Do Developers Adopt Green Architectural Tactics for ML-Enabled Systems? A Mining Software Repository Study

As machine learning (ML) and artificial intelligence (AI) technologies become more widespread, concerns about their environmental impact are increasing due to the resource-intensive nature of training and inference processes. Green AI advocates for reducing computational demands while still maintain...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/ACM International Conference on Software Engineering: Software Engineering in Society (Online) pp. 135 - 139
Main Authors: De Martino, Vincenzo, Martinez-Fernandez, Silverio, Palomba, Fabio
Format: Conference Proceeding
Language:English
Published: IEEE 27.04.2025
Subjects:
Automation
Data mining
Empirical Software Engineering
Green AI
Green products
Large language models
Machine learning
Machine Learning-Enabled Systems
Software development management
Software engineering
Software Sustainability
Sustainable development
System software
Training
ISSN:2832-7616
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract As machine learning (ML) and artificial intelligence (AI) technologies become more widespread, concerns about their environmental impact are increasing due to the resource-intensive nature of training and inference processes. Green AI advocates for reducing computational demands while still maintaining accuracy. Although various strategies for creating sustainable ML systems have been identified, their real-world implementation is still underexplored. This paper addresses this gap by studying 168 open-source ML projects on GitHub. It employs a novel large language model (LLM)-based mining mechanism to identify and analyze green strategies. The findings reveal the adoption of established tactics that offer significant environmental benefits. This provides practical insights for developers and paves the way for future automation of sustainable practices in ML systems.
AbstractList As machine learning (ML) and artificial intelligence (AI) technologies become more widespread, concerns about their environmental impact are increasing due to the resource-intensive nature of training and inference processes. Green AI advocates for reducing computational demands while still maintaining accuracy. Although various strategies for creating sustainable ML systems have been identified, their real-world implementation is still underexplored. This paper addresses this gap by studying 168 open-source ML projects on GitHub. It employs a novel large language model (LLM)-based mining mechanism to identify and analyze green strategies. The findings reveal the adoption of established tactics that offer significant environmental benefits. This provides practical insights for developers and paves the way for future automation of sustainable practices in ML systems.
Author De Martino, Vincenzo
Martinez-Fernandez, Silverio
Palomba, Fabio
Author_xml – sequence: 1
  givenname: Vincenzo
  surname: De Martino
  fullname: De Martino, Vincenzo
  email: vdemartino@unisa.it
  organization: University of Salerno,Software Engineering (SeSa) Lab,Italy
– sequence: 2
  givenname: Silverio
  surname: Martinez-Fernandez
  fullname: Martinez-Fernandez, Silverio
  email: silverio.martinez@upc.edu
  organization: Universitat Politècnica de Catalunya,Spain
– sequence: 3
  givenname: Fabio
  surname: Palomba
  fullname: Palomba, Fabio
  email: fpalomba@unisa.it
  organization: University of Salerno,Software Engineering (SeSa) Lab,Italy
BookMark eNotkM1OwkAYAFejiYi8gYf1AYr70-7PyTRQkQRiYvFMtt2vWlK6ze4i6dtLoqe5TOYw9-imdz0g9ETJnFKin9eLskjKYl0KwTM6Z4Rlc0II1VdopqVWnNOMSyLTazRhirNECiru0CyEw0XjjFLJ6AQdlg4v4Qc6N4APOLduiHjlAXqc-_q7jVDHkzcd3pk6tnXAjfN4u0mK3lQdWFyOIcIxvOAcb9u-7b9w6Zp4Nh7wBwwutNH5EZfxZMcHdNuYLsDsn1P0-VrsFm_J5n21XuSbxDBJYiJZIypVy9Rm2qagFVGcElEJUddAIbVGaN2wlElpqGpSUFYTIWXaZJZVFeVT9PjXbQFgP_j2aPy4v0xjXGnBfwFdllxt
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICSE-SEIS66351.2025.00019
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331537074
EISSN 2832-7616
EndPage 139
ExternalDocumentID 11023896
Genre orig-research
GroupedDBID 6IE
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-a270t-72f6b8c74d59d4e98083106b66cce1e4da699f24277a18f4e8d906774f5d2bb13
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001553878700014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Jun 18 06:01:25 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a270t-72f6b8c74d59d4e98083106b66cce1e4da699f24277a18f4e8d906774f5d2bb13
PageCount 5
ParticipantIDs ieee_primary_11023896
PublicationCentury 2000
PublicationDate 2025-April-27
PublicationDateYYYYMMDD 2025-04-27
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-April-27
  day: 27
PublicationDecade 2020
PublicationTitle IEEE/ACM International Conference on Software Engineering: Software Engineering in Society (Online)
PublicationTitleAbbrev ICSE-SEIS
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211721
Score 2.2969196
Snippet As machine learning (ML) and artificial intelligence (AI) technologies become more widespread, concerns about their environmental impact are increasing due to...
