[bmwg] Re: New Version Notification for draft-zhuang-ippm-network-measurement-ps-00.txt

[庄瑞 <[e-mail]>]

Dear All,I would like to draw your attention to a new draft that has recently been submitted: I-D draft-zhuang-ippm-network-measurement-ps-00.The draft presents a problem statement and gap analysis for network measurement in modern high‑speed, large‑scale, and distributed environments. As network applications such as AI/ML training and cloud services demand adaptive, high‑performance infrastructure, network measurement becomes essential for traffic engineering, load balancing, congestion control, resource accounting, and fault diagnosis. However, existing prevalent measurement techniques, including sketch‑based measurement, in‑band network telemetry, sampling‑based measurement, and probing‑based measurement, each face limitations in accuracy, overhead, scalability, and adaptability. The draft analyses these limitations and further highlights the unique challenges introduced by distributed systems.




The goal of this draft is to articulate the pressing issues that prevent current solutions from meeting the demands of modern networks, thereby encouraging the development of more effective measurement systems.




The draft is available here: https://datatracker.ietf.org/doc/draft-zhuang-ippm-network-measurement-ps/




We welcome your comments, suggestions, and discussions -- especially any insights on additional problem scenarios, practical deployment experiences, or potential approaches that could address the identified gaps.




Best regards,

Zhuang








----邮件原文---- 发件人：internet-drafts 

收件人：Rui Zhuang ,Tong Yang ,Weiqiang Cheng ,Xiaobai Chen 

抄　送: (无) 
发送时间：2026-07-06 12:16:11 
Subject：New Version Notification for draft-zhuang-ippm-network-measurement-ps-00.txt


A new version of Internet-Draft 
draft-zhuang-ippm-network-measurement-ps-00.txt has been successfully 
submitted by Rui Zhuang and posted to the 
IETF repository. 


 Name: draft-zhuang-ippm-network-measurement-ps 
Revision: 00 
Title: Network Measurement Problem Statement 
Date: 2026-07-06 
Group: Individual Submission 
Pages: 12 
URL: https://www.ietf.org/archive/id/draft-zhuang-ippm-network-measurement-ps-00.txt 
Status: https://datatracker.ietf.org/doc/draft-zhuang-ippm-network-measurement-ps/ 
HTML: https://www.ietf.org/archive/id/draft-zhuang-ippm-network-measurement-ps-00.html 
HTMLized: https://datatracker.ietf.org/doc/html/draft-zhuang-ippm-network-measurement-ps 


Abstract: 
Modern network applications, ranging from artificial intelligence 
(AI) and machine learning (ML) training to large-scale 
cloud
 services, require adaptive and high-performance networks. Network 
measurement is fundamental to achieving observability, enabling 
traffic engineering (TE), load balancing, congestion control (CC),
resource accounting, and fault diagnosis. However, existing network
measurement techniques face significant challenges in accuracy,
overhead, scalability, and adaptability, especially in distributed
and high-speed environments. This document describes the problems
and gaps in current network measurement approaches, including sketch-
based measurement, in-band network telemetry (INT), sampling, and
probing, with a focus on distributed system scenarios.






The IETF Secretariat