基于时空相关性的卫星流量迁移预测

  • 焦阳 ,
  • 陆雨婷 ,
  • 欧阳键
展开
  • 南京邮电大学

收稿日期: 2024-07-12

  修回日期: 2024-09-10

  网络出版日期: 2024-09-18

基金资助

Transfer Prediction of Satellite Traffic Based on Spatiotemporal Correlation

  • JIAO Yang ,
  • LU Yu-Ting ,
  • LU Yu-Ting Yang-Jian
Expand

Received date: 2024-07-12

  Revised date: 2024-09-10

  Online published: 2024-09-18

Supported by

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的稳定运行,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着无法有效预测的问题。为此,本文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。仿真表明,所提方法可以有效预测目标卫星流量的动态变化。

本文引用格式

焦阳 , 陆雨婷 , 欧阳键 . 基于时空相关性的卫星流量迁移预测[J]. 航空学报, 0 : 0 -0 . DOI: 10.7527/S1000-6893.2024.30938

Abstract

Accurately predicting the traffic between satellites and ground users is crucial for the stable operation of the satellite in response to user demand and environmental changes, thus maintaining the 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, for the satellite traffic data, 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 effectively forecasts the dynamic changes in target satellite traffic.

参考文献

[1]安建平, 李建国, 于季弘, 等.空天通信网络关键技术综述[J].电子学报, 2022, 50(02):470-479
[2]AN J P, LI J G, YU J H, et al.A Survey on Key Tech-nologies of Aeronautical Communication Networks[J].Acta Electronica Sinica, 2022, 50(02):470-479
[3]GUO H, LI J, LIU J, et al.A Survey on Space-Air-Ground-Sea Integrated Network Security in 6G[J].IEEE Communications Surveys & Tutorials, 2022, 24(1):53-87
[4]喻思琪, 张小红, 郭斐, 等.卫星导航进近技术进展[J].航空学报, 2019, 40(03):16-37
[5]YU S Q, ZHANG X H, GUO F, et al.Advances in Satellite Navigation Approach Technology[J].Acta Aeronautica et Astronautica Sinica, 2019, 40(03):16-37
[6]H.AL-HRAISHAWI,HCHOUGRANI. A Survey on Nongeosta tionary Satellite Systems: The Communi-cation Perspective[J].IEEE Communications Surveys & Tutorials, 2023, 25(1):101-132
[7]YKAWAMOTO Y, TAKAHASHI M, VERMA S.Traf-fic-Pre diction-Based Dynamic Resource Control Strategy in HAPS-Mounted MEC-Assisted Satellite Communication Systems[J].IEEE Internet of Things Journal, 2024, 11(8):13824-13836
[8]ZHANG B, YUAN F W, BO Y Z, et al.Progress and Challenges in Intelligent Remote Sensing Satellite Systems[J]. IEEE Journal of Selected Topics in Ap-plied Earth Observations and Remote Sensing, 2022, 15:1814-1822.[J].IEEE Journal of Selected Topics in Applied Earth Ob-servations and Remote Sensing, 2022, 15:1814-1822
[9]康梦轩, 宋俊平, 范鹏飞, 等.基于深度学习的网络流量预测研究综述[J].计算机工程与应用, 2021, 57(10):1-9
[10]KANG M X, SONG J P, FAN P F, et al.A Review on Network Traffic Prediction Based on Deep Learning[J].Computer Engineering and Applications, 2021, 57(10):1-9
[11]SHEN W X, ZHANG H X, GUO S S, et al.Time-Wise Attention Aided Convolutional Neural Network for Data-Driven Cellular Traffic Prediction[J].IEEE Wireless Communications Letters, 2021, 10(8):1747-1751
[12]MA X, ZHENG B, JIANG G, et al.Cellular Network Traffic Prediction Based on Correlation ConvLSTM and Self-Attention Network[J].IEEE Communica-tions Letters, 2023, 27(7):1909-1912
