全光通信网络非线性突变频率干扰检测算法

安宁

doi:10.13756/j.gtxyj.2024.230064

您当前的位置：

首页 >

文章列表页 >

全光通信网络非线性突变频率干扰检测算法

光通信系统与网络技术 | 更新时间：2024-05-30

- 全光通信网络非线性突变频率干扰检测算法
- Nonlinear Mutation Frequency Interference Detection Algorithm for All Optical Communication Networks
- 光通信研究 2024年第3期页码：23006401-23006405
- 作者机构：
  
  国家电网公司东北分部，沈阳　110180
- 作者简介：
  
  安宁（1980-），男，辽宁沈阳人。高级工程师，硕士，主要研究方向为电力系统通信。
- 基金信息：
- DOI：10.13756/j.gtxyj.2024.230064
  中图分类号： TN912
- 纸质出版日期：2024-06-10，
  
  收稿日期：2023-04-28，
  
  修回日期：2023-06-05，
扫描看全文
安宁.全光通信网络非线性突变频率干扰检测算法[J].光通信研究，2024（3）：230064.

An N. Nonlinear Mutation Frequency Interference Detection Algorithm for All Optical Communication Networks[J]. Study on Optical Communications, 2024（3）：230064.
安宁.全光通信网络非线性突变频率干扰检测算法[J].光通信研究，2024（3）：230064. DOI： 10.13756/j.gtxyj.2024.230064.

An N. Nonlinear Mutation Frequency Interference Detection Algorithm for All Optical Communication Networks[J]. Study on Optical Communications, 2024（3）：230064. DOI： 10.13756/j.gtxyj.2024.230064.

摘要

【目的】

针对全光通信网络非线性突变频率干扰问题进行分析时，主要依托于估计信道协方差直接展开干扰检测，并未展开网络通信信号变换处理，使得检测结果的F

-score值较低，为此提出了基于时域有限差分的全光通信网络非线性突变频率干扰检测算法。

【方法】

结合数据包抓包和镜像两种方式采集全光通信网络流量数据，并进行清理、转换和规约处理。依托于时域有限差分工作原理，在时域和频域空间内描述信号的时宽和带宽，应用导数与傅里叶变换算法对实时采集信号进行处理，利用变换后的信号分析非线性突变频率干扰情况，再针对变换后的信号进行检测分析。在时间-频率联合特征分析方法辅助下，提取干扰信号的时域、频域特征，依托于反向传播算法和最小化损失函数，简化非线性突变频率干扰检测过程，采用特征距离函数替换网络损失函数，并将其输入基于孪生网络的干扰识别模型中，得出非线性突变频率干扰检测结果。

【结果】

在不同噪声条件下，所提算法非线性突变频率干扰检测结果的F

-score值保持在0.95以上，检测时间低于40 ms。

【结论】

应用时域有限差分方法的新型检测方法，能够更准确地反映当前通信网络的干扰情况，保证通信网络正常运行，更好地满足了全光通信网络干扰检测要求。

Abstract

【Objective】

When analyzing the nonlinear mutation frequency interference problem in all optical communication networks

interference detection mainly relies on estimating channel covariance directly

without expanding network communication signal transformation processing

resulting in low F1-score values of the detection results. Therefore

a nonlinear abrupt frequency interference detection algorithm based on finite difference time domain is proposed for all-optical communication networks.

【Methods】

We collect all optical communication network traffic data by combining packet capturing and mirroring methods

followed by cleaning

conversion

and protocol processing. Relying on the working principle of finite difference time-domain method

we first describe the time width and bandwidth of the signal in time-domain and frequency-domain space. Then we apply derivative and Fourier transform algorithm to transform the real-time collected network communication signal. Next

we use the transformed signal to analyze the nonlinear abrupt frequency interference. Finally the transformed signal is detected and analyzed. With the aid of the time-frequency joint feature analysis method

the time-domain and frequency-domain features of the interference signal are extracted. Relying on the back propagation algorithm and the minimization of the loss function

the detection process of nonlinear abrupt frequency interference is simplified. The characteristic distance function is used to replace the network loss function

and it is input into the interference recognition model based on the twin network to obtain the detection results of nonlinear abrupt frequency interference.

