A rough wavelet network model with genetic algorithm and its application to aging forecasting of application server

Abstract

According to the characteristics of the operational behavior and runtime state of application sever, the resource consumption time series are observed and modeled by rough neural network (RWN). The dimensionality of input variables of RWN is reduced by information entropy reduction method, and the structure and parameters of RWN are optimized with adaptive genetic algorithm (GA). Judging by the model, we can get the aging threshold before application server failed and preventively maintenance the application server before systematic parameter value reaches the threshold. The experiments are carried out to validate the efficiency of the proposed forecasting model and show that the aging forecasting model based on RWN with adaptive genetic algorithm is superior to the neural network (NN) model and wavelet network (WN) model in the aspects of convergence rate and forecasting precision. ©2007 IEEE.