|
Work item:
|
Y.bDDN-ENTPM
|
|
Subject/title:
|
Big data driven networking -Evaluation of network traffic prediction model
|
|
Status:
|
Under study
|
|
Approval process:
|
AAP
|
|
Type of work item:
|
Recommendation
|
|
Version:
|
New
|
|
Equivalent number:
|
-
|
|
Timing:
|
2027-11 (Medium priority)
|
|
Liaison:
|
IETF OPS
|
|
Supporting members:
|
China Information Communication Technologies Group, Peng Cheng Laboratory, Hubei University
|
|
Summary:
|
A network traffic prediction model is a computational model that uses statistical methods, machine learning, or deep learning techniques to estimate and forecast future network traffic trends, volumes, anomalies and etc., based on historical traffic data. Network traffic prediction model plays a crucial role in bDDN and network intelligence, and it is the core in network management and operation for future networks. Network traffic prediction models are key technologies for achieving network traffic prediction using AI technology. Currently, there are many types of models in the industry. Therefore, how to evaluate a network traffic prediction model and how to select a good model are very critical issues. This work item specifies the evaluation framework of network traffic prediction model, and functional evaluation, performance evaluation, robustness evaluation and cost-effectiveness evaluation of network traffic prediction model.
|
|
Comment:
|
-
|
|
Reference(s):
|
|
|
Historic references:
|
|
Contact(s):
|
|
| ITU-T A.5 justification(s): |
|
|
|
|
First registration in the WP:
2025-07-30 14:10:51
|
|
Last update:
2025-07-30 14:12:16
|