SourceID ieee
SourceType Publisher
StartPage 135
SubjectTerms Automation
Data mining
Empirical Software Engineering
Green AI
Green products
Large language models
Machine learning
Machine Learning-Enabled Systems
Software development management
Software engineering
Software Sustainability
Sustainable development
System software
Training
Title Do Developers Adopt Green Architectural Tactics for ML-Enabled Systems? A Mining Software Repository Study
URI https://ieeexplore.ieee.org/document/11023896
WOSCitedRecordID wos001553878700014&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NS8MwGA5uiHhSceI3r-C1rk2zfJxkzA0Hbgw2YbfRJm9hIutYO8V_b5LVzYsHD4XSQygJ5Hm_nuch5D42SlFt01SMDAtYghhYEBYB1TbbsI9uGebNJsRwKKdTNarI6p4Lg4h--Awf3Kvv5Ztcr12prBk5nQGpeI3UhOAbsta2oBLbxW06c0DuKh3NZr8z7tpbqT92qOpyQerqJ15U55eTigeS3tE_f-GYNHaUPBhtweaE7OHilLw95VBN_dgoDtomX5bgJ2mgvWsQJO8w8VSoAmyECoOXoOsJUwYqufJHaMPAG0XA2N7Kn8kKwQXmxdx14MGNGn41yGuvO-k8B5V5QpBQEZaBoBlPpRbMtJRhqKS3FOMp51pjhMwkXKnMArQQSSQzhtIopybHspahaRrFZ6S-yBd4ToCZSPjFZByyhClXOjVZKBQNJdoI54I03EbNlht9jNnPHl3-8f2KHLqzcD0ZKq5JvVyt8Ybs649yXqxu_al-A6Y5olk
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwGA06RT2pOPG3n-C12qZpk5xkzI0NtzHYhN1Gm3yFiaxj6xT_e5Osbl48eCiUHkJJIO_79d4j5D7UUlJl0lQMNPNYgugZEOYeVSbbMI-KNHNmE7zXE6OR7JdkdceFQUQ3fIYP9tX18nWulrZU9hhYnQEh422yEzFG_RVda11SCc3yJqHZI3elkuZjuz5omHupPbC4arNBaisoTlbnl5eKg5Lm4T9_4ohUN6Q86K_h5phs4fSEvD3nUM79mDgOajqfFeBmaaC2aREk7zB0ZKgFmBgVuh2v4ShTGkrB8ieoQddZRcDA3MufyRzBhuaLie3Bgx02_KqS12ZjWG95pX2Cl1DuFx6nWZwKxZmOpGYohTMVi9M4VgoDZDqJpcwMRHOeBCJjKLS0enIsizRN0yA8JZVpPsUzAkwH3C0mQp8lTNriqc58Lqkv0MQ456RqN2o8WylkjH_26OKP77dkvzXsdsaddu_lkhzYc7EdGsqvSKWYL_Ga7KqPYrKY37gT_gZHZqWg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=IEEE%2FACM+International+Conference+on+Software+Engineering%3A+Software+Engineering+in+Society+%28Online%29&rft.atitle=Do+Developers+Adopt+Green+Architectural+Tactics+for+ML-Enabled+Systems%3F+A+Mining+Software+Repository+Study&rft.au=De+Martino%2C+Vincenzo&rft.au=Martinez-Fernandez%2C+Silverio&rft.au=Palomba%2C+Fabio&rft.date=2025-04-27&rft.pub=IEEE&rft.eissn=2832-7616&rft.spage=135&rft.epage=139&rft_id=info:doi/10.1109%2FICSE-SEIS66351.2025.00019&rft.externalDocID=11023896