Grid Resource Prediction Based On Support Vector Regression And Simulated Annealing Algorithms

During 1990s, rapid development and widespread use of internet helped to produce a novel distributed computing system-grid. Grid computing derives its name from the analogy with the electricity grid. A commonly used definition of grid is the internet-based infrastructure that aggregates geographically distributed and heterogeneous resources as an ensemble to solve large-scale problems. In the grid environment, the resources are provided and managed by different administrators. The availability of grid resources vary over time and such changes will affect the performance of the tasks running on the grid. If we can predict the future information of grid resources, the scheduler will be able to manage the grid resources more effectively.This study focused on grid resources prediction and talked to the designing the system architecture, the prediction algorithms of grid resources prediction and grid resources optimization.In grid resource prediction, many relevant research models have been developed and have generated accurate prediction in practice. These prediction models that provide future resources information generally apply the time series prediction models which mostly use statistical and artificial intelligent approach.Resource Prediction System (RPS) is a project in which grid resources are modeled as linear time series process. Multiple conventional linear models are evaluated; the simple AR model is the best model of this class because of its good predictive power and low overhead.The Network Weather Service (NWS) uses a combination of several models for the prediction of one resource. NWS allows some adaptation by dynamically choosing the model that has performed the best recently for the next prediction, but its adaptation is limited to the selection of a model from several candidates that are conventional statistical models.With the development of artificial neural networks (ANNs), ANNs have been successfully employed for modeling time series. Eswaradass et al.applied ANNs to grid resources prediction successfully. Experimental results showed the ANN approach provided an improved prediction over that of NWS. However, ANNs have some drawbacks ,such as hard to pre-select the system architecture, spending much training time, and lacking knowledge representation facilities.In 1995, support vector machine (SVM) was developed by Vapnik to provide better solutions than ANNs. SVM can solve classification problems (SVC) and regression problems (SVR) successfully and effectively. However, the determination of SVR's parameters is an open problem and no general guidelines are available to select these parameters. Simulated annealing algorithm (SA) is an effective optimization algorithm, and it has been successfully applied to various NP-hard combinatorial optimization problems. Therefore, in this study, SA was adopted to automatically determine the optimal hyper-parameters of SVR.This paper described the working principle of simulated annealing and Characteristics of simulated annealing. a key point of this article. selected the most suitable to carry out optimization of support vector regression machine In a variety of simulated annealing algorithm. This paper described two common typical of simulated annealing algorithm:(1)Very fast simulated annealing algorithm,(2)simulated annealing with memory algorithm. In the application of two simulated annealing algorithm to optimize the process of support vector machines found some deficiencies. Therefore, this paper proposed an improved two-stage simulated annealing algorithm.the Improved two-stage simulated annealing algorithm can be ideal not only optimized parameters, but also had a good time more efficiently.This paper also detailed the architecture and principle of simulated annealing algorithm and support vector.Owing to the higher performance of SA in experiments, we used SA to optimize the parameters of support vector machine. The experimental results showed that SA was effective and converged rapidly. The optimized support vector machine worked well in grid resources prediction, so it was suitable for grid resources prediction system.Accurate grid resources prediction is crucial for a grid scheduler. In this study, support vector regression (SVR), which is a novel and effective regression algorithm, is applied to grid resources prediction. In order to build an effective SVR model, SVR's parameters must be selected carefully. Therefore, we develop a simulated annealing algorithm-based SVR (SA-SVR) model that can automatically determine the optimal parameters of SVR with higher predictive accuracy and generalization ability simultaneously. Currently, Grid is in the process of development. With the standardizing of grid framework, some new feathers will appear and the performance of grid will be better. Grid is far cheaper than mainframe computer, and a well-managed grid does not work worse than mainframe computer. Even, sometimes gird works better than mainframe. Accordingly, Grid application has promising future. OSGA has defined grid monitoring and grid prediction modules. Hence, GGF also attaches great importance to grid monitoring and prediction. Therefore, it is worthy to study grid monitoring and prediction deeply.