摘要
针对电力通信网络异常数据流入侵检测效率低的问题,提出对基于深度学习的电力通信网络异常数据流入侵自动检测方法。该方法首先通过通信网络进行数据采集和预处理,设计交叉混淆检测矩阵,然后建立深度学习电力网络异常数据流入侵自动检测模型,采用入侵持续定位修正的方式实现自动检测。结果表明,与传统方法相比,该设计方法的自动检测平均次数较高,检测的效果更具体,实际应用价值较高。
Aiming at the problem of low efficiency in detecting abnormal data flow intrusion in power communication networks,a deep learning based automatic detection method for abnormal data flow intrusion in power communication networks is proposed.This method first collects and preprocesses communication network data,designs a cross confusion detection matrix,and then establishes a deep learning automatic detection model for abnormal data flow intrusion in power networks.The intrusion detection is achieved through continuous localization and correction.The results show that compared with traditional methods,this design method has a higher average number of automatic detections,more specific detection effects,and higher practical application value.
作者
魏晶平
杜梦迪
王阔
WEI Jingping;DU Mengdi;WANG Kuo(Wuzhong Power Supply Company,State Grid Ningxia Electric Power Co.,Ltd.,Wuzhong,Ningxia 751100,China)
出处
《自动化应用》
2025年第4期247-248,252,共3页
Automation Application
关键词
深度学习
电力通信
通信网络
异常数据
入侵检测
检测方法
deep learning
power communication
communication network
abnormal data
intrusion detection
detection method
