Cellular Traffic Prediction Based on CVAE and Transformer

Jianwu Li*, Yiguang Liu*, Qingyao Liu, Zhixiao Ni*, Bin Liu, Mingyue Qi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationICNC-FSKD 2024 - 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery
EditorsMaozhen Li, Ning Xiong, Jianguo Chen, Zheng Xiao, Kenli Li, Lipo Wang
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350356328
DOIs
Publication statusPublished - 2024
Event20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024 - Guangzhou, China
Duration: 27 Jul 202429 Jul 2024

Publication series

NameICNC-FSKD 2024 - 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

Conference

Conference20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2024
Country/TerritoryChina
CityGuangzhou
Period27/07/2429/07/24

Fingerprint

Dive into the research topics of 'Cellular Traffic Prediction Based on CVAE and Transformer'. Together they form a unique fingerprint.

Cite this