Lightbend, Inc.

Uday K Chettiar

Omer Emre Velipasaoglu

Arun Kejariwal

Amit Sasturkar

Vishal Surana

Dhruv Hemchand Jain

Mohamed A Abdelhafez

Alan Honkwan Ngai

Craig David Upson

The technology disclosed relates to building ensemble analytic rules for reusable operators and tuning an operations monitoring system. In particular, it relates to analyzing a metric stream by applying an ensemble analytical rule. After analysis of the metric stream by applying the ensemble analytical rule, quantized results are fed back for expert analysis. Then, one or more type I or type II errors are identified in the quantized results, and one or more of the parameters of the operators are automatically adjusted to correct the identified errors. The metric stream is further analyzed by applying the ensemble analytical rule with the automatically adjusted parameters.

Tuning context-aware rule engine for anomaly detection

The technology disclosed relates to differential analysis of sets of time series pairs. In particular, it relates to building estimators of magnitude of difference between two time series. After the basic estimators are built, they are combined into ensemble estimators using linear or nonlinear prediction models to improve their accuracy. In one application, the ensemble is used for estimating the magnitudes of difference over sets of metric pairs observed from distributed applications and systems running over a computer network. The metric pairs are then ranked in decreasing order of magnitude of difference to guide an operator in prioritizing his root cause analysis of faults, thereby reducing the time-to-resolution of problems.

Resource and metric ranking by differential analysis

The technology disclosed relates to detecting anomalous behavior of network components in a complex network setting. In particular, it relates to processing a historical stream of latency sample points by applying a wide aperture temporal aggregator that summarizes historical stream in a reduced number of summary points, based on a moving window, with a metric date-time indicator associated with each summary point, processing a current stream of latency sample points, including, applying a narrow aperture temporal aggregator that summarizes the current stream in a reduced number of summary points, based on a moving window, comparing summary points from the current stream to summary points from the historical stream at a date-time indicator with a predetermined periodic-temporal relationship to a particular current stream summary point, and quantizing the comparison to at least three comparison values of low-range, normal and high-range and recording at least low-range and high-range quantized comparisons for analysis.

Context-aware rule engine for anomaly detection

Growing community of inventors

Mountain View, CA, United States of America

Uday K Chettiar