航空学报 > 2025, Vol. 46 Issue (4): 330938-330938   doi: 10.7527/S1000-6893.2024.30938

基于时空相关性的卫星流量迁移预测

焦阳1, 陆雨婷1, 许拔2, 欧阳键1()   

  1. 1.南京邮电大学 通信与信息工程学院,南京 210003
    2.国防科技大学 第六十三研究所,南京 210007
  • 收稿日期:2024-07-12 修回日期:2024-08-05 接受日期:2024-09-02 出版日期:2024-09-19 发布日期:2024-09-18
  • 通讯作者: 欧阳键 E-mail:ouyangjian@njupt.edu.cn
  • 基金资助:
    基础加强计划技术领域基金(2019-JCJQ-JJ-226)

Transfer prediction of satellite traffic based on spatiotemporal correlation

Yang JIAO1, Yuting LU1, Ba XU2, Jian OUYANG1()   

  1. 1.School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China
    2.Sixty-third Research Institute,National University of Defense Technology,Nanjing 210007,China
  • Received:2024-07-12 Revised:2024-08-05 Accepted:2024-09-02 Online:2024-09-19 Published:2024-09-18
  • Contact: Jian OUYANG E-mail:ouyangjian@njupt.edu.cn
  • Supported by:
    Basic Strengthening Plan Technology Field Fund Project(2019-JCJQ-JJ-226)

摘要:

准确预测卫星与地面用户之间的流量可确保卫星在面对用户需求和环境动态变化时稳定运行,从而保障卫星通信系统的高效运作。传统机器学习方法在预测目标卫星流量时需要拥有充足的历史样本数据。然而,面对节假日大规模人口流动引起的不同卫星服务区域之间的流量潮汐现象,传统机器学习方法由于缺乏目标卫星流量潮汐历史数据存在无法有效预测的问题。为此,提出了一种基于时空相关性的卫星流量迁移预测方法,该方法首先利用角度条件识别空间上的邻近卫星,并通过计算时滞Pearson相关系数量化不同卫星之间流量的时空相关性,进而构建源卫星流量数据集。其次,利用共有模式学习器动态调整源卫星流量数据集中各流量样本的迁移权重,并采用基于加权迁移的长短期记忆网络优化迁移学习过程,提升迁移模型对目标卫星流量的预测能力。仿真结果表明,所提方法可以有效预测目标卫星流量的动态变化。

关键词: 卫星流量预测, 迁移学习, 时空相关性, 长短期记忆网络, 流量潮汐

Abstract:

Accurately predicting the traffic between satellites and ground users is crucial for stable operation of the satellite in response to changes of user demand and environment, thus maintaining efficient performance of the satellite communication system. Traditional machine learning methods require ample historical sample data to predict the traffic of target satellites. However, during major holidays, large-scale population movements can create tidal phenomena in traffic between different satellite service areas. Traditional methods struggle to address this issue due to the absence of historical tidal data specific to the target satellites. To address this issue, this paper presents a satellite traffic migration prediction method based on spatiotemporal correlation. The method initially identifies spatially adjacent satellites using angular conditions and quantifies the spatiotemporal correlation of traffic between different satellites by calculating the time-lagged Pearson correlation coefficient, thereby constructing a source satellite traffic dataset. Subsequently, a common pattern learner is used to dynamically adjust the transfer weights of traffic samples in the source domain dataset. A weighted transfer long short-term memory network is then employed to optimize the transfer learning process, enhancing the model’s ability to predict traffic for the target satellite. Simulations demonstrate that the proposed method can effectively forecast dynamic changes in target satellite traffic.

Key words: satellite traffic prediction, transfer learning, spatiotemporal correlation, LSTM, traffic tides

中图分类号: