查看文章

Cloud computing is the product of the integration of traditional computing. For Hybrid Cloud managers, delay prediction plays an important role in Hybrid Cloud management. Machine learning has shown good predictive performance in many areas. In this paper, we have proposed a training model based on machine learning algorithm, and predicted the delay using this model. The experimental results reflect the GBDT model with the strongest prediction ability compared to RF and SVM. According to the delay prediction, the dynamic threshold is more likely to find network traffic abnormalies.