Detection of abnormal resource usage in a data center
A resource and data technology, applied in the field of detecting abnormal resource usage in the data center, can solve the problem of high cost
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0015] In some embodiments, an abnormal activity detection ("AAD") system detects when resource usage at a data center is so high that the resource usage may be fraudulent. Such fraudulent use may be referred to as a "spoof storm" at the data center because significant fraudulent use occurs suddenly. The AAD system detects spoofing storms using a classifier for classifying whether current resource usage indicates abnormal activity resulting in abnormal resource usage at the data center. To generate classifiers, the AAD system can generate predictive models for various resources to predict normal resource usage given past resource usage. The AAD system uses resources that may increase during a spoof storm, such as number of cores in use, number of new subscriptions, outbound traffic, disk usage, etc. The AAD system can also generate an error model for estimating the error in the prediction model based on a comparison of the predicted resource usage to the actual resource usage...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


