Traffic-Efficient Split Computing Mechanism for Internet of Things

Hojin Yeom; Haneul Ko; Sangheon Pack

doi:10.1109/ICTC58733.2023.10392723

Traffic-Efficient Split Computing Mechanism for Internet of Things

Hojin Yeom, Haneul Ko, Sangheon Pack

School of Electrical Engineering

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

Abstract

In the split computing approach, channel coding can be exploited to transmit the intermediate data, balancing the tradeoff between accuracy and traffic overhead. In this paper, we propose a traffic-efficient split computing mechanism (TESC) in which the IoT device decides whether to exploit channel coding and its error correction capability according to the channel condition to transmit the intermediate data to the edge cloud. Evaluation results show that TESC can reduce the traffic overhead by over 80% while maintaining the accuracy of the model at a high level compared to the retransmission-based scheme.

Original language	English
Title of host publication	ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence
Subtitle of host publication	Exploring the Frontiers of ICT Innovation
Publisher	IEEE Computer Society
Pages	495-496
Number of pages	2
ISBN (Electronic)	9798350313277
DOIs	https://doi.org/10.1109/ICTC58733.2023.10392723
Publication status	Published - 2023
Event	14th International Conference on Information and Communication Technology Convergence, ICTC 2023 - Jeju Island, Korea, Republic of Duration: 2023 Oct 11 → 2023 Oct 13

Publication series

Name	International Conference on ICT Convergence
ISSN (Print)	2162-1233
ISSN (Electronic)	2162-1241

Conference

Conference	14th International Conference on Information and Communication Technology Convergence, ICTC 2023
Country/Territory	Korea, Republic of
City	Jeju Island
Period	23/10/11 → 23/10/13

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Internet of Things
Split ML
Split computing
distributed computing
inference

ASJC Scopus subject areas

Information Systems
Computer Networks and Communications

Access to Document

10.1109/ICTC58733.2023.10392723

Cite this

Yeom, H., Ko, H., & Pack, S. (2023). Traffic-Efficient Split Computing Mechanism for Internet of Things. In ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation (pp. 495-496). (International Conference on ICT Convergence). IEEE Computer Society. https://doi.org/10.1109/ICTC58733.2023.10392723

Traffic-Efficient Split Computing Mechanism for Internet of Things. / Yeom, Hojin; Ko, Haneul; Pack, Sangheon.
ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. IEEE Computer Society, 2023. p. 495-496 (International Conference on ICT Convergence).

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

Yeom, H, Ko, H & Pack, S 2023, Traffic-Efficient Split Computing Mechanism for Internet of Things. in ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence: Exploring the Frontiers of ICT Innovation. International Conference on ICT Convergence, IEEE Computer Society, pp. 495-496, 14th International Conference on Information and Communication Technology Convergence, ICTC 2023, Jeju Island, Korea, Republic of, 23/10/11. https://doi.org/10.1109/ICTC58733.2023.10392723

@inproceedings{b27bcd151f0447d1af44f92c07439466,

title = "Traffic-Efficient Split Computing Mechanism for Internet of Things",

abstract = "In the split computing approach, channel coding can be exploited to transmit the intermediate data, balancing the tradeoff between accuracy and traffic overhead. In this paper, we propose a traffic-efficient split computing mechanism (TESC) in which the IoT device decides whether to exploit channel coding and its error correction capability according to the channel condition to transmit the intermediate data to the edge cloud. Evaluation results show that TESC can reduce the traffic overhead by over 80% while maintaining the accuracy of the model at a high level compared to the retransmission-based scheme.",

keywords = "Internet of Things, Split ML, Split computing, distributed computing, inference",

author = "Hojin Yeom and Haneul Ko and Sangheon Pack",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th International Conference on Information and Communication Technology Convergence, ICTC 2023 ; Conference date: 11-10-2023 Through 13-10-2023",

year = "2023",

doi = "10.1109/ICTC58733.2023.10392723",

language = "English",

series = "International Conference on ICT Convergence",

publisher = "IEEE Computer Society",

pages = "495--496",

booktitle = "ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence",

}

TY - GEN

T1 - Traffic-Efficient Split Computing Mechanism for Internet of Things

AU - Yeom, Hojin

AU - Ko, Haneul

AU - Pack, Sangheon

PY - 2023

Y1 - 2023

N2 - In the split computing approach, channel coding can be exploited to transmit the intermediate data, balancing the tradeoff between accuracy and traffic overhead. In this paper, we propose a traffic-efficient split computing mechanism (TESC) in which the IoT device decides whether to exploit channel coding and its error correction capability according to the channel condition to transmit the intermediate data to the edge cloud. Evaluation results show that TESC can reduce the traffic overhead by over 80% while maintaining the accuracy of the model at a high level compared to the retransmission-based scheme.

AB - In the split computing approach, channel coding can be exploited to transmit the intermediate data, balancing the tradeoff between accuracy and traffic overhead. In this paper, we propose a traffic-efficient split computing mechanism (TESC) in which the IoT device decides whether to exploit channel coding and its error correction capability according to the channel condition to transmit the intermediate data to the edge cloud. Evaluation results show that TESC can reduce the traffic overhead by over 80% while maintaining the accuracy of the model at a high level compared to the retransmission-based scheme.

KW - Internet of Things

KW - Split ML

KW - Split computing

KW - distributed computing

KW - inference

UR - http://www.scopus.com/inward/record.url?scp=85184583611&partnerID=8YFLogxK

U2 - 10.1109/ICTC58733.2023.10392723

DO - 10.1109/ICTC58733.2023.10392723

M3 - Conference contribution

AN - SCOPUS:85184583611

T3 - International Conference on ICT Convergence

SP - 495

EP - 496

BT - ICTC 2023 - 14th International Conference on Information and Communication Technology Convergence

PB - IEEE Computer Society

T2 - 14th International Conference on Information and Communication Technology Convergence, ICTC 2023

Y2 - 11 October 2023 through 13 October 2023

ER -

Traffic-Efficient Split Computing Mechanism for Internet of Things

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this