基于GRNN的协作车联网的中断性能预测
Prediction of Outage Probability of Cooperative Vehicular Network Based on GRNN
摘要: 针对车联网通信系统，为了提升系统的传输性能，建立多中继多天线协作车联网模型，并设计了一种基于广义回归神经网络(GRNN)的中断概率预测算法。通信链路服从级联Nakagmi-m分布，中继使用混合译码放大转发(HDAF)协议，目的端运用等增益合并。针对多天线，设计天线选择方案，并推导出中断概率表达式；进而构建预测中断概率的数据集，建立GRNN模型。实验结果表明，信道级联、HDAF协议和等增益合并能够提升中断性能，GRNN能有效实现中断概率的预测。
Abstract: For the Internet of vehicles (IoV) communication system, for the sake of improving the transmission performance, a multi-relay and multi-antenna cooperative vehicular network (CVN) model was es-tablished, and an outage probability (OP) prediction algorithm based on generalized regression neural network (GRNN) was designed. The communication links follow the cascaded Nakagmi-m distribution, the relays use hybrid decode-amplify farward (HDAF) protocol, and the destination uses equal gain combining. For MIMO system, the antenna selection scheme is proposed and the OP expression is derived. Then the data set to predict the OP is constructed, and the GRNN model is es-tablished. Experimental results show that the channel cascade, HDAF protocol and equal gain com-bination can improve the interrupt performance, and GRNN can effectively predict the OP.
文章引用：李亚, 张宇. 基于GRNN的协作车联网的中断性能预测[J]. 无线通信, 2023, 13(1): 1-11. https://doi.org/10.12677/HJWC.2023.131001

参考文献

[1] 谭晓芳, 张搴, 付凡成. 利用机器学习和双平面博弈模型的车联网拥挤感知路由算法[J]. 计算机应用与软件, 2020, 37(12): 150-157.
[2] Ahmed, E. and Gharavi, H. (2018) Cooperative Vehicular Networking: A Survey. IEEE Transactions on Intelligent Transportation Systems, 19, 996-1014. [Google Scholar] [CrossRef] 
[3] 吴琪, 邱斌, 蒋为, 李婉莹. 基于信噪比门限的车载协作通信功率分配优化方案[J]. 现代电子技术, 2020, 43(7): 10-13.
[4] 张雪茹, 冀保峰, 宋康, 沈森, 李春国. 基于DF中继协作的车联网安全传输性能研究[J]. 信号处理, 2020, 36(5): 723-732.
[5] 蒋为, 肖海林, 金晓晴. 基于Double-Nakagami-m的非对称全双工AF中继车载通信系统[J]. 桂林电子科技大学学报, 2019, 39(5): 351-356.
[6] Shi, Z., Zhang, H., Wang, H., et al. (2022) Block Error Rate Analysis of Short-Packet Mobile-to-Mobile Communications Over Correlated Cascaded Fading Channels. IEEE Transactions on Vehicular Technology, 71, 4087-4101. [Google Scholar] [CrossRef] 
[7] Xu, L., Zhou, X., Khan, M.A., et al. (2021) Communication Quality Pre-diction for Internet of Vehicle (IoV) Networks: An Elman Approach. IEEE Transactions on Intelligent Transportation Systems, 23, 19644-19654. [Google Scholar] [CrossRef] 
[8] Jaiswal, N. and Purohit, N. (2021) Performance Analysis of NOMA-Enabled Vehicular Communication Systems with Transmit Antenna Selection over Double Nakagami-m Fading. IEEE Transactions on Vehicular Technology, 70, 12725-12741. [Google Scholar] [CrossRef] 
[9] Mobini, Z., Mohammadi, M., Tsiftsis, T., et al. (2022) New Antenna Selection Schemes for Full-Duplex Cooperative MIMO-NOMA Sys-tems. IEEE Transactions on Communications, 70, 4343-4358. [Google Scholar] [CrossRef] 
[10] Xie, Y., Li, C., Lv, Y., et al. (2019) Predicting Lightning Outages of Transmission Lines Using Generalized Regression Neural Network. Applied Soft Computing, 78, 438-446. [Google Scholar] [CrossRef] 
[11] Bao, T., Zhu, J., Yang, H.C., et al. (2020) Secrecy Outage Performance of Ground-to-Air Communications with Multiple Aerial Eavesdroppers and Its Deep Learning Evaluation. IEEE Wireless Commu-nications Letters, 9, 1351-1355. [Google Scholar] [CrossRef] 
[12] Karagiannidis, G., Sagias, N. and Mathiopoulos, P. (2007) N*Nakagami: A Novel Stochastic Model for Cascaded Fading Channels. IEEE Transactions on Communications, 55, 1453-1458. [Google Scholar] [CrossRef] 
[13] Ikki, S. and Ahmed, M.H. (2007) Performance Analysis of Coopera-tive Diversity Wireless Networks over Nakagami-m Fading Channel. IEEE Communications Letters, 11, 334-336. [Google Scholar] [CrossRef] 
[14] Kumar, D. and Bhattacharjya, R.K. (2021) GRNN Model for Prediction of Groundwater Fluctuation in the State of Uttarakhand of India Using GRACE Data under Limited Bore Well Data. Journal of Hydroinformatics, 23, 567-588. [Google Scholar] [CrossRef]