Abstract: The present disclosure describes a flexible technique to learn patterns in time series data that recur over time. The patterns may be used for simulation, predicting future behavior, or detecting anomalies in a system in which the data is collected. The technique incrementally detects daily, weekly, monthly, and yearly patterns. Each pattern is built over time instead of requiring all the data to be available at the beginning of the analysis. Instead of modeling each pattern explicitly, each pattern is described in the context of a day and formed based on time series data collected over an entire day. An example use of the technique is detecting load patterns in a computer system. A metric of system load such as CPU utilization may be collected periodically over a day. The techniques presented herein capture multiple daily models, each representing a different load pattern.

Abstract: Techniques for artificial intelligence driven configuration management are described herein. In some embodiments, a machine-learning process determines a feature set for a plurality of deployments of a software resource. Based on varying values in the feature set, the process clusters each of the plurality of deployments into a cluster of a plurality of clusters. Each cluster of the plurality of clusters comprises one or more nodes and each node of the one or more nodes corresponds to at least a subset of values of the feature set that are detected in at least one deployment of the plurality of deployments of the software resource. The process determines a representative node for each cluster of the plurality of clusters. An operation may be performed based on the representative node for at least one cluster.

Abstract: Techniques for efficiently generating aggregate distribution approximations are disclosed. In some embodiments, a system receives a plurality of piecewise approximations that represent different distributions of a set of values on at least one computing resource. Based on the plurality of piecewise approximations, a set of clusters are generated, within volatile or non-volatile memory, that approximate an aggregate distribution of the set of metric values on the at least one computing resource. The set of clusters is transformed, within volatile or non-volatile memory, to an aggregate piecewise approximation of a function for the set of metric values on the at least one computing resource.

Abstract: Techniques are described for automatically detecting and accommodating state changes in a computer-generated forecast. In one or more embodiments, a representation of a time-series signal is generated within volatile and/or non-volatile storage of a computing device. The representation may be generated in such a way as to approximate the behavior of the time-series signal across one or more seasonal periods. Once generated, a set of one or more state changes within the representation of the time-series signal is identified. Based at least in part on at least one state change in the set of one or more state changes, a subset of values from the sequence of values is selected to train a model. An analytical output is then generated, within volatile and/or non-volatile storage of the computing device, using the trained model.

Abstract: Techniques for generating distribution approximations with low memory footprints are disclosed. In some embodiments, a system receives a first set of values that measure one or more metrics of at least one computing resource. A set of clusters are generated, within volatile or non-volatile memory, that approximate a distribution of the first set of values measuring the one or more metrics of the at least one computing resource. The set of clusters is transformed, within volatile or non-volatile memory, to a piecewise approximation of a function for the first set of values.

Abstract: Techniques are described for optimizing scalability of analytics that use time-series models. In one or more embodiments, a stored time-series model includes a plurality of data points representing seasonal behavior in a training set of time-series data for at least one season. A target time for evaluating the time-series model is then determined, and the target time or one or more times relative to the target time are mapped to a subset of the plurality of data points. Based on the mapping, a trimmed version of the time-series model is generated by loading the subset of the plurality of data points into a cache, the subset of data points representing seasonal behavior in the training set of time-series data for a portion of the at least one season. A target set of time-series data may be evaluated suing the trimmed version of the time-series in the cache.

Abstract: Techniques are described for applying what-f analytics to simulate performance of computing resources in cloud and other computing environments. In one or more embodiments, a plurality of time-series datasets are received including time-series datasets representing a plurality of demands on a resource and datasets representing performance metrics for a resource. Based on the datasets at least one demand propagation model and at least one resource prediction model are trained. Responsive to receiving an adjustment to a first set of one or more values associated with a first demand: (a) a second adjustment is generated for a second set of one or more values associated with a second demand; and (b) a third adjustment is generated for a third set of one or more values that is associated with the resource performance metric.

Abstract: Techniques for predictive system remediation are disclosed. Based on attributes associated with applications of one or more system-selected remedial actions to one or more problematic system behaviors in a system (e.g., a database system), the system determines a predicted effectiveness of one or more future applications of a remedial action to a particular problematic system behavior, as of one or more future times. The system determines that the predicted effectiveness of the one or more future applications of the remedial action is positive but does not satisfy a performance criterion. Responsive to determining that the predicted effectiveness is positive but does not satisfy the performance criterion, the system generates a notification corresponding to the predicted effectiveness not satisfying the performance criterion.

Abstract: Techniques are described for generating predictive alerts. In one or more embodiments, a seasonal model is generated, the seasonal model representing one or more seasonal patterns within a first set of time-series data, the first set of time-series data comprising data points from a first range of time. A trend-based model is also generated to represent trending patterns within a second set of time-series data comprising data points from a second range of time that is different than the first range of time. A set of forecasted values is generated based on the seasonal model and the trend-based model. Responsive to determining that a set of alerting thresholds has been satisfied based on the set of forecasted values, an alert is generated.

Abstract: Techniques are described for generating seasonal forecasts. According to an embodiment, a set of time-series data is associated with one or more classes, which may include a first class that represent a dense pattern that repeats over multiple instances of a season in the set of time-series data and a second class that represent another pattern that repeats over multiple instances of the season in the set of time-series data. A particular class of data is associated with at least two sub-classes of data, where a first sub-class represents high data points from the first class, and a second sub-class represents another set of data points from the first class. A trend rate is determined for a particular sub-class. Based at least in part on the trend rate, a forecast is generated.

