{"title":"Time-varying Millimeter Wave Channel Modeling Based on LSTM","authors":"Lujia Yu, Fei Du, Xiongwen Zhao, S. Geng","doi":"10.1109/EEI59236.2023.10212937","DOIUrl":null,"url":null,"abstract":"In order to improve the accuracy of time-varying channel modeling, it is necessary not only to identify and analyze the channel features at each moment, but also to track the evolution of the channel features over time. The cluster-based channel model conforms to characteristics of the physical channel, and can balance the complexity and accuracy of the model. Therefore, a trajectory prediction model based on Long Short Term Memory (LSTM) for multipath component (MPC) clusters in time-varying millimeter wave channels is proposed. Specifically, after a clustering algorithm used to identify the MPC clusters, Kuhn-munkres (KM) algorithm is applied to identify the moving trajectories of the MPC clusters, and finally LSTM is established to predict and track the moving trajectories of the clusters. The performance of the proposed algorithm is verified by the simulated channel data, and cluster-based channel model of 5G time-varying millimeter wave can be established accurately.","PeriodicalId":363603,"journal":{"name":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 5th International Conference on Electronic Engineering and Informatics (EEI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/EEI59236.2023.10212937","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In order to improve the accuracy of time-varying channel modeling, it is necessary not only to identify and analyze the channel features at each moment, but also to track the evolution of the channel features over time. The cluster-based channel model conforms to characteristics of the physical channel, and can balance the complexity and accuracy of the model. Therefore, a trajectory prediction model based on Long Short Term Memory (LSTM) for multipath component (MPC) clusters in time-varying millimeter wave channels is proposed. Specifically, after a clustering algorithm used to identify the MPC clusters, Kuhn-munkres (KM) algorithm is applied to identify the moving trajectories of the MPC clusters, and finally LSTM is established to predict and track the moving trajectories of the clusters. The performance of the proposed algorithm is verified by the simulated channel data, and cluster-based channel model of 5G time-varying millimeter wave can be established accurately.