignment and executing modes selection (approximate or exact modes of the tasks) can be efficiently solved by formulating it as a linear programming problem. The extensive simulation results show that the proposed TAAC algorithm significantly outperforms the previous approaches.

Original language	English
Title of host publication	2020 IEEE International Symposium on Circuits and Systems (ISCAS)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Number of pages	5
ISBN (Electronic)	9781728133201
ISBN (Print)	978-1-7281-3320-1
DOIs	https://doi.org/10.1109/ISCAS45731.2020.9180895
Publication status	Published - 28 Sept 2020
Event	52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020 - Virtual Conference, Virtual, Online, Spain Duration: 10 Oct 2020 → 21 Oct 2020 Conference number: 52 https://www.iscas2020.org/

Publication series

Name	IEEE International Symposium on Circuits and Systems (ISCAS)
Publisher	IEEE
Volume	2020
ISSN (Print)	2158-1525

Conference

Conference	52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020
Abbreviated title	ISCAS 2020
Country/Territory	Spain
City	Virtual, Online
Period	10/10/20 → 21/10/20
Internet address	https://www.iscas2020.org/

Keywords

22/2 OA procedure

Access to Document

10.1109/ISCAS45731.2020.9180895

Yu-2020-Taac-task-allocation-meets-approximFinal published version, 306 KBLicence: Taverne

Cite this

@inproceedings{e8927419acbf4d6eb291cd58cc7370db,

title = "TAAC: Task Allocation Meets Approximate Computing for Internet of Things",

abstract = "Ultra-low-power operation, as required by Internet of Things (IoT) systems, requires to address energy consumption at all levels from circuit to system. Two of the promising solutions at circuit and system levels are approximate computing and energy aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. For the first time, this work proposes an optimal Task Allocation algorithm taking the Approximate Computing into account (TAAC) to fill this gap. The problem of tasks assignment and executing modes selection (approximate or exact modes of the tasks) can be efficiently solved by formulating it as a linear programming problem. The extensive simulation results show that the proposed TAAC algorithm significantly outperforms the previous approaches.",

keywords = "22/2 OA procedure",

author = "Wanli Yu and Ardalan Najafi and Yarib Nevarez and Yanqiu Huang and Alberto Garcia-Ortiz",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE; 52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020, ISCAS 2020 ; Conference date: 10-10-2020 Through 21-10-2020",

year = "2020",

month = sep,

day = "28",

doi = "10.1109/ISCAS45731.2020.9180895",

language = "English",

isbn = "978-1-7281-3320-1",

series = "IEEE International Symposium on Circuits and Systems (ISCAS)",

publisher = "IEEE",

booktitle = "2020 IEEE International Symposium on Circuits and Systems (ISCAS)",

address = "United States",

url = "https://www.iscas2020.org/",

}

Yu, W, Najafi, A, Nevarez, Y, Huang, Y & Garcia-Ortiz, A 2020, TAAC: Task Allocation Meets Approximate Computing for Internet of Things. in 2020 IEEE International Symposium on Circuits and Systems (ISCAS)., 9180895, IEEE International Symposium on Circuits and Systems (ISCAS), vol. 2020, IEEE, Piscataway, NJ, 52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020, Virtual, Online, Spain, 10/10/20. https://doi.org/10.1109/ISCAS45731.2020.9180895

TAAC: Task Allocation Meets Approximate Computing for Internet of Things. / Yu, Wanli ; Najafi, Ardalan; Nevarez, Yarib et al.
2020 IEEE International Symposium on Circuits and Systems (ISCAS). Piscataway, NJ: IEEE, 2020. 9180895 (IEEE International Symposium on Circuits and Systems (ISCAS); Vol. 2020).

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

TY - GEN

T1 - TAAC: Task Allocation Meets Approximate Computing for Internet of Things

AU - Yu, Wanli

AU - Najafi, Ardalan

AU - Nevarez, Yarib

AU - Huang, Yanqiu

AU - Garcia-Ortiz, Alberto

N1 - Conference code: 52

PY - 2020/9/28

Y1 - 2020/9/28

N2 - Ultra-low-power operation, as required by Internet of Things (IoT) systems, requires to address energy consumption at all levels from circuit to system. Two of the promising solutions at circuit and system levels are approximate computing and energy aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. For the first time, this work proposes an optimal Task Allocation algorithm taking the Approximate Computing into account (TAAC) to fill this gap. The problem of tasks assignment and executing modes selection (approximate or exact modes of the tasks) can be efficiently solved by formulating it as a linear programming problem. The extensive simulation results show that the proposed TAAC algorithm significantly outperforms the previous approaches.

AB - Ultra-low-power operation, as required by Internet of Things (IoT) systems, requires to address energy consumption at all levels from circuit to system. Two of the promising solutions at circuit and system levels are approximate computing and energy aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. For the first time, this work proposes an optimal Task Allocation algorithm taking the Approximate Computing into account (TAAC) to fill this gap. The problem of tasks assignment and executing modes selection (approximate or exact modes of the tasks) can be efficiently solved by formulating it as a linear programming problem. The extensive simulation results show that the proposed TAAC algorithm significantly outperforms the previous approaches.

KW - 22/2 OA procedure

UR - http://www.scopus.com/inward/record.url?scp=85104862629&partnerID=8YFLogxK

U2 - 10.1109/ISCAS45731.2020.9180895

DO - 10.1109/ISCAS45731.2020.9180895

M3 - Conference contribution

SN - 978-1-7281-3320-1

T3 - IEEE International Symposium on Circuits and Systems (ISCAS)

BT - 2020 IEEE International Symposium on Circuits and Systems (ISCAS)

PB - IEEE

CY - Piscataway, NJ

T2 - 52nd IEEE International Symposium on Circuits and Systems, ISCAS 2020

Y2 - 10 October 2020 through 21 October 2020

ER -

TAAC: Task Allocation Meets Approximate Computing for Internet of Things

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this