LSTM循环神经网络的高速铁路越区切换算法

doi:10.19665/j.issn1001-2400.2023.01.009

摘要/Abstract

摘要：

在高速铁路列车运行过程中,为了保持不中断通信,列车需要不断地与基站进行越区切换。越区切换作为LTE-R通信的关键技术,对于保障行车安全至关重要。针对下一代高速铁路无线通信LTE-R系统越区切换算法,因迟滞门限参数固定而导致切换成功率低等问题,提出了一种基于长短期记忆循环神经网络的高速铁路越区切换算法。首先,利用长短期记忆神经网络的记忆特性以及高速铁路越区切换重叠区信号时空相关性的特点,构建了基于长短期记忆循环神经网络的越区切换迟滞门限参数动态预测深度学习网络;其次,通过提出的长短期记忆深度学习模型,对越区切换迟滞参数进行线下训练和线上预测来获取未来时刻的切换门限值,实现了对越区切换迟滞参数的自适应预测,克服了迟滞门限参数固定的缺点;最后,通过仿真实验的结果表明,所提基于长短期记忆循环神经网络的高速铁路越区切换算法较其他比较方法能够有效地提高越区切换的成功率,并降低乒乓切换率的影响。

关键词: 越区切换, 铁路长期演进通信系统, 长短期记忆循环神经网络, 切换预测, 高速铁路

Abstract:

In the process of high-speed railway train operation,in order to maintain uninterrupted communication,the train needs to constantly carry out handover with the base station.As a key technology of LTE-R communication,handover is crucial to ensuring traffic safety.Aiming at the low success rate of handover in the next generation high-speed railway LTE-R wireless communication system due to the fixed hysteresis threshold parameters,a high-speed railway handover algorithm based on the LSTM recurrent neural network is proposed.First,by using the memory characteristics of the LSTM neural network and the temporal and spatial correlation characteristics of high-speed railway handover overlapping area signals,a deep learning network for dynamic prediction of handover hysteresis threshold parameters based on the LSTM recurrent neural network is constructed.Second,through the proposed LSTM deep learning model,the handover hysteresis parameters are trained offline and predicted online to obtain the handover threshold value at the future time,which realizes the adaptive prediction of handover hysteresis parameters during high-speed train driving,and overcomes the disadvantage of fixed hysteresis threshold parameters.Finally,simulation results show that the proposed method can effectively improve the handover success rate and reduce the impact of the ping-pong handover rate compared with the traditional A3 algorithm and other comparison algorithms.Research results provide a certain theoretical reference for high-speed railway traffic safety and LTE-R evolution.

Key words: handover, long-term evolution for railway, LSTM recurrent neural network, handover prediction, high-speed railway

中图分类号:

TP391

陈永,牛凯玉,康婕. LSTM循环神经网络的高速铁路越区切换算法[J]. 西安电子科技大学学报, 2023, 50(1): 76-84.

CHEN Yong,NIU Kaiyu,KANG Jie. Handover algorithm for a high-speed railway based on the LSTM recurrent neural network[J]. Journal of Xidian University, 2023, 50(1): 76-84.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

