|
Work item:
|
Y.ANC_Network
|
|
Subject/title:
|
AI Use Cases and pipeline node Characterization for IMT-2020 networks and beyond
|
|
Status:
|
Under study
|
|
Approval process:
|
Agreement
|
|
Type of work item:
|
Supplement
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2026-Q4 (Medium priority)
|
|
Liaison:
|
ITU-T SG20, 3GPP SA2
|
|
Supporting members:
|
India (Republic of), CDOT (India)
|
|
Summary:
|
This study focuses on analyzing AI-enabled use cases in IMT-2020 and beyond networks by mapping the functional pipeline nodes involved such as source, pre-processing, collector, AI model, and sink to their corresponding network entities. For each pipeline node, key characteristics related to computation, memory, storage, and data transfer are identified, highlighting the overheads introduced by AI procedures. By examining these AI pipeline node characteristics, the study provides insights into efficient task allocation, resource management, and the trade-offs between AI benefits and associated overheads, aiming to enhance overall network performance and reduce AI cost. This study underscores the need for some standardization actions to balance AI benefits against AI operational costs, ensuring that AI integration enhances rather than compromises the network performance.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2025-11-14 16:49:52
|
|
Last update:
2025-11-14 16:59:02
|
