| 259 | 0 | 118 |
| 下载次数 | 被引频次 | 阅读次数 |
传统直接序列扩频(Direct Sequence Spread Spectrum, DSSS)技术在无线通信抗干扰中应用广泛，能够通过扩展频谱带宽改善接收端的输入信噪比，提升通信过程的安全性。随着干扰样式日趋智能化，此类技术在应对未知且动态变化的干扰时，产生了一定的使用缺陷。基于干扰对抗思想，提出一种基于强化学习的动态扩频抗干扰策略，在确保收发端可靠通信的前提下，最大化信息传输速率。区别于大部分以规避干扰方式来抗干扰的策略，所提策略将抵抗干扰问题建模为马尔可夫决策过程(Markov Decision Process, MDP),优化目标为在保证固定信道可靠通信的前提下，同时最大化系统吞吐量。提出一种基于退火Q学习的动态扩频通信抗干扰策略，平衡环境探索与经验学习，提高收敛速度和决策成功率。仿真结果表明，在可变强度的随机窄带干扰模式下，所提算法的吞吐量性能优于基于LT码的DSSS通信系统、基于频谱感知的随机扩频因子选择策略和固定扩频因子策略。
Abstract：Traditional Direct Sequence Spread Spectrum(DSSS)technology has been widely used in wireless communication for anti-jamming purposes, which can improve the input signal to noise ratio at the receiving end and enhance the communication process security by expanding the bandwidth of the spread spectrum. However, as the intelligent nature of interference becomes more prevalent, this technology has certain usage defects in dealing with unknown and dynamically changing interference. A dynamic spread spectrum anti-jamming strategy based on reinforcement learning is proposed, which ensures reliable communication between the transmitter and receiver while maximizing the information transmission rate. Unlike most anti-interference strategies that avoid interference, the resistance to interference problem is modeled as a Markov Decision Process(MDP), with the optimization goal of maximizing the system throughput while ensuring reliable communication under a fixed channel. Then, a dynamic spread spectrum communication anti-jamming strategy based on simulated annealing Q-learning is proposed, which balances exploration of the environment and experience learning to improve convergence speed and decision success rate. Simulation results show that the throughput performance of the proposed algorithm is better than DSSS communication system based on LT code, traditional random spreading factor selection strategy and fixed spreading factor strategy under random narrowband interference with variable intensity.
[1]乌日娜.现代战争中电磁频谱相关技术的发展与应用[J].电子技术与软件工程,2020(5):108-109.
[2]杜子亮,王英民.军用无线通信干扰和抗干扰技术分析[J].雷达与对抗,2020,40(4):29-32.
[3]石锐,李勇,牛英滔.无线通信智能抗干扰研究进展和发展方向[J].电子信息对抗技术,2024,39(4):98-108.
[4]杨万君,伍滨,王旭宁.一种扩频通信系统的实现[J].无线电通信技术,2013,39(3):17-19.
[5]顾建峰,陈立强,王坡.无线通信抗干扰技术研究[J].中国高新科技,2023(7):133-135.
[6]陈玮.扩频通信技术的原理及应用研究[J].电子元器件与信息技术,2022,6(10):171-174.
[7]蔡武,张世超,邱硕丰,等.一种DS/FH混合扩频的抗干扰波形设计方法[J].舰船电子对抗,2023,46(4):32-39.
[8]CHEN B,TANG S,DU X L,et al.Study on an Anti-jamming Method of Spread-spectrum Communication Based on LT Codes[C]//11th International Conference on Wireless Communications,Networking and Mobile Computing(WiCOM 2015).Shanghai:IEEE,2015:1-5.
[9]YANG S,LI J H,HE B Z.A Novel Interference Suppression Method in Spread Spectrum Communication Based on Blind Source Separation[C]//2017 3rd IEEE International Conference on Computer and Communications (IC-CC).Chengdu:IEEE,2017:816-820.
[10]MEI X Y,YU L.An Adaptive Hybrid Spread Spectrum System Design and Anti-jamming Capability Analysis[C]//2013 IEEE 10th International Conference on High Performance Computing and Communications&2013IEEE International Conference on Embedded and Ubiquitous Computing.Zhangjiajie:IEEE,2013:226-229.
[11]ALAGIL A,LIU Y.Randomized Positioning DSSS with Message Shuffling for Anti-jamming Wireless Communications[C]//2019 IEEE Conference on Dependable and Secure Computing (DSC).Hangzhou:IEEE,2019:1-8.
[12]ZHANG Z X,WU Q H,ZHANG B,et al.Intelligent AntiJamming Relay Communication System Based on Reinforcement Learning[C]//2019 2nd International Conference on Communication Engineering and Technology (IC-CET).Nagoya:IEEE,2019:52-56.
[13]NIE J,HAYKIN S.A Q-learning-based Dynamic Channel Assignment Technique for Mobile Communication Systems[J].IEEE Transactions on Vehicular Technology,1999,48(5):1676-1687.
[14]GWON Y,DASTANGOO S,FOSSA C,et al.Competing Mobile Network Game:Embracing Anti-jamming and Jamming Strategies with Reinforcement Learning[C]//2013 IEEE Conference on Communications and Network Security (CNS).National Harbor:IEEE,2013:28-36.
[15]LI Y Y,XU Y H,WANG X M,et al.Power and Frequency Selection Optimization in Anti-jamming Communication:ADeep Reinforcement Learning Approach[C]//2019 IEEE 5th International Conference on Computer and Communications(ICCC).Chengdu:IEEE,2019:815-820.
[16]HANAWAL M K,ABDEL-RAHMAN M J,KRUNZ M.Joint Adaptation of Frequency Hopping and Transmission Rate for Anti-jamming Wireless Systems[J].IEEE Transactions on Mobile Computing,2016,15(9):2247-2259.
[17]LI Y,XU Y H,XU Y T,et al.Dynamic Spectrum Antijamming in Broadband Communications:A Hierarchical Deep Reinforcement Learning Approach[J].IEEE Wireless Communications Letters,2020,9(10):1616-1619.
[18]靳越,吴晓富,张剑书.融合注意力机制和LSTM的跳频抗干扰智能决策[J].无线电通信技术,2023,49(6):1059-1066.
[19]WATKINS C,DAYAN P.Q-learning[J].Machine Learning,1992,8(3):279-292.
[20]WORTHEN A,STARK W.Interference Mitigation in Frequency-hopped Spread-spectrum Systems[C]//2000 IEEESixth International Symposium on Spread Spectrum Techniques and Applications.Piscataway:IEEE,2000:58-62.
基本信息:
DOI：
中图分类号:TN914.42;TP18
引用信息:
[1]刘淼,龚玉萍,任国春等.基于退火Q学习的动态扩频通信抗干扰策略[J].无线电通信技术,2025,51(02):274-282.
基金信息:
江苏省青年科技基金(BK20231027)~~