上海大学通信与信息工程学院;中兴通信股份有限公司;移动网络和移动多媒体技术国家重点实验室;
工业控制场景下5G-A终端传输时延是确定性网络能力的直接表征之一，时延预测对提高网络确定性至关重要。由于传输时延序列的不稳定性和随机性，单一模型难以准确预测。针对该问题，提出一种基于优化变分模态分解(Variational Mode Decomposition, VMD)和卷积注意力长短时记忆网络(Convolutional Attention Long Short Term Memory Network, CA-LSTM)的传输时延预测方法。为提高VMD的分解性能，利用相关系数检验法确定时延序列分解的模态数，并利用蝗虫优化寻优分解的惩罚因子和保真度系数；设计CA-LSTM网络，借助卷积滤波器以及注意力机制使得网络具备分辨时延特征重要程度的能力；将各模态预测值重建成一维时延值得到预测结果。实验研究结果表明，优化VDM能够将5G终端传输时延序列有效分解，结合CA-LSTM模型相比于经典LSTM在MSE、RMSE和MAE上分别提升了37.1%、21.3%和23.6%。
| 224 | 1 | 18 |
| 下载次数 | 被引频次 | 阅读次数 |
[1] 艾渤，马国玉，钟章队.智能高铁中的 5G 技术及应用[J].中兴通信技术，2019,25(6):42-47.
[2] KOKKONIEMI-TARKKANEN H,HORSMANHEIMO S,GRUDNITSKY A,et al.Enabling Safe Wireless Harbor Automation via 5G URLLC[C]//2019 IEEE 2nd 5G World Forum (5GWF).Dresden:IEEE,2019:403-408.
[3] BAGHERI H,NOOR-A-RAHIM M,LIU Z L,et al.5G NR-V2X:Toward Connected and Cooperative Autonomous Driving[J].IEEE Communications Standards Magazine,2021,5(1):48-54.
[4] ZHANG X M,HAN Q L,GE X H,et al.Networked Control Systems:A Survey of Trends and Techniques[J].IEEE/CAA Journal of Automatica Sinica,2020,7(1):1-17.
[5] YUAN H T,BI J,ZHOU M C,et al.Time-aware Multi-application Task Scheduling with Guaranteed Delay Constraints in Green Data Center[J].IEEE Transactions on Automation Science and Engineering,2018,15(3):1138-1151.
[6] BI J,FENG T Z,YUAN H T.Real-time and Short-term Anomaly Detection for GWAC Light Curves[J].Computers in Industry,2018,97:76-84.
[7] BI J,YUAN H T,ZHOU M C.Temporal Prediction of Multiapplication Consolidated Workloads in Distributed Clouds[J].IEEE Transactions on Automation Science and Engineering,2019,16(4):1763-1773.
[8] BI J,YUAN H T,ZHANG L B,et al.SGW-SCN:An Integrated Machine Learning Approach for Workload Forecasting in Geo-distributed Cloud Data Centers[J].Information Sciences,2019,481:57-68.
[9] KANG Q,SHI L,ZHOU M C,et al.A Distance-based Weighted Undersampling Scheme for Support Vector Machines and Its Application to Imbalanced Classification[J].IEEE Transactions on Neural Networks and Learning Systems,2017,29(9):4152-4165.
[10] YU P F,YAN X S.Stock Price Prediction Based on Deep Neural Networks[J].Neural Computing and Applications,2020,32(6):1609-1628.
[11] TIAN Z D.A Method to Predict Random Time-delay of Networked Control System[J].IETE Journal of Research,2020,68(5):3503-3513.
[12] BI J,ZHANG L B,YUAN H T,et al.Hybrid Task Prediction Based on Wavelet Decomposition and ARIMA Model in Cloud Data Center[C]//2018 IEEE 15th International Conference on Networking,Sensing and Control (ICNSC).Zhuhai:IEEE,2018:1-6.
[13] 戴婷，张榆锋，章克信，等.经验模态分解及其模态混叠消除的研究进展[J].电子技术应用，2019,45 (3):7-12.
[14] 赵斯琪，李松松，栾明慧，等.基于集合经验模态分解的超声检测信号处理[J].无损检测，2021,43(5):16-23.
[15] 吴龙文，聂雨亭，张宇鹏，等.基于变分模态分解的自适应滤波降噪方法[J].电子学报，2021,49(8):1457-1465.
[16] DRAGOMIRETSKIY K,ZOSSO D.Variational Mode Decomposition[J].IEEE Transactions on Signal Processing,2013,62(3):531-544.
[17] ALGAMAL Z Y,QASIM M K,LEE M H,et al.Improving Grasshopper Optimization Algorithm for Hyperparameters Estimation and Feature Selection in Support Vector Regression[J].Chemometrics and Intelligent Laboratory Systems,2021,208:104196.
[18] LANDI F,BARALDI L,CORNIA M,et al.Working Memory Connections for LSTM[J].Neural Networks,2021,144:334-341.
[19] SHON S,HA J H,POKHREL B P,et al.Intrinsic Mode Function and Its Orthogonality of the Ensemble Empirical Mode Decomposition Using Orthogonalization Method[J].Journal of the Korean Association for Spatial Structures,2019,19(2):101-108.
基本信息:
DOI：
中图分类号:TN929.5
引用信息:
[1]刘壮,盛志超,魏浩等.确定性网络5G-A终端时延预测[J].无线电工程,2024,54(04):1034-1042.
基金信息:
国家自然科学基金（61901254）; 航空科学基金（2020Z0660S6001）~~