LSTM-based throughput prediction for LTE networks

被引：9
|
作者：
Na, Hyeonjun [1 ]
Shin, Yongjoo [2 ]
Lee, Dongwon [2 ]
Lee, Joohyun [2 ]
机构：
[1] Hanyang Univ, Dept Appl Artificial Intelligence, Ansan, South Korea
[2] Hanyang Univ, Dept Elect & Elect Engn, Ansan, South Korea
来源：
ICT EXPRESS | 2023年 / 9卷 / 02期
关键词：
Machine learning; Deep learning; Throughput prediction; LSTM; Attention method; REGRESSION;
D O I：
10.1016/j.icte.2021.12.001
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Throughput prediction is crucial for reducing latency in time-critical services. We study the attention-based LSTM model for predicting future throughput. First, we collected the TCP logs and throughputs in LTE networks and transformed them using CUBIC and BBR trace log data. Then, we use the sliding window method to create input data for the prediction model. Finally, we trained the LSTM model with an attention mechanism. In the experiment, the proposed method shows lower normalized RMSEs than the other method.(c) 2021 The Author(s). Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
引用
收藏
页码：247 / 252
页数：6
相关论文
共 50 条
  • [31] BE-LSTM: An LSTM-based framework for feature selection and building electricity consumption prediction on small datasets
    Wang, Weihao
    Shimakawa, Hajime
    Jie, Bo
    Sato, Masahiro
    Kumada, Akiko
    JOURNAL OF BUILDING ENGINEERING, 2025, 102
  • [32] LSTM-based Service Migration for Pervasive Cloud Computing
    Jing, Haifeng
    Zhang, Yafei
    Zhou, Jiehan
    Zhang, Weishan
    Liu, Xin
    Min, Guizhi
    Zhang, Zhanmin
    IEEE 2018 INTERNATIONAL CONGRESS ON CYBERMATICS / 2018 IEEE CONFERENCES ON INTERNET OF THINGS, GREEN COMPUTING AND COMMUNICATIONS, CYBER, PHYSICAL AND SOCIAL COMPUTING, SMART DATA, BLOCKCHAIN, COMPUTER AND INFORMATION TECHNOLOGY, 2018, : 1835 - 1840
  • [33] Dynamic Sliding Window and Neighborhood LSTM-Based Model for Stock Price Prediction
    Giang Thi Thu H.
    Nguyen Thanh T.
    Le Quy T.
    SN Computer Science, 2022, 3 (3)
  • [34] Ventilation prediction for ICU patients with LSTM-based deep relative risk model
    Liu, Bin
    Yin, Guosheng
    DEVELOPMENTS OF ARTIFICIAL INTELLIGENCE TECHNOLOGIES IN COMPUTATION AND ROBOTICS, 2020, 12 : 979 - 986
  • [35] LSTM-Based Path Prediction for Effective Sensor Filtering in Sensor Registry System
    Chen, Haotian
    Lee, Sukhoon
    On, Byung-Won
    Jeong, Dongwon
    SENSORS, 2021, 21 (23)
  • [36] RevOPT: An LSTM-based Efficient Caching Strategy for CDN
    Ben-Ammar, Hamza
    Ghamri-Doudane, Yacine
    2021 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2021,
  • [37] OneHotEncoding and LSTM-based deep learning models for protein secondary structure prediction
    Enireddy, Vamsidhar
    Karthikeyan, C.
    Babu, D. Vijendra
    SOFT COMPUTING, 2022, 26 (08) : 3825 - 3836
  • [38] LSTM-based Automatic Modulation Classification
    Zhou, Quan
    Jing, Xiaojun
    He, Yuan
    Cui, Yuanhao
    Kadoch, Michel
    Cheriet, Mohamed
    2020 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB), 2020,
  • [39] Construction and Application of LSTM-Based Prediction Model for Tunnel Surrounding Rock Deformation
    He, Yongchao
    Chen, Qiunan
    SUSTAINABILITY, 2023, 15 (08)
  • [40] Microwave Link Failures Prediction via LSTM-based Feature Fusion Network
    Ruan, Zichan
    Yang, Shuiqiao
    Pan, Lei
    Ma, Xingjun
    Luo, Wei
    Grobler, Marthie
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
12345