自由空间激光通信网络异常数据检测方法

Abnormal data detection method for free space laser communication network

检测自由空间激光通信网络异常数据时,存在数据查全率低、检测出的异常数据少以及执行时间长的问题,为此提出自由空间激光通信网络异常数据检测方法。通过数据分段法对激光通信网络数据进行数据分段,基于分段结果完成数据的离散化,使用小波去噪法完成数据去噪;根据去噪结果建立激光通信网络的异常数据检测模型;最后使用遗传算法对该模型进行求解,实现异常数据检测目的。实验结果表明,对自由空间激光通信网络进行异常数据检测时,数据查全率较高,最高为99%、检测出的异常数据多,最高检出率为98%、执行时间较短,最短为40 s。

When detecting the abnormal data of free space laser communication network, there are some problems, such as low data recall, few detected abnormal data and long execution time. Therefore, a method for detecting the abnormal data of free space laser communication network is proposed. The laser communication network data is segmented by the data segmentation method, the data discretization is completed based on the segmentation results, and the data denoising is completed by the wavelet denoising method;According to the denoising results, the abnormal data detection model of laser communication network is established;Finally, genetic algorithm is used to solve the model to achieve the purpose of abnormal data detection. The experimental results show that when detecting abnormal data in free space laser communication network, the data recall rate is high, the maximum is 99%, there are many abnormal data detected, the maximum detection rate is 98%, the execution time is short, and the minimum is 40 s.