Online intrusion detection mechanism based on model migration in intelligent pumped storage power stations

Abstract

With the continuous integration of new energy into the power grid, various new attacks continue to emerge and the feature distributions are constantly changing during the deployment of intelligent pumped storage power stations. The intrusion detection model trained on the old data is hard to effectively identify new attacks, and it is difficult to update the intrusion detection model in time when lacking data. To solve this issue, by using model-based transfer learning methods, in this paper we propose a convolutional neural network (CNN) based transfer online sequential extreme learning machine (TOS-ELM) scheme to enable the online intrusion detection, which is called CNN-TOSELM in this paper. In our proposed scheme, we use pre-trained CNN to extract the characteristics of the target domain data as input, and then build online learning classifier TOS-ELM to transfer the parameter of the ELM classifier of the source domain. Experimental results show the proposed CNNTOSELM scheme can achieve better detection performance and extremely short model update time for intelligent pumped storage power stations.