@inproceedings{5e00b901eb8b423d8d72d20e9219ad93,
title = "Cellular Traffic Prediction Based on CVAE and Transformer",
abstract = "Cellular traffic prediction is an important problem in the field of communication management. In this paper, a cellular traffic prediction method CTSTN based on spatio-temporal learning is designed combining Transformer and Conditional Variational Auto-Encoder (CVAE). This paper explores the application of CVAE in the spatial states modeling and generating of cellular traffic data, constructs a spatial states dataset from the raw dataset, and designs an S-CVAE module to learn spatial characteristics of traffic data. Meanwhile, the Transformer is used to model temporal features of cellular traffic data. We conduct experiments and analyses on CTSTN and its sub-modules on real datasets. The results show the effectiveness of applying CVAE to spatial status prediction and validate the accuracy of CTSTN predictions.",
author = "Jianwu Li and Yiguang Liu and Qingyao Liu and Zhixiao Ni and Bin Liu and Mingyue Qi",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024 ; Conference date: 27-07-2024 Through 29-07-2024",
year = "2024",
doi = "10.1109/ICNC-FSKD64080.2024.10702233",
language = "English",
series = "ICNC-FSKD 2024 - 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
editor = "Maozhen Li and Ning Xiong and Jianguo Chen and Zheng Xiao and Kenli Li and Lipo Wang",
booktitle = "ICNC-FSKD 2024 - 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery",
address = "United States",
}