Predictive models for proactive network management: application to a production Web server

Proactive management holds the promise of taking corrective actions in advance of service disruptions. Achieving this goal requires predictive models so that potential problems can be anticipated. Our approach builds on previous research in which HTTP operations per second are studied in a Web server. As in this prior work, we model HTTP operations as two subprocesses, a (deterministic) trend subprocess and a (random but stationary) residual subprocess. Herein, the trend model is enhanced by using a low-pass filter. Further, we employ techniques that reduce the required data history, thereby reducing the impact of changes in the trend process. As in the prior work, an autoregressive model is used for the residual process. We study the limits of the autoregressive model in the prediction of network traffic. Then we demonstrate that long-range dependencies remain in the residual process even after autoregressive components are removed, which impacts our ability to predict future observations. Last, we analyze the validity of assumptions employed, especially the normality assumption