Abstract: Techniques are described for generating seasonal forecasts. According to an embodiment, a set of time-series data is associated with one or more classes, which may include a first class that represent a dense pattern that repeats over multiple instances of a season in the set of time-series data and a second class that represent another pattern that repeats over multiple instances of the season in the set of time-series data. A particular class of data is associated with at least two sub-classes of data, where a first sub-class represents high data points from the first class, and a second sub-class represents another set of data points from the first class. A trend rate is determined for a particular sub-class. Based at least in part on the trend rate, a forecast is generated.

Abstract: Systems and methods are described for efficiently detecting an optimal number of behaviors to model software system performance data and the aspects of the software systems that best separate the behaviors. The behaviors may be ranked according to how well fitting functions partition the performance data.

Abstract: Techniques are disclosed for summarizing, diagnosing, and correcting the cause of anomalous behavior in computing systems. In some embodiments, a system identifies a plurality of time series that track different metrics over time for a set of one or more computing resources. The system detects a first set of anomalies in a first time series that tracks a first metric and assigns a different respective range of time to each anomaly. The system determines whether the respective range of time assigned to an anomaly overlaps with timestamps or ranges of time associated with anomalies from one or more other time series. The system generates at least one cluster that groups metrics based on how many anomalies have respective ranges of time and/or timestamps that overlap. The system may preform, based on the cluster, one or more automated actions for diagnosing or correcting a cause of anomalous behavior.

Abstract: Systems and methods for unsupervised training and evaluation of anomaly detection models are described. In some embodiments, an unsupervised process comprises generating an approximation of a data distribution for a training dataset including varying values for a metric of a computing resource. The process further determines, based on the size of the training dataset, a first quantile probability and a second quantile probability that represent an interval for covering a prescribed proportion of values for the metric within a prescribed confidence level. The process further trains a lower limit of the anomaly detection model using a first quantile that represents the first quantile probability in the approximation of the data distribution and an upper limit using a second quantile that represents the second quantile probability in the approximation. The trained upper and lower limits may be used to monitor input data for anomalous behavior and, if detected, trigger responsive action(s).

Abstract: Techniques are disclosed for summarizing, diagnosing, and correcting the cause of anomalous behavior in computing systems. In some embodiments, a system identifies a plurality of time series that track different metrics over time for a set of one or more computing resources. The system detects a first set of anomalies in a first time series that tracks a first metric and assigns a different respective range of time to each anomaly. The system determines whether the respective range of time assigned to an anomaly overlaps with timestamps or ranges of time associated with anomalies from one or more other time series. The system generates at least one cluster that groups metrics based on how many anomalies have respective ranges of time and/or timestamps that overlap. The system may preform, based on the cluster, one or more automated actions for diagnosing or correcting a cause of anomalous behavior.

Abstract: Techniques are described for applying what-f analytics to simulate performance of computing resources in cloud and other computing environments. In one or more embodiments, a plurality of time-series datasets are received including time-series datasets representing a plurality of demands on a resource and datasets representing performance metrics for a resource. Based on the datasets at least one demand propagation model and at least one resource prediction model are trained. Responsive to receiving an adjustment to a first set of one or more values associated with a first demand: (a) a second adjustment is generated for a second set of one or more values associated with a second demand; and (b) a third adjustment is generated for a third set of one or more values that is associated with the resource performance metric.

Abstract: Techniques for analyzing, understanding, and remediating differences in configurations among many software resources are described herein. Machine learning processes are applied to determine a small feature set of parameters from among the complete set of parameters configured for each software resource. The feature set of parameters is selected to optimally cluster configuration instances for each of the software resources. Once clustered based on the values of the feature set of parameters, a graph is generated for each cluster of configuration instances that depicts the differences among the configuration instances within the cluster. An interactive visualization tool renders the graph in a user interface, and a management tool allows changes to the graph and changes to the configuration of one or more software resources.

Abstract: Techniques are disclosed for summarizing, diagnosing, and correcting the cause of anomalous behavior in computing systems. In some embodiments, a system identifies a plurality of time series that track different metrics over time for a set of one or more computing resources. The system detects a first set of anomalies in a first time series that tracks a first metric and assigns a different respective range of time to each anomaly. The system determines whether the respective range of time assigned to an anomaly overlaps with timestamps or ranges of time associated with anomalies from one or more other time series. The system generates at least one cluster that groups metrics based on how many anomalies have respective ranges of time and/or timestamps that overlap. The system may preform, based on the cluster, one or more automated actions for diagnosing or correcting a cause of anomalous behavior.

Abstract: Systems and methods are described for efficiently detecting an optimal number of behaviors to model software system performance data and the aspects of the software systems that best separate the behaviors. The behaviors may be ranked according to how well fitting functions partition the performance data.

Abstract: Techniques for artificial intelligence driven configuration management are described herein. In some embodiments, a machine-learning process determines a feature set for a plurality of deployments of a software resource. Based on varying values in the feature set, the process clusters each of the plurality of deployments into a cluster of a plurality of clusters. Each cluster of the plurality of clusters comprises one or more nodes and each node of the one or more nodes corresponds to at least a subset of values of the feature set that are detected in at least one deployment of the plurality of deployments of the software resource. The process determines a representative node for each cluster of the plurality of clusters. An operation may be performed based on the representative node for at least one cluster.