Abstract:

A prediction method based on the Gaussian process optimized by glowworm swarm optimization (GSO) is proposed to solve the problems of difficult determination of iteration steps and less accuracy of prediction which are caused by searching the hyperparameters of the Gaussian process with the conjugate gradient algorithm. And it is applied to the research of network security situation prediction. The hyperparameters of the Gaussian process are intelligently searched by the GSO algorithm for establishing the network security situation prediction model based on Gaussian process regression. The analysis results of the experiment show that the average relative prediction error of this new method is reduced by about 29.46%, 10.37% and 4.22% compared with the conjugate gradient algorithm, the particle swarm optimization (PSO) algorithm and the artificial bee colony (ABC) algorithm separately, and the new method has a better convergence. In addition, the impact of the prediction results are analyzed and compared by three single type covariance functions and two composite type covariance functions, and the analysis results of the experiment show that the average relative prediction error with neural network and rational quadratic composite covariance function (NN-RQ) is reduced by 1.65% to 7.51% compared with other four covariance functions.