Abstract: A workload characterization system characterizes an exemplary business intelligence workload for use in sizing a hardware configuration required by a new database system running a similar business intelligence workload. The workload characterization system uses performance-oriented measurements to characterize an exemplary workload in terms of resource usage and performance metrics. The workload characterization system applies unsupervised data mining techniques to group individual business intelligence queries into general classes of queries based on system resource usage, providing insight into the resource demands of queries typical of a business intelligence workload. The general classes of queries are used to define an anticipated workload for a planned database system and to help identify the hardware required for the planned database system.

Abstract: Known techniques for characterizing network traffic are based on comparing new traffic with lists of older, known traffic. Performance degrades when such lists are long, as they are in Internet applications. Furthermore, the comparison process often requests a database lookup and hence must take place at the application level. In contrast, a technique is presented that uses geometric regions in a low-dimensional space to characterize network traffic. A packet of new traffic is classified by mapping of the header of the packet to a point in the low-dimensional space and performing a comparison of the point to the geometric regions. Comparison is cheap, and can be carried out in the protocol layer. The approach can be applied to intrusion and novelty detection and to automatic quality of service or content determination.