基于LSTM的电力网络恶意流量攻击检测研究

Research on Malicious Traffic Attack Detection in Power Networks Based on LSTM

随着物理电网与网络的深度融合,电网系统越来越容易受到网络攻击的威胁,其中包括恶意流量攻击。这类攻击通过网络传播恶意流量,可能导致智能电网出现通信故障,因此及时准确地检测此类攻击对电力企业至关重要。本文提出了一种基于长短期记忆(long short-term memory,LSTM)深度学习模型的实时恶意流量攻击检测方法。该方法通过实时采集网络流量并提取关键特征,利用LSTM模型识别网络流量的性质,以判断网络是否遭受攻击。此外,在软件定义网络(software-defined networking,SDN)架构下构建了一个相应的原型系统。原型系统实验结果显示,该方法能有效抵御实际网络中的恶意流量攻击,提高了电网的网络安全。

With the deep integration of the physical power grid and cyber networks,the smart grid faces a variety of cyber attacks,including malicious traffic attacks.By blindly forwarding malicious traffic,these attacks could cause communication failures in the smart grid.Therefore,it is crucial to detect such attacks promptly and accurately for power enterprise operations.In this paper,we propose a real-time malicious traffic attack detection method based on the Long Short-Term Memory(LSTM)deep learning model.By collecting network traffic in real time and extracting key features,our proposed method can determine whether the network is under attack using the LSTM model.Furthermore,a corresponding prototype system was constructed under the Software-Defined Networking(SDN)architecture.The experimental results from the prototype system demonstrate its effectiveness in defending against malicious traffic attacks in actual networks,thereby enhancing the cybersecurity of the power grid.