基于神经网络的大型无人值守风电场网络安全监控技术研究  

Research on network security monitoring technology forlarge unmanned wind farm based on neural network

作　　者：邱情芳 曹学铭 王丹丹[1] 蔡继峰[1] 李新华 周成胜 Qiu Qingfang;Cao Xueming;Wang Dandan;Cai Jifeng;Li Xinhua;Zhou Chengsheng(China General Certification Center,Beijing 100013,China;China Academy of Information and Communications Technology,Beijing 100083,China)

机构地区：[1]北京鉴衡认证中心有限公司,北京100013 [2]中国信息通信研究院,北京100083

出　　处：《网络安全与数据治理》2025年第2期10-16,31,共8页CYBER SECURITY AND DATA GOVERNANCE

基　　金：国家重点研发计划(2023YEB4203104)。

摘　　要：大型无人值守风电场作为清洁能源的重要组成部分,其网络安全不仅关系到风电场的稳定运行,还直接影响到整个电力系统的安全。研究基于神经网络的大型无人值守风电场网络安全监控技术,以提高风电场的网络安全防护能力。首先分析了大型无人值守风电场的网络安全威胁,包括外部攻击、内部泄露、设备故障等。针对这些威胁,设计了基于神经网络的网络安全监控模型,该模型能够实时监测风电场的网络流量、设备状态等关键信息,并通过深度学习算法对异常行为进行识别和预警。为了验证模型的有效性,在模拟风电场环境中进行了实验,结果表明,该模型能够准确识别出多种网络安全威胁,并提前发出预警,为风电场的网络安全防护提供了有力支持。Large-scale unmanned wind farm is an important component of clean energy,and its network security not only relates to the stable operation of wind farms,but also directly affects the security of the entire power system.Therefore,this study aims to explore the network security monitoring technology for large-scale unmanned wind farms based on neural networks,in order to improve the network security protection capability of wind farms.This study first analyzed the network security threats of large unmanned wind farms,including external attacks,internal leaks,equipment failures etc.In response to these threats,this study designed a neural network-based network security monitoring model that can monitor key information such as network traffic and equipment status of wind farms in real time,and identify and warn of abnormal behavior through deep learning algorithms.In order to verify the effectiveness of the model,experiments were conducted in a simulated wind farm environment.The results showed that the model can accurately identify various network security threats and issue early warnings,providing strong support for the network security protection of wind farms.

关 键 词：风电场 网络安全 安全监控 神经网络 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]