【Results】

The experimental results show that under different noise conditions

the F1-score value of the proposed algorithm's nonlinear mutation frequency interference detection results remains above 0.95. The detection time is less than 40 ms.

【Conclusion】

The new detection method using the finite difference time-domain method can more accurately reflect the interference situation of the current communication network. It ensures the normal operation of the communication network

and meets the interference detection requirements of all-optical communication network.

关键词

全光通信网络非线性突变频率干扰时域有限差分通信信号信号变换干扰检测

Keywords

all optical communication networknonlinear mutation frequency interferencefinite difference time domaincommunication signalsignal transformationinterference detection

references

杨海宁, 李昆, 初大平. 硅基液晶技术与可重构全光通信网络[J]. 液晶与显示, 2021, 36(6): 772-788.

Yang H N, Li K, Chu D P. Liquid Crystal on Silicon Technology and Reconfigurable All-optical Networks[J]. Chinese Journal of Liquid Crystals and Displays, 2021, 36(6): 772-788.

陈晓威, 杨文革. 基于时变白化滤波器的DSSS系统干扰盲检测[J]. 系统工程与电子技术, 2021, 43(7): 1981-1988.

Chen X W, Yang W G. Blind Jamming Detection based on Time Variant Whitener for DSSS Systems[J]. Systems Engineering and Electronics, 2021, 43(7): 1981-1988.

曾宏志, 史洪松. 面向光通信网络系统的异常入侵在线检测研究[J]. 激光杂志, 2022, 43(12): 139-143.

Zeng H Z, Shi H S. Research on Abnormal Intrusion Online Detection for Optical Communication Network Systems[J]. Laser Journal, 2022, 43(12): 139-143.

王晓惠, 冯彩英. 基于子波变换的无线通信网络干扰信号检测研究[J]. 激光与红外, 2022, 52(6): 875-880.

Wang X H, Feng C Y. Research on Interference Signal Detection based on Wavelet Transform in Wireless Communication Network[J]. Laser & Infrared, 2022, 52(6): 875-880.

李丽艳, 胡鸿豪, 王云兴. 电子通信非线性突变频率干扰检测与仿真[J]. 计算机仿真, 2022, 39(9): 471-475.

Li L Y, Hu H H, Wang Y X. Detection and Simulation of Nonlinear Abrupt Frequency Interference in Electronic Communication[J]. Computer Simulation, 2022, 39(9): 471-475.

谭韶生, 夏旭. 基于大数据优化神经网络的船舶通信网络干扰信息识别[J]. 舰船科学技术, 2022, 44(14): 133-136.

Tan S S, Xia X. Disturbance Information Identification of Ship Communication Network based on Big Data Optimization Neural Network[J]. Ship Science and Technology, 2022, 44(14): 133-136.

赵凤龙. 大数据资源调度下船舶通信网络干扰信息识别研究[J]. 舰船科学技术, 2022, 44(12): 133-136.

Zhao F L. Research on Interference Information Identification of Ship Communication Network based on Big Data Resource Scheduling[J]. Ship Science and Technology, 2022, 44(12): 133-136.

靳增源, 张晓瀛, 谭思源, 等. 基于集成时频通道注意力的倒残差神经网络干扰识别[J]. 信号处理, 2023, 39(2): 343-355.

Jin Z Y, Zhang X Y, Tan S Y, et al. Jamming Identification based on Inverse Residual Neural Network with Integrated Time-frequency Channel Attention[J]. Journal of Signal Processing, 2023, 39(2): 343-355.

刘明骞, 高晓腾, 李明, 等. 空地协同场景下通信干扰智能识别方法[J]. 电子与信息学报, 2022, 44(3): 825-834.

Liu M Q, Gao X T, Li M, et al. Communication Interference Intelligent Recognition in the Air-to-ground Collaboration Scenario[J]. Journal of Electronics & In-formation Technology, 2022, 44(3): 825-834.

赵伟, 王文娟. 基于深度信念网络的光通信网络数据异常识别研究[J]. 激光杂志, 2023, 44(1): 174-178.

Zhao W, Wang W J. Research on Data Anomaly Identification of Optical Communication Network based on Deep Belief Network[J]. Laser Journal, 2023, 44(1): 174-178.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据