| 19 | 0 | 5 |
| 下载次数 | 被引频次 | 阅读次数 |
针对传统检测方法在复杂干扰条件下鲁棒性不足的问题，提出一种基于混合专家（Mixture-of-Experts, MoE）网络的抗干扰检测方法，用于复杂电磁环境下正交频分复用（Orthogonal Frequency Division Multiplexing, OFDM）信号的可靠检测。依托复杂干扰条件下的OFDM信号模型，采用融合导频信息的多通道接收特征作为模型输入；设计干扰识别驱动的级联接收结构，通过干扰识别网络判别干扰类型，并根据识别结果自适应选择MoE网络中的对应专家模型，实现针对性干扰抑制；结合DeepRx检测网络实现比特级检测。仿真结果表明，在多类典型干扰场景下，所提方法相比直接检测、混合干扰训练模型以及线性最小均方误差（Linear Minimum Mean Square Error,LMMSE）检测器，能够获得更低的误码率（Bit Error Rate, BER），并表现出更稳定的检测性能，从而有效提升复杂电磁环境下OFDM系统的抗干扰检测能力。
Abstract：Conventional detection methods are vulnerable to complex jamming conditions. To address this issue, this paper proposes a Mixture-of-Experts(MoE)-based anti-jamming detection method for reliable Orthogonal Frequency Division Multiplexing(OFDM)signal detection in complex electromagnetic environments. Based on the OFDM signal model under jamming conditions, multi-channel received features incorporating pilot information are used as the input to the learning model. An interference-recognitiondriven cascaded receiver architecture is developed, where the interference type is identified by an interference recognition network, and the corresponding expert model is selected within the MoE framework according to the recognition result. A DeepRx detection network is employed for bit-level detection. Simulation results demonstrate that, under multiple representative jamming scenarios, the proposed method achieves lower Bit Error Rate(BER) than direct detection, models trained on mixed jamming data, and the Linear Minimum Mean Square Error(LMMSE) detector, while maintaining more stable detection performance across different jamming conditions. Therefore, the proposed method effectively enhances the anti-jamming detection capability of OFDM systems in complex electromagnetic environments.
[1]Pirayesh H, Zeng H. Jamming attacks and anti-jamming strategies in wireless networks:A comprehensive survey[J].IEEE Communications Surveys&Tutorials, 2022, 24(2):767-809.
[2]Aref M A, Jayaweera S K, Yecez E. Survey on cognitive anti-jamming communications[J]. IET Communications,2020, 14(18):3110-3127.
[3]Wu Y Y, Zou W Y. Orthogonal frequency division multiplexing:A multi-carrier modulation scheme[J].IEEE Transactions on Consumer Electronics, 1995, 41(3):392-399.
[4]Lasorte N, Barnes W J, Refai H H. The history of orthogonal frequency division multiplexing[C]//Proceedings of the IEEE GLOBECOM 2008-2008 IEEE Global Telecommunications Conference. New Orleans:IEEE, 2008:1-5.
[5]Clancy T C. Efficient OFDM denial:Pilot jamming and pilot nulling[C]//Proceedings of the 2011 IEEE International Conference on Communications(ICC).Kyoto:IEEE, 2011:1-5.
[6]Shahriar C, Clancy T C, Mcgwier R W. Equalization attacks against OFDM:analysis and countermeasures[J].Wireless Communications and Mobile Computing, 2016,16(13):1809-1825.
[7]Mahal J A, Clancy T C. The BER analysis of OFDMA and SC-FDMA under pilot-assisted channel estimation and pilot jamming in rayleigh slow-fading channel[J]. Wireless Communications and Mobile Computing, 2016, 16(15):2315-2328.
[8]El Gebali A, Landry R J. Single and multiple continuouswave interference suppression using adaptive IIR notch filters based on direct-form structure in a QPSK communication system[J]. Applied Sciences, 2022, 12(4):2186.
[9]O’shea T, Hoydis J. An introduction to deep learning for the physical layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2017, 3(4):563-575.
[10]Honkala M, Korpi D, Huttunen J M. DeepRx:Fully convolutional deep learning receiver[J]. IEEE Transactions on Wireless Communications, 2021, 20(6):3925-3940.
[11]Zheng S L, Chen S C, Yang X N. DeepReceiver:a deep learning-based intelligent receiver for wireless communications in the physical layer[J]. IEEE Transactions on Cognitive Communications and Networking, 2021, 7(1):5-20.
[12]He H T, Jin S, Wen C K, et al. Model-driven deep learning for physical layer communications[J]. IEEE Wireless Communications, 2019, 26(5):77-83.
[13]Shlezinger N, Fu R, Eldar Y C. DeepSIC:Deep soft interference cancellation for multiuser MIMO detection[J].IEEE Transactions on Wireless Communications, 2021,20(2):1349-1362.
[14]Jiang M, Ye Z, Xiao Y, et al. Federated transfer learning aided interference classification in GNSS signals[C]//2024IEEE/CIC International Conference on Communications in China(ICCC). Hangzhou:IEEE, 2024:1988-1993.
[15]Ait Aoudia F, Hoydis J. Model-free training of end-to-end communication systems[J]. IEEE Journal on Selected Areas in Communications, 2019, 37(11):2503-2516.
[16]Ait Aoudia F, Hoydis J. End-to-end learning for OFDM:from neural receivers to pilotless communication[J]. IEEE Transactions on Wireless Communications, 2022, 21(2):1049-1063.
[17]Felix A, Cammerer S, D?rner S, et al. OFDM-autoencoder for end-to-end learning of communications systems[C]//Proceedings of the 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications(SPAWC). Kalamata:IEEE, 2018:1-5.
[18]Jiang M, Ye Z Q, Xiao Y, et al. ACSNet:A deep neural network for compound GNSS jamming signal classification[J]. IEEE Transactions on Cognitive Communications and Networking, 2026, 12:1601-1615.
基本信息:
中图分类号:TN975
引用信息:
[1]何洪雨,包阳,叶子强,等.复杂电磁环境下基于混合专家网络的抗干扰检测方法[J].无线电通信技术().
基金信息:
国家重点研发计划“面向下一代高效无线通信接入的智能资源利用关键技术研究”(2025YFE0100900); 基础科研创新基金(IFN202510)
2026-05-21
2026-05-21
2026-05-21