To deal with the existing problems of current network security situation prediction methods, such as overfitting, underfitting, various free variables and insufficient prediction accuracy, this paper proposed a RVM (Relevance Vector Machine) model with an improved Simulated Annealing (PSA-RVM) to solve the network security situation prediction problems. In the process of prediction, the sample data of network security situation were firstly reconstructed in phase-space to form the training sample set; then, Powell algorithm was used to improve Simulated Annealing (PSA) and RVM was inserted into the target function calculation process of PSA algorithm to optimize RVM hyper parameters and to acquire a network security situation prediction model with enhanced learning capability and prediction accuracy. The simulation experiment results indicate that the proposed method has higher prediction accuracy, with Mean Average Percentage Error (MAPE) and Root Mean Squared Error (RMSE) of 0.39256 and 0.01261, higher than Elman and Particle Swarm Optimization-based Support Vector Regression (PSO-SVR) models; the proposed method can depict well the changing tendency of network security situation, which is helpful for network administrators to control the development trend of future network security situation and take the initiative to take network defense measures.

To solve the problem of feature extraction and state prediction of intermittent non-stationary time series in the industrial field, a new prediction approach based on Ensemble Empirical Mode Decomposition (EEMD), Principal Component Analysis (PCA) and Support Vector Machine (SVM) was proposed in this paper. Firstly, the intermittent non-stationary time series was analyzed by multiple time scales and decomposed into a couple of IMF components which possessed the different scales by the EEMD algorithm. Then, the noise energy was estimated to determine the cumulative contribution rate adaptively on the basis of 3-sigma principle. The feature dimension and redundancy were reduced and the noise in IMF was removed by using PCA algorithm. Finally, on the basis of the determining of SVM key parameters, the principal components were regarded as input variables to predict future. Instance's testing results show that Mean Average Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE) and Mean Squared Percentage Error (MSPE) were 514.774, 78.216, 12.03% and 1.862%, respectively. It is concluded that the SVM prediction of the time series of output power of wind farm possesses a higher accuracy than not using PCA because the frequency mixing phenomena was inhibited, the non-stationary was reduced and the noise was further eliminated by EEMD algorithm and PCA algorithm.