A self-attention sequential model for long-term prediction of video streams

被引:0
|
作者
Ge, Yunfeng [1 ]
Li, Hongyan [1 ]
Shi, Keyi [1 ]
机构
[1] School of Telecommunications Engineering, Xidian University, Xi'an,710071, China
关键词
D O I
10.19665/j.issn1001-2400.20240202
中图分类号
学科分类号
摘要
Video traffic prediction is a key technology to achieve accurate transmission bandwidth allocation and improve the quality of the Internet service. However, the inherent high rate variability, long-term dependence and short-term dependence of video traffic make it difficult to make a quick, accurate and long- term prediction:because existing models for predicting sequence dependencies have a high complexity and prediction models fail quickly. Aiming at the problem of long-term prediction of video streams, a sequential self-attention model with frame structure feature embedding is proposed. The sequential self-attention model has a strong modeling ability for the nonlinear relationship of discrete data. Based on the difference of correlation between video frames, this paper applies the time series self-attention model to the long-term prediction of video traffic for the first time. The existing time series self-attention model cannot effectively represent the category features of video frames. By introducing an embedding layer based on the frame structure, the frame structure information is effectively embedded into the time series to improve the accuracy of the model. The results show that, compared with the existing long short-term memory network model and convolutional neural network model, the proposed sequential self-attention model based on frame structure feature embedding has a fast inference speed, and that the prediction accuracy is reduced by at least 32% in the mean absolute error. © 2024 ournal of Xidian University. All Rights Reserved.
引用
收藏
页码:88 / 102
相关论文
共 50 条
  • [1] Sequential Recommendation Based on Long-Term and Short-Term User Behavior with Self-attention
    Wei, Xing
    Zuo, Xianglin
    Yang, Bo
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, KSEM 2019, PT I, 2019, 11775 : 72 - 83
  • [2] Sequential Prediction of Glycosylated Hemoglobin Based on Long Short-Term Memory with Self-Attention Mechanism
    Wang, Xiaojia
    Gong, Wenqing
    Zhu, Keyu
    Yao, Lushi
    Zhang, Shanshan
    Xu, Weiqun
    Guan, Yuxiang
    INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2020, 13 (01) : 1578 - 1589
  • [3] Sequential Prediction of Glycosylated Hemoglobin Based on Long Short-Term Memory with Self-Attention Mechanism
    Xiaojia Wang
    Wenqing Gong
    Keyu Zhu
    Lushi Yao
    Shanshan Zhang
    Weiqun Xu
    Yuxiang Guan
    International Journal of Computational Intelligence Systems, 2020, 13 : 1578 - 1589
  • [4] Enhanced Self-Attention Mechanism for Long and Short Term Sequential Recommendation Models
    Zheng, Xiaoyao
    Li, Xingwang
    Chen, Zhenghua
    Sun, Liping
    Yu, Qingying
    Guo, Liangmin
    Luo, Yonglong
    IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024, 8 (03): : 2457 - 2466
  • [5] Long- and short-term self-attention network for sequential recommendation
    Xu, Chengfeng
    Feng, Jian
    Zhao, Pengpeng
    Zhuang, Fuzhen
    Wang, Deqing
    Liu, Yanchi
    Sheng, Victor S.
    NEUROCOMPUTING, 2021, 423 : 580 - 589
  • [6] SALSTM: segmented self-attention long short-term memory for long-term forecasting
    Dai, Zhi-Qiang
    Li, Jie
    Cao, Yang-Jie
    Zhang, Yong-Xiang
    JOURNAL OF SUPERCOMPUTING, 2025, 81 (01):
  • [7] Reliable Long-Term Energy Load Trend Prediction Model for Smart Grid Using Hierarchical Decomposition Self-Attention Network
    Zhan, Xianghao
    Kou, Liang
    Xue, Meiting
    Zhang, Jilin
    Zhou, Li
    IEEE TRANSACTIONS ON RELIABILITY, 2023, 72 (02) : 609 - 621
  • [8] Spatiotemporal module for video saliency prediction based on self-attention
    Wang, Yuhao
    Liu, Zhuoran
    Xia, Yibo
    Zhu, Chunbo
    Zhao, Danpei
    IMAGE AND VISION COMPUTING, 2021, 112
  • [9] Aero-engine remaining useful life prediction based on a long-term channel self-attention network
    Xuezhen Liu
    Yongyi Chen
    Hongjie Ni
    Dan Zhang
    Signal, Image and Video Processing, 2024, 18 (1) : 637 - 645
  • [10] Aero-engine remaining useful life prediction based on a long-term channel self-attention network
    Liu, Xuezhen
    Chen, Yongyi
    Ni, Hongjie
    Zhang, Dan
    SIGNAL IMAGE AND VIDEO PROCESSING, 2024, 18 (01) : 637 - 645