Software Aging Prediction based on Extreme Learning Machine

In the research on software aging and rejuvenation, one of the most important questions is when to trigger the rejuvenation action. And it is useful to predict the system resource utilization state efficiently for determining the rejuvenation time. In this paper, we propose software aging prediction model based on extreme learning machine (ELM) for a real VOD system. First, the data on the parameters of system resources and application server are collected. Then, the data is preprocessed by normalization and principal component analysis (PCA). Then, ELMs are constructed to model the extracted data series of systematic parameters. Finally, we get the predicted data of system resource by computing the sum of the outputs of these ELMs. Experiments show that the proposed software aging prediction method based on wavelet transform and ELM is superior to the artificial neural network (ANN) and support vector machine (SVM) in the aspects of prediction precision and efficiency. Based on the models employed here, software rejuvenation policies can be triggered by actual measurements.