Abstract
To improve the security of Electric Power Network Security, and identify, understand, evaluate and predict various activities in the network, corresponding detection and prediction models are established for network intrusion detection and network security situation prediction based on the machine learning algorithm, and carries out network security situation awareness. First, a network intrusion detection model is established based on the support vector machine (SVM) and neural network. The two kinds of classification detection methods are combined to detect different traffic types respectively to improve the detection effect of the network intrusion detection system. Then, the network security situation prediction model is established based on the SVM, and the kernel function and related parameters of SVM are optimized by simulated annealing (SA) algorithm. Then, the training data are pre-processed and divided into five categories, and carried out relevant experiments. The intrusion detection model experiments show that the hybrid model of network intrusion detection system combines the advantages of SVM and neural network, which has a good detection effect for five kinds of data; the overall detection rate of the hybrid model is higher than that of the single model, and the training time and detection time are greatly reduced. Compared with other machine learning algorithms, the hybrid model has a better overall detection effect. The network security situation prediction model experiments show that root mean square error (RMSE) and fitness (Rsquared) of Gaussian kernel function are the smallest, and the penalty factor obtained by SA algorithm is C=8.58, and the width of radial basis function (RBF) kernel is g=0.125. The prediction of the model based on SVM is basically consistent with the actual value. Therefore, the network intrusion detection model and network security situation prediction model designed based on machine learning have good detection and prediction effect, and can be used in the application of network security situation awareness. This exploration provides a reference for the construction of network security.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.