|
Work item:
|
F.748.83 (ex F.VIS-FML)
|
|
Subject/title:
|
Requirements and framework of visual inspection system based on federated machine learning in smart grid
|
|
Status:
|
Determined on 2026-07-17 [Issued from previous study period]
|
|
Approval process:
|
TAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2026 (Medium priority)
|
|
Liaison:
|
ITU-T SG17; IEEE Power & Energy Society; ISO/IEC JTC 1/SC 42
|
|
Supporting members:
|
STATE GRID of China, MIIT, China Telecom, Nokia, Zhejiang Lab
|
|
Summary:
|
AI-powered visual analysis is extensively adopted in smart grid visual inspection systems. However, centralized model development is impeded by privacy concerns, high costs of visual data transmission, and the shortage of sufficient labeled data, particularly for fault detection tasks. Federated machine learning addresses these challenges by allowing participants to train models locally on their own data, thus avoiding the need to share raw visual data (preserving privacy) and reducing costly data transmission, while simultaneously aggregating knowledge from distributed datasets to compensate for data scarcity and improve model performance. This Recommendation specifies a comprehensive framework and detailed requirements for deploying federated machine learning in smart grid visual inspection systems.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2024-06-24 10:09:01
|
|
Last update:
2026-08-04 11:08:12
|
