Network Service Identification Method for Electric Power Cloud

Electric power cloud data center becomes more and more widely applied, and yet lacks security protection inside it. The most direct solution for this issue is internal network isolation. This paper focuses on the first task of the isolation, namely network service identification, and proposes a network service identification framework based on deep clustering. In order to obtain service stream, a network service stream extraction algorithm is proposed based on the flow metric and traffic pattern. Considering the high dimensionality and complexity of service streams, the denoising and convolutional autoencoders are combined for feature extraction. And then a self-organizing mean maps network is adopted to achieve network service identification. Experiment results illustrate the effectiveness and superiority of the self-organizing mean maps network with regard to the internal evaluation index of clustering. Therefore, the identification framework proposed seems to provide a foundation for subsequent isolation study.