Cloud Belief Rule Base Model for Network Security Situation Prediction

Abstract

To predict network security situations better using expert knowledge and quantitative data, a new forecasting model known as cloud belief rule base (CBRB) model is proposed. The CBRB model utilizes the cloud model to describe the referential point of belief rule, which is more accurate for describing expert knowledge. Moreover, to achieve the optimal parameters of the proposed model, a constraint covariance matrix adaptation evolution strategy (CMA-ES) algorithm is presented in this letter. A case study for network security situation prediction is conducted with CBRB and CMA-ES. The experimental results demonstrate the effectiveness and practicality of the proposed CBRB model.