Efficient edge computing: harnessing compact machine learning models for workload optimization

Mahdi Abbasi; Hassan Haghighi; Seifeddine Benelghali; Mohammad Reza Pour-Hosseini; Ehsan Mohammadi-Pasand; Bahman Javadi; Parham Moradi

doi:10.1145/3638530.3654307

Efficient edge computing: harnessing compact machine learning models for workload optimization

Mahdi Abbasi, Hassan Haghighi, Seifeddine Benelghali, Mohammad Reza Pour-Hosseini, Ehsan Mohammadi-Pasand, Bahman Javadi, Parham Moradi

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

3 Citations (Scopus)

Abstract

This paper proposes an innovative lightweight workload distribution model, TinyXCS, specifically designed for traditional edge devices, emphasizing efficiency and compactness. TinyXCS, an online model based on XCS learning classifier systems, demonstrates high levels of performance in reducing delays and energy consumption. Engineered to operate efficiently on conventional edge devices, The model offers a promising solution for optimizing workload distribution while considering memory constraints. Experimental results validate effectiveness of this model, representing a significant advancement in the quest for streamlined edge computing solutions.

Original language	English
Title of host publication	GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia
Place of Publication	U.S.
Publisher	Association for Computing Machinery
Pages	239-242
Number of pages	4
ISBN (Electronic)	9798400704956
DOIs	https://doi.org/10.1145/3638530.3654307
Publication status	Published - 2024
Event	2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion - Melbourne, Australia Duration: 14 Jul 2024 → 18 Jul 2024

Conference

Conference	2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion
Country/Territory	Australia
City	Melbourne
Period	14/07/24 → 18/07/24

Keywords

edge computing
internet of things
memory constraints
network optimization
workload distribution

Access to Document

10.1145/3638530.3654307

Cite this

Abbasi, M., Haghighi, H., Benelghali, S., Pour-Hosseini, M. R., Mohammadi-Pasand, E., Javadi, B., & Moradi, P. (2024). Efficient edge computing: harnessing compact machine learning models for workload optimization. In GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia (pp. 239-242). Association for Computing Machinery. https://doi.org/10.1145/3638530.3654307

@inproceedings{fb9a37a739ce44eabb4fe2a7459790b7,

title = "Efficient edge computing: harnessing compact machine learning models for workload optimization",

abstract = "This paper proposes an innovative lightweight workload distribution model, TinyXCS, specifically designed for traditional edge devices, emphasizing efficiency and compactness. TinyXCS, an online model based on XCS learning classifier systems, demonstrates high levels of performance in reducing delays and energy consumption. Engineered to operate efficiently on conventional edge devices, The model offers a promising solution for optimizing workload distribution while considering memory constraints. Experimental results validate effectiveness of this model, representing a significant advancement in the quest for streamlined edge computing solutions.",

keywords = "edge computing, internet of things, memory constraints, network optimization, workload distribution",

author = "Mahdi Abbasi and Hassan Haghighi and Seifeddine Benelghali and Pour-Hosseini, {Mohammad Reza} and Ehsan Mohammadi-Pasand and Bahman Javadi and Parham Moradi",

year = "2024",

doi = "10.1145/3638530.3654307",

language = "English",

pages = "239--242",

booktitle = "GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia",

publisher = "Association for Computing Machinery",

note = "2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion ; Conference date: 14-07-2024 Through 18-07-2024",

}

Abbasi, M, Haghighi, H, Benelghali, S, Pour-Hosseini, MR, Mohammadi-Pasand, E, Javadi, B & Moradi, P 2024, Efficient edge computing: harnessing compact machine learning models for workload optimization. in GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia. Association for Computing Machinery, U.S., pp. 239-242, 2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion, Melbourne, Australia, 14/07/24. https://doi.org/10.1145/3638530.3654307

Efficient edge computing: harnessing compact machine learning models for workload optimization. / Abbasi, Mahdi; Haghighi, Hassan; Benelghali, Seifeddine et al.
GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia. U.S.: Association for Computing Machinery, 2024. p. 239-242.

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

TY - GEN

T1 - Efficient edge computing: harnessing compact machine learning models for workload optimization

AU - Abbasi, Mahdi

AU - Haghighi, Hassan

AU - Benelghali, Seifeddine

AU - Pour-Hosseini, Mohammad Reza

AU - Mohammadi-Pasand, Ehsan

AU - Javadi, Bahman

AU - Moradi, Parham

PY - 2024

Y1 - 2024

N2 - This paper proposes an innovative lightweight workload distribution model, TinyXCS, specifically designed for traditional edge devices, emphasizing efficiency and compactness. TinyXCS, an online model based on XCS learning classifier systems, demonstrates high levels of performance in reducing delays and energy consumption. Engineered to operate efficiently on conventional edge devices, The model offers a promising solution for optimizing workload distribution while considering memory constraints. Experimental results validate effectiveness of this model, representing a significant advancement in the quest for streamlined edge computing solutions.

AB - This paper proposes an innovative lightweight workload distribution model, TinyXCS, specifically designed for traditional edge devices, emphasizing efficiency and compactness. TinyXCS, an online model based on XCS learning classifier systems, demonstrates high levels of performance in reducing delays and energy consumption. Engineered to operate efficiently on conventional edge devices, The model offers a promising solution for optimizing workload distribution while considering memory constraints. Experimental results validate effectiveness of this model, representing a significant advancement in the quest for streamlined edge computing solutions.

KW - edge computing

KW - internet of things

KW - memory constraints

KW - network optimization

KW - workload distribution

UR - http://www.scopus.com/inward/record.url?scp=85201949713&partnerID=8YFLogxK

UR - https://go.openathens.net/redirector/westernsydney.edu.au?url=https://doi.org/10.1145/3638530.3654307

U2 - 10.1145/3638530.3654307

DO - 10.1145/3638530.3654307

M3 - Conference Paper

AN - SCOPUS:85201949713

SP - 239

EP - 242

BT - GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia

PB - Association for Computing Machinery

CY - U.S.

T2 - 2024 Genetic and Evolutionary Computation Conference Companion, GECCO 2024 Companion

Y2 - 14 July 2024 through 18 July 2024

ER -

Abbasi M, Haghighi H, Benelghali S, Pour-Hosseini MR, Mohammadi-Pasand E, Javadi B et al. Efficient edge computing: harnessing compact machine learning models for workload optimization. In GECCO'24 Companion: Proceedings of the 2024 Genetic and Evolutionary Computation Conference Companion, July 14-18, 2024, Melbourne, Australia. U.S.: Association for Computing Machinery. 2024. p. 239-242 doi: 10.1145/3638530.3654307

Efficient edge computing: harnessing compact machine learning models for workload optimization

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this