A Multi-Sequence Combination Prediction Method of Host Load Based on Wavelet Packet Decomposition

Abstract

The invention relates to a multi-sequence combination prediction method of host load based on wavelet packet decomposition, which belongs to the field of computer application technology. Starting from the perspective of nonlinear and non-stationary information processing, the present invention constructs multiple sequences and utilizes various data relationships related to each sequence and load, and combines the wavelet packet-SVR model and the AR model to predict the load of the host to improve the load of the host. load prediction accuracy. This method is suitable for the host load prediction of key periods or key moments.

Description

Technical field [0001] The invention relates to a host load multi-sequence combination prediction method based on wavelet packet decomposition, and belongs to the technical field of computer applications. Background technique [0002] Generally, in a distributed network environment, load prediction is divided into network-based load prediction (network load prediction) and host-based load prediction (host load prediction). Host load prediction is currently mainly used to achieve dynamic load balancing in a distributed / parallel environment, as well as host intrusion detection systems in the field of information security, to achieve prediction-based host load abnormality detection. For dynamic load balancing, the higher the host load prediction accuracy, the higher the accuracy of the balancing system for the distribution of work tasks among the computer nodes, and the more likely it is that tasks will be redistributed due to unbalanced distribution. Low, thereby effectively impro...

AI Technical Summary

Problems solved by technology

[0026] However, the disadvantage of this method is that, for historical sequences, each branch after wavelet decomposition uses BP neural network and AR prediction, while the literature "Research on Chaotic Time Series Prediction Based on Support Vector Machine and Wavelet Theory" (University of Science and Technology of China Doctoral dissertation. 2003) clearly pointed out that BP neural network has obvious defects compared with the support vector machine (SVM) method, such as learning is easy to fall into local minimum points, and it is easy to cause over-fitting and affect the generalization ability of the network, etc.

[0028] The defect of this prediction method is that the wavelet decomposition is performed on the historical sequence, and the wavelet decomposition only continues to decompose the low-frequency signal of the upper layer every time, and the high-frequency signal is no longer processed, so it is not as detailed as the wavelet packet decomposition, which affects the time of signal decomposition. frequency resolution, which is not conducive to predicting