Handling Session Classes for Predicting ASP.NET Performance Metrics

Distributed systems and web applications play an important role in computer science nowadays. The most common consideration is performance, because these systems must provide services with low response time, high availability, and certain throughput level. With the help of performance models, the performance metrics can be determined at the early stages of the development process. The goal of our work is to predict the response time, the throughput and the tier utilization of web applications, based on queueing models handling one and multiple session classes, with MVA and approximate MVA (Mean-Value Analysis) evaluation algorithm, in addition to balanced job bounds calculation. We estimated the model parameters based on one measurement. We implemented the MVA and the approximate MVA evaluation algorithm for closed queueing networks along with the calculation of the balanced job bounds with the help of MATLAB. We have tested a web application with concurrent user sessions in order to validate the models in ASP.NET environment.