IP Library Granted Patent US 7,558,985
Granted Patent B2
US 7,558,985 · App. 11/353,559 · Granted Jul 7, 2009

High-efficiency time-series archival system for telemetry signals

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 7,558,985
App. No.
11/353,559
Granted
Jul 7, 2009
Kind
B2
Abstract

In one embodiment, a method and apparatus for high-efficiency time-series archiving for computer server telemetry signals is disclosed. The method includes selecting one or more telemetry signals of a plurality of telemetry signals by a sequential probability ratio test (SPRT) algorithm, the SPRT algorithm identifying the one or more telemetry signals as not consistent with normal behavior of the plurality of telemetry signals, injecting synthetic samples around the selected one or more telemetry signals to create a continuous time series telemetry sample, and analyzing the continuous time series telemetry sample to identify leading indicators of faults in the target. Other embodiments are also disclosed.

Claims (26)

1. A method comprising:

selecting one or more telemetry signals of a plurality of telemetry signals by a sequential probability ratio test (SPRT) algorithm, the SPRT algorithm identifying the one or more telemetry signals as not consistent with normal behavior of the plurality of telemetry signals, wherein a control tower appliance connected to a target performs the SPRT algorithm to select the one or more telemetry signals;

injecting synthetic samples around the selected one or more telemetry signals to create a continuous time series telemetry sample; and

analyzing the continuous time series telemetry sample to identify leading indicators of faults in the target.

2. The method of claim 1 , further comprising archiving the selected one or more telemetry signals for later injecting and analyzing.

3. The method of claim 1 , wherein a sensor in the target collects the plurality of telemetry signals to be selected by the SPRT algorithm.

4. The method of claim 3 , wherein the target is a server.

5. The method of claim 3 , wherein the target performs the SPRT algorithm to select the one or more telemetry signals.

6. The method of claim 1 , wherein the normal behavior is based on a distribution of the plurality of telemetry signals with an average mean, and wherein the SPRT algorithm selects the one or more telemetry signals if they have at least one of a higher or a lower mean than the average mean.

7. The method of claim 1 , wherein the normal behavior is based on a distribution of the plurality of telemetry signals with an average variability, and wherein the SPRT algorithm selects the one or more telemetry signals if they have at least one of a larger or a smaller variability than the average variability.

8. The method of claim 1 , wherein the synthetic samples are generated to adhere to a target distribution of the plurality of telemetry signals, the target distribution having a same mean and a same variance as the plurality of telemetry signals that were not selected.

9. An article of manufacture, comprising a machine-accessible medium including data that, when accessed by a machine, cause the machine to perform operations comprising:

selecting one or more telemetry signals of a plurality of telemetry signals by a sequential probability ratio test (SPRT) algorithm, the SPRT algorithm identifying the one or more telemetry signals as not consistent with normal behavior of the plurality of telemetry signals, wherein a control tower appliance connected to a target performs the SPRT algorithm to select the one or more telemetry signals;

injecting synthetic samples around the selected one or more telemetry signals to create a continuous time series telemetry sample; and

analyzing the continuous time series telemetry sample with at least one of pattern recognition technique, a data mining technique, and a graphical representation to identify leading indicators of faults in the target.

10. The article of manufacture of claim 9 , wherein a sensor in the target collects the plurality of telemetry signals to be selected by the SPRT algorithm.

11. The article of manufacture of claim 9 , wherein the target performs the SPRT algorithm to select the one or more telemetry signals.

12. The article of manufacture of claim 9 , wherein the synthetic samples are generated to adhere to a target distribution of the plurality of telemetry signals, the target distribution having a same mean and a same variance as the plurality of telemetry signals that were not selected.

13. An apparatus, comprising:

a sensor in a target to generate a plurality of telemetry signals representing a performance metric of the target;

an analysis component to receive one or more telemetry signals of the plurality of telemetry signals in order to inject synthetic samples around the selected one or more telemetry signals to create a continuous time series telemetry sample;

wherein a sequential probability ratio test (SPRT) algorithm is applied to the plurality of telemetry signals to identify the one or more telemetry signals, the one or more telemetry signals being inconsistent with normal behavior of the plurality of telemetry signals, and wherein a control tower connected to the target is to apply the SPRT algorithm to the plurality of telemetry signals received from the target and is to transmit the one or more telemetry signals to the analysis component.

14. The apparatus of claim 13 , wherein the target to apply the SPRT algorithm to the plurality of telemetry signals and to transmit the identified one or more telemetry signals to the control tower appliance.

15. The apparatus of claim 13 , wherein the normal behavior is based on a distribution of the plurality of telemetry signals with an average mean, and wherein the SPRT algorithm selects the one or more telemetry signals if they have at least one of a higher or a lower mean than the average mean.

16. The apparatus of claim 13 , wherein the normal behavior is based on a distribution of the plurality of telemetry signals with an average variability, and wherein the SPRT algorithm selects the one or more telemetry signals if they have at least one of a larger or a smaller variability than the average variability.

17. The apparatus of claim 13 , wherein the synthetic samples are generated to adhere to a target distribution of the plurality of telemetry signals, the target distribution having a same mean and a same variance as the plurality of telemetry signals that were not selected.

Assignments (2)
MERGER AND CHANGE OF NAME Recorded Dec 16, 2015
From: ORACLE USA, INC.; SUN MICROSYSTEMS, INC.; ORACLE AMERICA, INC.
To: ORACLE AMERICA, INC.
Reel/Frame 037304/0183 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 13, 2006
From: GREAVES, JON D.; WHISNANT, KEITH A.; GROSS, KENNY C.
To: SUN MICROSYSTEMS, INC.
Reel/Frame 017587/0112 →