萤火虫群算法优化高斯过程的网络安全态势预测

Network security situation prediction based on Gaussian process optimized by glowworm swarm optimization

针对共轭梯度法获取高斯过程超参数存在迭代次数难以确定及预测不精准等问题，提出一种萤火虫群算法优化高斯过程的预测方法，并将其应用于网络安全态势预测研究。采用萤火虫群优化算法对高斯过程超参数进行智能寻优，建立基于高斯过程回归的网络安全态势预测模型。实验结果表明新方法的平均相对预测误差较共轭梯度法、粒子群优化算法和人工蜂群优化算法分别降低了近29．46％、10．37％和4．22％，且新方法收敛较快。另外，分析对比了3种单一类型和2种复合类型的协方差函数对高斯过程预测的影响，实验结果表明采用神经网络与有理二次的复合协方差函数（neural network and rational quadratic composite covariance function，NN-RQ）的平均相对预测误差较其他4类协方差函数降低了1．65％～7．51％。

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 predic- tion which are caused by searching the hyperparameters of the Gaussian process with the conjugate gradient al- gorithm. 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 av- erage 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.