Software aging analysis and prediction in a web server based on multiple linear regression algorithm

Abstract

In the last few years, software aging has been reported. The phenomenon of software aging is that the performance of the software system is degradation in a long-running state, which is the result of exhaustion of system resources, the accumulation of internal error conditions and so on. In order to counteract software aging, a technique, which called software rejuvenation, has been proposed, this procedure involves occasionally stopping a system process, cleaning its running environment and restarting it. Due to the direct and indirect costs incurred by software rejuvenation, when to carry out this action is very important. Traditionally, most scholars focused on time series or analytic methods to model software aging process, however, machine learning algorithm has been neglected. In this paper, we make a detailed analysis and predict about the web server parameters by multiple linear regression algorithm. Firstly, the aging phenomenon of the system is simulated by the pressure testing tool and then collecting data and preprocessed. Secondly, we fit time series models to the data collected and determine the trend of resource consumption. Thirdly, using the feature selection algorithm to select a subset set as the input parameters of the algorithm. Fourthly, using the multiple linear regression algorithm to analysis and predict the aging process. Finally, we evaluate the feasibility of the algorithm by evaluation metrics. The result shows that we can use this algorithm to predict the aging process in the allowable error range.