Method for building LS-SVM prediction model based on chaotic search

Abstract

The invention relates to a method for building an LS-SVM prediction model based on the chaotic search. The method includes the following steps: (A) building a sample training data set; (B) calculating coefficients of the model; (C) conducting optimization with the chaotic search improvement algorithm, and obtaining the minimum value and the optimal chaotic variable of a to-be-optimized function; (D) determining the optimized LS-SVM prediction model; (E) updating a sample. By means of the method, the LS-SVM self-adaptation resource prediction model is built after parameters of the model are optimized with the chaotic search improvement algorithm, the operating state of prediction objects in cloud calculation can be dynamically predicted, prediction results have good adaptability, and it can be guaranteed that the prediction resultsmoreapproximate to true values of the prediction objects. The sensibility of the chaotic search to the initial value is remitted through the model; in addition, in the chaotic iterative search process, the second-time search can be rapidly carried out in the optimal solution neighborhood through the adjustment on the chaotic variable, the search efficiency is improved, and the possibility of being caught into the local optimum is decreased.

Description

technical field [0001] The invention relates to a resource prediction technology, in particular to a method for establishing a chaotic search-based LS-SVM prediction model. Background technique [0002] The improvement of network infrastructure cannot meet people's endless demand for network resources, which leads to many undesirable phenomena such as network performance degradation and response delay. In fact, in the network, on the one hand, some resources are overused, and on the other hand, a large number of resources are idle. Cloud computing uses virtualization technology to construct resource pools of various underlying physical resources in the network, and distributes user requests to different resource pools for on-demand services and on-demand billing. How to reasonably allocate and schedule underlying physical resources in the cloud platform, effectively improve service quality and system performance, and ensure load balancing has become a challenge for the indu...

AI Technical Summary

Problems solved by technology

[0002] The improvement of network infrastructure cannot meet people's endless demand for network resources, which leads to many undesirable phenomena such as network performance degradation and response delay

In fact, in the network, on the one hand, some resources are overused, and on the other hand, a large number of resources are idle.

Images