电力信息与通信技术2025，Vol.23Issue(7)：1-9,9.DOI:10.16543/j.2095-641x.electric.power.ict.2025.07.01
能源互联网环境下基于稀疏随机投影和深度学习的入侵检测算法
Intrusion Detection Algorithm Based on Sparse Random Projection and Deep Learning in Environment of Energy Internet
摘要
Abstract
The characteristics of openness,sharing and interconnection make the energy Internet face more network intrusion risks.How to detect network intrusion efficiently and accurately is very important for the safe and stable operation of energy Internet.The existing machine learning based intrusion detection algorithms have problems such as inability to effectively handle high-dimensional intrusion datasets and low real-time and accuracy.To address the aforementioned issues,this paper proposes an intrusion detection algorithm based on sparse random projection and deep learning(ID-SRPDL).The algorithm first utilizes sparse random projection to select features from intrusion datasets,reducing the impact of high-dimensional features on intrusion detection accuracy.Then,combining the advantages of convolutional neural networks,genetic programming is used to optimize the parameters of convolutional neural networks,and an intrusion detection model based on genetic programming and convolutional neural networks is constructed.The experimental results on three standard intrusion detection datasets show that the proposed ID-SRPDL algorithm has significant advantages over classical and latest intrusion detection algorithms in terms of average time consumption,intrusion detection accuracy,false positive rate,and false negative rate.关键词
能源互联网/稀疏随机投影/卷积神经网络/入侵检测/遗传编程Key words
energy internet/sparse random projection/convolutional neural network/intrusion detection/genetic programming分类
信息技术与安全科学引用本文复制引用
张晓,张英杰,李佳霖,邓松..能源互联网环境下基于稀疏随机投影和深度学习的入侵检测算法[J].电力信息与通信技术,2025,23(7):1-9,9.基金项目
国家电网有限公司技术研究服务项目"电力二次系统年度技术发展研究支撑-电力监控系统网络安全技术研究"(SGZB0000GDJS2400388). （SGZB0000GDJS2400388）
