Affiliations: School of Computing, Informatics, Decision Systems
Engineering, Arizona State University, Tempe, AZ, USA
Note: [] Corresponding author: Nong Ye, School of Computing, Informatics,
Decision Systems Engineering, Arizona State University, Tempe, AZ 85287-8809,
USA. E-mail: nongye@asu.edu
Abstract: Various services running on computer and network systems compete for
shared system resources. Impacts of services on system activities, workloads
and performance need to be understood, modeled and used in many system planning
and control activities. Due to complex interactions of many system resources
(e.g., CPU, memory and network) and sharing of system resources by various
services running at the same time, it is challenging to uncover and model
relations of services with their resource workloads and resulting service
performance. This paper presents our methodology that uses statistical analysis
techniques to analyze empirical data of computer and network dynamics and
uncover significant variables of system activities, resource workloads and
service performance that are affected by services. Statistical modeling
techniques are also employed in our methodology to build quantitative models of
service impacts on system resource workloads and service performance. The
methodology is illustrated and tested on three services of voice data
communication, motion detection, and data encryption.
Keywords: Service impacts, resource workloads, service performance, computers and networks, statistical analysis and modeling
