Abstract: Disclosed in the present invention is a lightweight anomaly detection neural network model retraining method with anti-overfitting, which retrains an anomaly detection model based on depth variational autoencoders. When a data distribution changes, a conditional distribution of a hidden state and reconstructed data samples obtained by an encoder and a decoder of the depth variational autoencoders will also change. The present invention uses a mapping function to adjust the conditional distribution of the hidden state and the reconstructed data obtained by the calculation of an old model to adapt to a new data distribution. The mapping function has simple and convex characteristics, and can ensure a fast convergence rate and light overhead in a retraining process on a premise of using a loss function form defined by the present invention.

Abstract: The present invention discloses a server load prediction method based on deep learning, collecting the trend change of server load long series, and utilizing server load periodic information to establish a deep neural network prediction model to optimize peak load prediction. The present invention provides a method for improving the accuracy of neural network prediction by combining periodic information, long-term trend information, and short-term time series information, and demonstrates superiority over traditional methods in the peak load section. The method of the present invention can effectively improve prediction accuracy, provide more accurate scheduling and evacuation decision-making basis for cloud service providers, thereby reducing the redundant equipment required to ensure high reliability, reducing the operating costs of cloud service providers, and reducing the rental expenses of cloud service tenants.

Abstract: The present invention discloses a server load prediction method based on deep learning, collecting the trend change of server load long series, and utilizing server load periodic information to establish a deep neural network prediction model to optimize peak load prediction. The present invention provides a method for improving the accuracy of neural network prediction by combining periodic information, long-term trend information, and short-term time series information, and demonstrates superiority over traditional methods in the peak load section. The method of the present invention can effectively improve prediction accuracy, provide more accurate scheduling and evacuation decision-making basis for cloud service providers, thereby reducing the redundant equipment required to ensure high reliability, reducing the operating costs of cloud service providers, and reducing the rental expenses of cloud service tenants.