针对低轨卫星多波束系统在多方向通信时出现峰均比过高的问题,提出一种基于深度神经网络的峰均比抑制方法。该方法主要根据多波束通信系统在不同场景下的目标方向位置、接收端信噪比、误码率误差范围等输入层参数,自适应地选择限幅法的最优门限值,从而对每个阵元上合成的信号进行限幅操作,在保证低轨卫星多波束系统误码率的前提下降低了该系统的峰均比。最后通过仿真验证,该方法比传统固定门限的限幅法在误码率误差范围内对峰均比有明显改善。
Aiming at the problem that the peak-to-average ratio is too high when the LEO satellite multi-beam system communicates with multiple target directional angles, a method for suppressing the peak-to-average ratio based on a deep neural network is proposed. This method can adaptively select the optimal threshold of the limiting method based on the input layer parameters such as the target direction angle position of the multi-beam communication system, the SNR of the receiving end, and the error range of the BER. The signal synthesized on the element is subjected to amplitude limiting operation, which reduces the peak-to-average ratio of the LEO satellite multi-beam system while ensuring the BER of the system. Finally, it is verified by simulation that this method can significantly improve the peak-to-average ratio within the error range of the BER compared with the traditional fixed-threshold limiting method.
[1] 陈修继, 万继响. 通信卫星多波束天线的发展现状及建议[J]. 空间电子技术, 2016, 13(2):54-60. DOI:10.3969/j.issn.1674-7135.2016.02.011.
[2] Guo C, Hong W, Tian L, et al. Design and implementation of a full-digital beamforming array with nonreciprocal tx/rx beam patterns[J]. IEEE Antennas and Wireless Propagation Letters, 2020, 19(11):1978-1982. DOI:10.1109/LAWP.2020.2977061.
[3] Schmidt C A, Crussière M, Hélard J F. Digital beamforming with PAPR reduction:an approach for energy efficient massive MIMO[C]//2020 IEEE 91st Vehicular Technology Conference. May 25-28, 2020, Antwerp, Belgium. IEEE, 2020:1-6. DOI:10.1109/VTC2020-Spring48590.2020.9128621.
[4] 刘婉莹, 夏师懿, 姜泉江, 等. 低轨卫星网络基于跳波束的资源调度算法[J]. 中国科学院大学学报, 2020, 37(6):805-813. DOI:10.7523/j.issn.2095-6134.2020.06.012.
[5] Hu X, Liu S J, Wang Y P, et al. Deep reinforcement learning-based beam Hopping algorithm in multibeam satellite systems[J]. IET Communications, 2019, 13(16):2485-2491. DOI:10.1049/iet-com.2018.5774.
[6] 屈传慧. 多信号合成的峰均比与恒功率合成技术研究[D]. 西安:西安电子科技大学, 2018. DOI:CNKI:CDMD:2.1019.017884.
[7] Zhi X H, Huan H, Yu X. Peak-to-average power ratio analysis and reduction in transform domain communication system[C]//2016 IEEE 13th International Conference on Signal Processing. November 6-10, 2016, Chengdu, China. IEEE, 2016:1191-1195. DOI:10.1109/ICSP.2016.7878016.
[8] 李启虎. 《优化阵列信号处理》(上、下册)[J]. 声学学报, 2018, 43(4):728. DOI:10.15949/j.cnki.0371-0025.2018.04.033.
[9] 赵红梅. 星载数字多波束相控阵天线若干关键技术研究[D]. 南京:南京理工大学, 2009. DOI:10.7666/d.y1542753.
[10] Bulusu S S K C, Crussière M, Hélard J F, et al. Quasi-optimal tone reservation PAPR reduction algorithm for next generation broadcasting systems:a performance/complexity/latency tradeoff with testbed implementation[J]. IEEE Transactions on Broadcasting, 2018, 64(4):883-899. DOI:10.1109/TBC.2018.2811623.
[11] 刘璐, 赵国庆. 数字波束成形中峰均比抑制方法的研究[J]. 通信学报, 2018, 39(2):114-121. DOI:10.11959/j.issn.1000-436x.2018030.
[12] 刘璐, 赵国庆. 一种峰均比抑制方法的研究[J]. 电子学报, 2018, 46(10):2443-2449. DOI:10.3969/j.issn.0372-2112.2018.10.018.
[13] He X J, Yang F J, Xi R. Peak-to-average power ratio reduction in OFDM signals via self-adaptive EVM method[C]//2016 IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference. October 3-5, 2016, Xi'an, China. IEEE, 2016:676-679. DOI:10.1109/IMCEC.2016.7867295.
[14] Sandoval F, Poitau G, Gagnon F. Hybrid peak-to-average power ratio reduction techniques:review and performance comparison[J]. IEEE Access, 2017, 5:27145-27161. DOI:10.1109/ACCESS.2017.2775859.
[15] 郭子钰. 毫米波通信系统中的信道估计及峰均比压缩方法研究[D]. 南京:东南大学, 2016. DOI:10.7666/d.Y3186158.
[16] Han D S, Yang W, Liu W. Improved clipping and filtering algorithm applied to reduce PAPR[J]. Journal of Beijing University of Posts and Telecommunications, 2014. DOI:10.13190/j.jbupt.2014.04.010.
[17] 高欢. 基于OFDM系统抑制峰均功率比算法的研究[D]. 北京:中国石油大学(北京), 2018. DOI:CNKI:CDMD:2.1012.017174.
[18] 林津辉. 基于机器学习的OFDM系统峰均比降低技术研究[D]. 西安:西安电子科技大学, 2020. DOI:10.27389/d.cnki.gxadu.2020.001001.
[19] Cheng Y, Wang D, Zhou P, et al. Model compression and acceleration for deep neural networks:the principles, progress, and challenges[J]. IEEE Signal Processing Magazine, 2018, 35(1):126-136. DOI:10.1109/MSP.2017.2765695.
[20] Ying X. An overview of overfitting and its solutions[J]. Journal of Physics:Conference Series, 2019, 1168:022022. DOI:10.1088/1742-6596/1168/2/022022.
[21] Boger Z, Guterman H. Knowledge extraction from artificial neural network models[C]//1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation. October 12-15, 1997, Orlando, FL, USA. IEEE, 1997:3030-3035. DOI:10.1109/ICSMC.1997.633051.
