Abstract: Techniques for predicting anomalies in forecasted time-series data are disclosed. A system. A system predicts whether a monitored computing system will experience anomalies by comparing forecasted values associated with components in the monitored computing system to threshold values. The system utilizes time-series machine learning models to forecast workloads of computing resources in the monitored computing system. The system trains and tests multiple different versions of a time-series model and selects the most accurate version to generate forecasts for a particular workload in the computing system. The system compares the forecasts to threshold values to predict anomalies. Based on detecting anomalies, the system generates recommendations for remediating predicted anomalies.

Abstract: Techniques for selecting and training candidate time-series models to forecast computational workloads are disclosed. A system creates a candidate set of time-series models for forecasting computing workloads by filtering the sets of parameter values to a number that meets system performance specifications. The system selects different sets of parameter values for different candidate models based on analyzing correlogram data. The system identifies in the correlogram data a set of one or more correlation values that (a) meet or exceed a threshold value, and (b) meet a distance criteria from the threshold value. The system trains the candidate set of time-series models with a training data set. The system selects the best-performing time-series model to generate forecasts for a particular computing resource in a computing system.

Abstract: Techniques for multi-layer forecasting of computational workloads are disclosed. A system identifies a level of granularity associated with a request to forecast a computational workload for a particular entity. The system obtains attribute data of computational resources at the specified level of granularity. The system determines whether computational resources, not specified in the request, should be included in a workload forecast. The system applies a time-series forecast model to time-series data obtained from computational resources associated with the request. The system presents one or more workload forecasts for computational workloads associated with the request.

Abstract: Techniques for time-series analysis for forecasting computational workloads are disclosed. A resource management system monitors a computing system and obtains metrics data from the computing system. The metrics data is stored as a set of historical data points of a data set. A first portion of the set of historical data points comprise an outlier that does not correspond to a seasonality pattern associated with a second portion of the set of historical data points. The resource management system tests a first time-series model that incorporates a first exogenous variable corresponding to a first exogeneous factor to determine that the first time-series model fits both the first portion of the set of historical data points and the second portion of the set of historical data points within an error threshold. Then, the resource management system selects the first time-series model to predict future data points of the data set.

Abstract: Techniques for time-series analysis for forecasting computational workloads are disclosed. A resource management system monitors a computing system and obtains metrics data from the computing system. The metrics data is stored as a set of historical data points of a data set. A first portion of the set of historical data points comprise an outlier that does not correspond to a seasonality pattern associated with a second portion of the set of historical data points. The resource management system tests a first time-series model that incorporates a first exogenous variable corresponding to a first exogeneous factor to determine that the first time-series model fits both the first portion of the set of historical data points and the second portion of the set of historical data points within an error threshold. Then, the resource management system selects the first time-series model to predict future data points of the data set.

Abstract: An incident predictor system is described herein for predicting impactful incidents in which server computer system operations fail or perform poorly. According to one embodiment of the invention, the incident prediction system trains a generalized linear model (GLM) to predict when a system health indicator will reach a level that represents an incident for the server system.

Abstract: An incident predictor system is described herein for predicting impactful incidents in which server computer system operations fail or perform poorly. According to one embodiment of the invention, the incident prediction system trains a generalized linear model (GLM) to predict when a system health indicator will reach a level that represents an incident for the server system.