EMBEDDED MICROCONTROLLERS CLASSIFYING SIGNATURES OF COMPONENTS FOR PREDICTIVE MAINTENANCE IN COMPUTER SERVERS

• US 20100332189A1
• Filed: 06/30/2009
• Published: 12/30/2010
• Est. Priority Date: 06/30/2009
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Sun Microsystems Incorporated (Oracle Corporation)
• Inventors: Donaldson, Darrell D., Urmanov, Aleksey M., Bougaev, Anton A.
• Granted Patent: US 8,290,746 B2
• Time in Patent Office: Days
• US Class Current: 702/186
• CPC Class Codes: G06F 11/0748 in a remote unit communicating with a single-box computer node experiencing an error/fault remote testing G06F11/2294
• CPC Class Codes: G06F 11/0751 Error or fault detection not based on redundancy power supply failures G06F1/30; network fault management H04L41/06
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206
• CPC Class Codes: G06F 11/3072 where the reporting involves data filtering, e.g. pattern matching, time or event triggered, adaptive or policy-based reporting

Abstract

Some embodiments of the present invention provide a system that analyzes data from a computer system. During operation, the system obtains the sensor data from a component in the computer system using a set of sensors. Next, the system transmits the sensor data to a microcontroller unit (MCU) coupled to the sensors and stores the sensor data in internal memory of the MCU. Finally, the system assesses the integrity of the component by analyzing the sensor data using a pattern-recognition apparatus in the MCU.

Claims

1. A method for analyzing sensor data from a computer system, comprising:

obtaining the sensor data from a component in the computer system using a set of sensors;

transmitting the sensor data to a microcontroller unit (MCU) coupled to the sensors;

storing the sensor data in internal memory of the MCU; and

assessing the integrity of the component by analyzing the sensor data using a pattern-recognition apparatus in the MCU.

2. The method of claim 1, further comprising:

further analyzing the sensor data using a system controller in the computer system.

3. The method of claim 2, wherein further analyzing the sensor data using the system controller involves at least one of:

transmitting a portion of the sensor data to the system controller; and

managing a fault in the computer system using the system controller.

4. The method of claim 2, wherein the sensor data is further analyzed using the system controller if the assessed integrity falls below a threshold.

5. The method of claim 1, wherein analyzing the sensor data using the pattern-recognition apparatus in the MCU involves at least one of:

constructing a waveform signature of the sensor data;

removing outliers in the sensor data;

performing feature extraction on the sensor data;

normalizing the sensor data;

performing missing attribute processing on the sensor data; and

classifying the component using the sensor data.

6. The method of claim 1, wherein the sensors correspond to microelectromechanical systems (MEMS) sensors.

7. The method of claim 1, wherein the sensor data comprises at least one of:

a load metric;

a CPU utilization;

an idle time;

a memory utilization;

a disk activity;

a transaction latency;

a temperature;

a voltage;

a fan speed;

a current; and

a vibration acceleration or displacement.

8. A system for analyzing sensor data from a computer system, comprising:

a set of sensors configured to obtain the sensor data from a component in the computer system; and

a microcontroller unit (MCU) coupled to the sensors, comprising;

internal memory configured to store the sensor data; and

a pattern-recognition module configured to assess the integrity of the component by analyzing the sensor data using a pattern-recognition apparatus in the MCU.

9. The system of claim 8, further comprising:

a system controller configured to further analyze the sensor data.

10. The system of claim 9, wherein further analyzing the sensor data using the system controller involves at least one of:

transmitting a portion of the sensor data to the system controller; and

managing a fault in the computer system using the system controller.

11. The system of claim 10, wherein the portion of the sensor data is transmitted to the system controller using a system bus on the computer system.

12. The system of claim 9, wherein the sensor data is further analyzed using the system controller if the assessed integrity falls below a threshold.

13. The system of claim 8, wherein the pattern-recognition apparatus in the MCU is configured to analyze the sensor data by:

constructing a waveform signature of the sensor data;

removing outliers in the sensor data;

performing feature extraction on the sensor data;

normalizing the sensor data;

performing missing attribute processing on the sensor data; and

classifying the component using the sensor data.

14. The system of claim 8, wherein the sensors correspond to microelectromechanical systems (MEMS) sensors.

15. The system of claim 8, wherein the sensor data comprises at least one of:

a load metric;

a CPU utilization;

an idle time;

a memory utilization;

a disk activity;

a transaction latency;

a temperature;

a voltage;

a fan speed;

a current; and

a vibration acceleration or displacement.

16. A computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for analyzing sensor data from a computer system, the method comprising:

obtaining the sensor data from a component in the computer system using a set of sensors;

transmitting the sensor data to a microcontroller unit (MCU) coupled to the sensors;

storing the sensor data in internal memory of the MCU; and

assessing the integrity of the component by analyzing the sensor data using a pattern-recognition apparatus in the MCU.

17. The computer-readable storage medium of claim 16, the method further comprising:

further analyzing the sensor data using a system controller in the computer system.

18. The computer-readable storage medium of claim 17, wherein further analyzing the sensor data using the system controller involves at least one of:

transmitting a portion of the sensor data to the system controller; and

managing a fault in the computer system using the system controller.

19. The computer-readable storage medium of claim 17, wherein the sensor data is further analyzed using the system controller if the assessed integrity falls below a threshold.

20. The computer-readable storage medium of claim 16, wherein analyzing the sensor data using the pattern-recognition apparatus in the MCU involves at least one of:

constructing a waveform signature of the sensor data;

removing outliers in the sensor data;

performing feature extraction on the sensor data;

normalizing the sensor data;

performing missing attribute processing on the sensor data; and

classifying the component using the sensor data.