This page is being moved to a new, faster, and mobile-friendly application! Access the enhanced and centralized experience now on MyWorkspace!
ITU's 160 anniversary

Connecting the world and beyond

  •  
GSR 2025

ITU-T Recommendations

Search by number:
Others:
Skip Navigation Links
Content search
Advanced search
Provisional name
Equivalent number
Formal description
Study Groups tree viewExpand Study Groups tree view

ITU-T Y.4494 (11/2023)

عربي | 中文 | English | Español | Français | Русский
Reference architecture of collaborative decentralized machine learning for intelligent Internet of things services
A collaborative decentralized machine learning (CDML) architecture can support machine learning (ML) model distributed training and inference across highly heterogeneous and resource-constrained Internet of things (IoT) devices, which results in less latency, higher reliability, lower energy consumption and saving bandwidth resources. Using CDML, spare resources across decentralized IoT devices can be fully used to perform computation-intensive ML tasks collaboratively with high performance.
Recommendation ITU-T Y.4494 introduces CDML for intelligent IoT services, and provides the characteristics and reference architecture of CDML for intelligent IoT services.
Citation: https://handle.itu.int/11.1002/1000/15688
Series title: Y series: Global information infrastructure, Internet protocol aspects, next-generation networks, Internet of Things and smart cities
  Y.4000-Y.4999: Internet of things and smart cities and communities
  Y.4400-Y.4549: Frameworks, architectures and protocols
Approval date: 2023-11-29
Provisional name:Y.CDML-arc
Approval process:AAP
Status: In force
Maintenance responsibility: ITU-T Study Group 20
Further details: Patent statement(s)
Development history