Based on the improved osprey optimization algorithm and its application in short-term network traffic anomaly detection

In order to effectively deal with the impact of the randomness and instability of network traffic data on data transmission, this study first performs feature dimension reduction on network traffic data through principal component analysis (PCA) to improve the quality and stability of the data. The Osprey optimization algorithm (IOOA) is improved by introducing Tent chaotic mapping, dynamic reverse learning and adaptive step size strategy. The improved IOOA improves the global search ability and local search accuracy, and enhances the ability to jump out of the local optimal value. The parameters of deep extreme learning machine (DELM) are finely optimized using the improved Osprey optimization algorithm. Secondly, PCA-IOOA-DELM multi-step short-term network traffic anomaly detection model is constructed. Finally, the model is applied to the classification and anomaly detection of network traffic. The simulation results show that compared with other detection models, the PCA-IOOA-DELM detection model proposed in this study shows significant advantages in the accuracy and precision of short-term network traffic anomaly detection, and effectively improves the ability to identify abnormal traffic.