图13

图14

参考文献 23

[1]	CAI X, WU C, SHENG J, et al. Spectrum Situation Awareness Based on Time-Series Depth Networks for LTE-R Communication System[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 7:1-12. doi: 10.1109/TITS.2005.858624
[2]	熊杰. 我国铁路下一代移动通信系统制式及演进探讨[J]. 西南交通大学学报, 2018, 53(5):879-885.
	XIONG Jie. Standardisation and Evolution of Next Generation Railway Mobile Communication Systems in China[J]. Journal of Southwest Jiaotong University, 2018, 53(5):879-885.
[3]	MOLLEL M S, ABUBAKAR A L, OZTURK M, et al. A Survey of Machine Learning Applications to Handover Management in 5G and Beyond[J]. IEEE Access, 2021, 9:45770-45802. doi: 10.1109/ACCESS.2021.3067503
[4]	崔恩杰. 高铁无线通信系统越区切换优化研究[D]. 西安: 长安大学, 2021.
[5]	HUSSAIN S M, YUSOF K M, ASUNCION R, et al. Artificial Intelligence Based Handover Decision and Network Selection in Heterogeneous Internet of Vehicles[J]. Indonesian Journal of Electrical Engineering and Computer Science, 2021, 22(2):1124-1134. doi: 10.11591/ijeecs.v22.i2
[6]	DA COSTA SILVA K, BECVAR Z, FRANCES C R L. Adaptive Hysteresis Margin Based on Fuzzy Logic for Handover in Mobile Networks with Dense Small Cells[J]. IEEE Access, 2018, 6:17178-17189. doi: 10.1109/ACCESS.2018.2811047
[7]	WEI W, LIU X J, LI Y. Research on the Handover for Urban Rail Transit Based on IGM-BP Algorithm[J]. Journal of Physics Conference Series, 2020, 1550:1-7.
[8]	LEE C, CHO H, SONG S, et al. Prediction-Based Conditional Handover for 5G mm-Wave Networks:A Deep-Learning Approach[J]. IEEE Vehicular Technology Magazine, 2020, 15(1):54-62. doi: 10.1109/MVT.10209
[9]	BANG J, OH S, KANG K, et al. A Bayesian Regression-Based LTE-R Handover Decision Algorithm for High-Speed Railway Systems[J]. IEEE Transactions on Vehicular Technology, 2019, 68(10):10160-10173. doi: 10.1109/TVT.25
[10]	WU C, CAI X, SHENG J, et al. Parameter Adaptation and Situation Awareness of LTE-R Handover for High-Speed Railway Communication[J]. IEEE Transactions on Intelligent Transportation Systems, 2020, 99:1-15.
[11]	MASRI A, VEIJALAINEN T, MARTIKAINEN H, et al. Machine-Learning-Based Predictive Handover[C]// 2021 IFIP/IEEE International Symposium on Integrated Network Management.Piscataway:IEEE, 2021:648-652.
[12]	李立华. 高铁环境下LTE系统切换技术的研究[D]. 成都: 西南交通大学, 2018.
[13]	刘云毅. 面向高速铁路环境的LTE-R越区切换技术研究[D]. 北京: 北京交通大学, 2018.
[14]	KURRI V, RAJA V, PRAKASAM P. Cellular Traffic Prediction on Blockchain-Based Mobile Networks Using LSTM Model in 4G LTE Network[J]. Peer-to-Peer Networking and Applications, 2021, 14(3):1088-1105. doi: 10.1007/s12083-021-01085-7
[15]	张春祥, 周雪松, 高雪瑶. 融合k均值聚类与LSTM网络的半监督词义消歧[J]. 西安电子科技大学学报, 2021, 48(6):161-171.
	ZHANG Chunxiang, ZHOU Xuesong, GAO Xueyao. Semi-Supervised Word Sense Disambiguation by Combining k-Means Clustering and the LSTM Network[J]. Journal of Xidian University, 2021, 48(6):161-171.
[16]	高德勇, 康自兵, 王松, 等. 利用卷积块注意力机制识别人体动作的方法[J]. 西安电子科技大学学报, 2022, 49(4):144-155.
	GAO Deyong, KANG Zibing, WANG Song, et al. Method to Recognize Human Action by Using the Convolutional Block Attention Mechanism[J]. Journal of Xidian University, 2022, 49(4):144-155.
[17]	李东航. 基于机器学习的高铁无线通信越区切换优化技术研究[D]. 南京: 南京邮电大学, 2020.
[18]	TONG Q Q, LIANG G N, BI J B. Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM[J]. Neurocomputing, 2022, 481:333-356. doi: 10.1016/j.neucom.2022.01.014 pmid: 35342226
[19]	AKHPASHEV R V, ANDREEV A V. COST 231 Hata Adaptation Model for Urban Conditions in LTE Networks[C]// PInternational Conference of Young Specialists on Micro/nanotechnologies & Electron Devices.Piscataway:IEEE, 2016:64-66.
[20]	FRANCH P B, OLIVELLA A E, ALARCIA R G, et al. User Mobility Inference and Clustering through LTE PDCCH Data Analysis[C]// 2021 IEEE 93rd Vehicular Technology Conference.Helsinki.Piscataway:IEEE, 2021:1-6.
[21]	GOYAL T, KAUSHAL S. Handover Optimization Scheme for LTE-Advance Networks Based on AHP-TOPSIS and Q-Learning[J]. Computer Communications, 2018, 133:67-76. doi: 10.1016/j.comcom.2018.10.011
[22]	丁元锋. 高速铁路车地宽带通信软切换技术研究[J]. 铁道学报, 2020, 42(7):87-94.
	DING Yuanfeng. Study on Soft Handover Technology in High-Speed Train-wayside Broadband Communication System[J]. Journal of the China Railway Society, 2020, 42(7):87-94.
[23]	李春铎. 铁路LTE-R宽带移动通信系统高速适应性研究[D]. 北京: 中国铁道科学研究院, 2019.