面向通信感知计算一体化网络业务的用户体验质量估计  

Quality of Experience Estimation for Communication-Sensing-Computation Integrated Network Services

作　　者：邓胜超 高晖 粟欣[3] 刘蓓[3] DENG Shengchao;GAO Hui;SU Xin;LIU Bei(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;School of Information and Communication Engineering,Beying University of Posts and Telecommunications,Beying 100876,China;Beijing National Research Center for Information Science and Technology,Tsinghua University,Beijing 100084,China)

机构地区：[1]重庆邮电大学通信与信息工程学院,重庆400065 [2]北京邮电大学信息与通信工程学院,北京100876 [3]清华大学北京信息科学与技术国家研究中心,北京100084

出　　处：《移动通信》2023年第3期67-72,共6页Mobile Communications

基　　金：国家重点研发计划资助项目(2020YFB1806702)。

摘　　要：未来的6G网络有望成为集感知、通信和计算为一体的通感算一体化网络,以满足各种新型业务的极致化需求。用户体验质量将成为网络运维管理的关注重点。因此,提出并设计了一种新的QoE估计方法。首先,应用机器学习算法构建KPI与QoE关联性分析模型。其次,根据关联性分析结果搭建深度神经网络利用KPI实现QoE估计。最后,仿真结果表明所提方法在估计用户体验质量方面具有很高的准确性。The future 6G network is expected to become a communication-sensing-computation integrated network of to meet the extreme requirements of various emerging businesses. Quality of experience(QoE) will become the focus of network operation and maintenance management. Therefore, a novel QoE estimation method is proposed and designed. First of all, the machine learning algorithm is utilized to build the correlation analysis model between KPI and QoE. Secondly, according to the results of correlation analysis, a deep neural network is built to realize QoE estimation with KPI. Finally, the simulation results show that the proposed method has high accuracy in QoE estimation.

关 键 词：用户体验质量 机器学习 深度学习 通信感知计算一体化 

分 类 号：TN919.8[电子电信—通信与信息系统]