发明名称 Transient detection for predictive health management of data processing systems
摘要 Systems, methods, and other embodiments associated with transient detection for predictive health management are described. In one embodiment, a method includes receiving a health signal from a data outlet. The health signal corresponds to a derivative variable derived from a combination of data processing system metrics not exposed beyond the data outlet. A transient is detected in the health signal. In response to detecting the transient, the method includes performing a corrective action. The example method may also include detecting the transient in a health signal from a data processing system by collecting historical values of the health signal; selecting a first statistical model that best fits the historical values; receiving a present value of the health signal; and applying the first statistical model to the present value of the health signal to determine whether the present value of the health signal is a transient.
申请公布号 US9116804(B2) 申请公布日期 2015.08.25
申请号 US201213598783 申请日期 2012.08.30
申请人 ORACLE INTERNATIONAL CORPORATION 发明人 Urmanov Aleksey M.;Bougaev Anton A.
分类号 G06F17/30;G06F11/07;G06F11/34;H04L12/24;G06F15/16 主分类号 G06F17/30
代理机构 Kraguljac Law Group, LLC 代理人 Kraguljac Law Group, LLC
主权项 1. A non-transitory computer-readable medium storing computer-executable instructions that when executed by a computer cause the computer to perform a method, the method comprising: with a component external to a data processing system, receiving a derivative value from a data outlet that isolates data processing system metrics from detection by the component, wherein the derivative value comprises a combination of the data processing system metrics that are not exposed beyond the data outlet; collecting historical values for the derivative value during operation of the data processing system; selecting a statistical model that best fits the historical values from between at least two statistical models; accumulating a cumulative threshold measure by: calculating an update term based on a difference between a mean derivative value of the selected statistical model and a present value of the derivative value; andadding the update term to a present value of the cumulative threshold measure; when the cumulative threshold measure exceeds an upper threshold, detecting a transient; and in response to detecting the transient, performing a corrective action.
地址 Redwood Shores CA US