Prediction of failure occurrence time based on system log message pattern learning

In order to avoid failures or diminish the impact of them, it is important to deal with them before its occurrence. Some existing approaches for online failure prediction are insufficient to handle the upcoming failures beforehand, because they cannot predict the failures early enough to execute workaround operations for failure. To solve this problem, we have developed a method to estimate the prediction period (the time period when a failure is expected to occur). Our method identifies the message patterns showing predictive signs of a certain failure through Bayesian learning from log messages and past failure reports. Using these patterns it predicts the occurrence of failures and their prediction period with sufficient interval. We conducted the evaluation of our approach with log data obtained from an actual system. The results shows that our method predicted the occurrence of failure with sufficient interval (60 minutes before the occurrence of failures) and sufficient accuracy (precision: over 0.7, recall: over 0.8).