Detection of abnormal resource usage in a data center

1. A method performed by a computer system for generating a classifier to identify abnormal resource usage in a data center, the method comprising:

providing resource data for a plurality of resources at various times;

for each of the plurality of resources,

for each of a plurality of times, identifying current resource usage data for that resource for that time and extracting features from past resource usage data prior to that time; and

generating a prediction model for that resource from the current resource usage data and the extracted features for the times to predict resource usage data for that resource at a current time given features extracted from past resource usage data;

generating from the resource usage data for the resources error statistics for the prediction models; and

establishing from the error statistics an abnormal resource usage criterion.

2. The method of claim 1 further comprising:

for each of the plurality of resources, providing current resource usage data for a current time, extracting features from the past resource usage data, generating by the prediction model for that resource predicted resource usage data for the current time, and determining error between the predicted resource usage data and the current resource usage data; and

when the determined errors satisfy the abnormal resource usage criterion, indicating abnormal resource usage has occurred.

3. The method of claim 1 wherein a resource is cores of the data center and the resource usage data for the cores is the number of cores in use at the data center.

4. The method of claim 3 wherein the extracted features for the number of cores include the average number of cores in use during past intervals.

5. The method of claim 1 wherein a resource is subscriptions to the data center and the resource usage data for the subscriptions is the number of new subscriptions to the data center.

6. The method of claim 5 wherein the extracted features for subscriptions is the number of new subscriptions during past intervals.

7. The method of claim 1 wherein the error statistics are generated using cross-validation of a prediction model.

8. The method of claim 1 further comprising regenerating the classifier on a periodic basis.

9. The method of claim 1 wherein the error statistics include a mean of the errors for each resource and a covariance for each pair of resources and the abnormal resource usage criterion is based on a p-value for the error statistics.

10. The method of claim 1 further comprising identifying and filling in gaps in the provide resource usage data.

11. A computer-readable storage medium storing computer-executable instructions for controlling a computing system to identify abnormal resource usage in a data center, the computer-executable instructions comprising instructions that:

access a prediction model for each of a plurality of resources and an abnormal resource usage criterion, the prediction models being generated from resource usage data of the data center, the abnormal resource usage criterion established based on error statistics for the prediction models;

for each of a plurality of resources of the data center,

access current resource usage data for that resource for a current time;

extract features from the past resource usage data for one or more resources;

predict by the prediction model for that resource predicted resource usage data for the current time based on the extracted features; and

determine an error between the predicted resource usage data and the current resource usage data; and

when the determined errors satisfy the abnormal resource usage criterion, indicate an abnormal resource usage has occurred.

12. The computer-readable storage medium of claim 11 wherein a resource is cores of the data center and a resource is subscriptions to the data center.

13. The computer-readable storage medium of claim 11 wherein the extracted features for the number of cores include the average number of cores in use during past intervals and the extracted features for subscriptions include the number of new subscriptions received during past intervals.

14. The computer-readable storage medium of claim 11 wherein the computer-executable instructions further comprise instructions that, for each of the plurality of resources of the data center, collect resource usage data for that resource at each of a plurality of intervals and wherein the extracted features include resource usage data for time intervals of one hour, one day, and one week prior to the current time.

15. A computer system that identifies abnormal resource usage in a data center, the computer system comprising:

one or more computer-readable storage media storing computer-executable instructions that:

access current resource usage data for a current time and features of past resource usage data for resources of the data center; and

apply a classifier to the current resource usage data and the features to determine whether the current resource usage data represents an abnormal resource usage, wherein the classifier,

for each of a plurality of resources of the data center, predicts using a prediction model for that resource predicted resource usage data for the current time based on the features and determines an error between the predicted resource usage data and the current resource usage data; and

when the determined errors satisfy the abnormal resource usage criterion, indicates an abnormal resource usage has occurred; and

one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage media.

16. The computer system of claim 15 wherein computer-executable instructions further include instructions for generating the classifier that:

for each of the plurality of resources,

for each of a plurality of times, identify current resource usage data for that resource for that time and extract features from past resource usage data for one or more resources; and

generate a prediction model for that resource from the current resource usage data and the extracted features for the times to predict resource usage data for that resource at a current time given features extracted from past resource usage data;

generate from the resource usage data for the resources error statistics for the prediction models; and

establish from the error statistics an abnormal resource usage criterion.

17. The computer system of claim 16 wherein the classifier is regenerated at various times using resource usage data that includes resource usage data collected since the classifier was last generated.

18. The computer system of claim 16 wherein the prediction models are generated using a linear regression technique.

19. The computer system of claim 15 wherein a resource is cores of the data center and a resource is subscriptions to the data center and the extracted features for the number of cores include the average number of cores in use during past intervals and the extracted features for subscriptions include the number of new subscriptions during past intervals.

20. The computer system of claim 15 wherein the one or more computer-readable storage media further include computer-executable instructions that identify and fill in gaps in the past resource usage data.