[13]潘成胜, 王羽夫, 杨力.基于改进算法的天地一体化信息网络流量预测[J].天地一体化信息网络, 2020, 1(02):57-65
[14]PAN C S, WANG Y F, YANG L.Traffic Prediction in Integrated Space-Ground Information Networks Based on Improved LSTM Algorithm[J].Integrated Space-Ground Information Network, 2020, 1(02):57-65
[15]D.A. TEDJOPURNOMO,BAO Z,ZHENG B,et alA Survey on Modern Deep Neural Network for Traffic Prediction: Trends,Methods and Challenges[J].IEEE Transactions on Knowledge and Data Engineering, 2022, 34(4):1544-1561
[16]PAN S J, YANG Q.A Survey on Transfer Learning[J].IEEE Transactions on Knowledge and Data Engineer-ing, 2010, 22(10):1345-1359
[17]FU Z Z, ZHU Y Q, KE Y D, et al.A Comprehensive Survey on Transfer Learning[J].Proceedings of the IEEE, 2021, 109(1):43-76
[18]NIU S T, LIU M, LIU Y X, et al.Distant Domain Transfer Learning for Medical Imaging[J].IEEE Journal of Biomedical and Health Informatics, 2021, 25(10):3784-3793
[19]ZHANG K, LIU Q, OIAN H, et al.EATN: An Effi-cient Adaptive Transfer Network for Aspect-Level Sentiment Analysis[J] IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1):377-389.[J].IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1):377-389
[20]于功也, 蔡伟东, 胡明辉, 等.故障机理与领域自适应混合驱动的机械故障智能迁移诊断[J].航空学报, 2023, 44(02):321-332
[21]YU G Y, CAI W D, HU M H, et al.Intelligent Trans-fer Diagnosis of Mechanical Faults Driven by Fault Mechanism and Domain Adaptation[J].Acta Aero-nautica et Astronautica Sinica, 2023, 44(02):321-332
[22]XU L, LIU H, SONG J, et al.TransMUSE: Transfera-ble Traffic Prediction in MUlti-Service Edge Net-works[J]. Computer Networks, 2023, 221:109518.[J].Social Science Electronic Publishing, 2022, :-
[23]Hu D L, Chen L, Fang H X, Z.Fang,et alSpatio-Temporal Trajectory Similarity Measures: A Compre-hensive Survey and Quantitative Study[J].IEEE Transactions on Knowledge and Data Engineering, 2024, 36(5):2191-2212
[24]覃继前, 徐宁辉, 梁月吉.不同卫星高度角对融合定位的影响[J].全球定位系统, 2021, 46(02):62-68
[25]QIN J Q, XU N H, LIANG Y J.The Impact of Differ-ent Satellite Elevation Angles on GPSGLONASSBDSGalileo Integrated Positioning[J].Global Positioning Systems, 2021, 46(02):62-68
[26] SAKURAI Y, PAPADIMITRIOU S, FALOUTSOS C.BRAID: Stream mining through group lag correla-tions[C]//Acm Sigmod Conference.ACM, 2005.
[27] FAWAZ H I, FORESTIER G, WEBER J, et al.Trans-fer learning for time series classification[C]//IEEE In-ternational Conference on Big Data.IEEE, 2018:1367–1376.
[28]S.HOCHREITER,JSCHMIDHUBER. Long Short-Term Memory[J].Neural Computation, 1997, 9(8):1735-1780
[29]LINDEMANN B, MüLLER T, VIETZ H, JAZDI N, et al.A survey on long short-term memory networks for time series prediction[J]. Procedia CIRP, 2021, 99: 650-655.[J].Procedia CIRP, 2021, 99:650-655
[30] DAI W, YANG Q, XUE G-R, et al.Boosting for transfer learning[C]//Proceedings of the 24th interna-tional conference on Machine learning Corvalis Ore-gon USA:ACM, 2007:193-200.
文章导航

/