Anomaly Detection in Multivariate Non-stationary Time Series for Automatic DBMS Diagnosis
This work addresses the problem of diagnosing anomalies in DBMSs for database administrators, but it is incremental as it combines existing methods like autoencoders and statistical process control.
The paper tackles anomaly detection in database management systems by proposing an automatic diagnosis system that identifies abnormal periods and causal events using a deep autoencoder with statistical process control and time series similarity measures. Experiment results demonstrate the model's effectiveness, particularly with a batch temporal normalization layer, for generating diagnosis reports to aid DBMS configuration and SQL tuning.
Anomaly detection in database management systems (DBMSs) is difficult because of increasing number of statistics (stat) and event metrics in big data system. In this paper, I propose an automatic DBMS diagnosis system that detects anomaly periods with abnormal DB stat metrics and finds causal events in the periods. Reconstruction error from deep autoencoder and statistical process control approach are applied to detect time period with anomalies. Related events are found using time series similarity measures between events and abnormal stat metrics. After training deep autoencoder with DBMS metric data, efficacy of anomaly detection is investigated from other DBMSs containing anomalies. Experiment results show effectiveness of proposed model, especially, batch temporal normalization layer. Proposed model is used for publishing automatic DBMS diagnosis reports in order to determine DBMS configuration and SQL tuning.