公开(公告)号：US11856424B2

公开(公告)日：2023-12-26

申请号：US17345273

申请日：2021-06-11

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Guojun Ye ,  Bo Cheng ,  Xi Li

IPC: H04W16/22 ,  H04W24/06 ,  G06N3/04 ,  G06N3/08 ,  H04L41/14

CPC classification number: H04W24/06 ,  G06N3/04 ,  G06N3/08 ,  H04L41/145 ,  H04W16/22

Abstract: A method for creating a network simulation platform that has a first black box model, includes: obtaining a candidate network performance indicator and feature information related to the candidate network performance indicator, where the feature information related to the candidate network performance indicator refers to a part or all of feature information needed to obtain the candidate network performance indicator; and training a machine learning model to obtain the first black box model, where an output parameter of the first black box model is the candidate network performance indicator, input parameters of the first black box model are the feature information related to the candidate network performance indicator, and the first black box model is used to simulate the candidate network performance indicator. The solutions provided help reduce simulation complexity and are applicable to large-scale network simulation.