The secured Internet service is one driving force behind the continuous exponential growth of the Internet. Fundamental to the build of robust and high-performance secured Internet services is a thorough understanding of the characteristics of the end-to-end performance perceived by remote users. Moreover, there is increasing demand for performance management in secured Internet services to provide statistical quality of service (QoS) guarantees. This project investigates a set of innovative techniques to passively monitor and to actively manage end-to-end performance of secured Internet services. These techniques rely on the service characteristics derived by analyzing interactions between networks and servers. Aided by such an characterization, the set of proposed techniques accurately monitor the real-time performance. With the support of the real-time performance, the proposed techniques then adaptively provide QoS guarantees. The contributions of the project include devising effective and efficient techniques for performance monitoring and management. It involves a comprehensive behavior characterization of browsers, networks, and servers based on new findings of secured Internet services as well as results from previous research. This project also explores ways of utilizing the derived behavior characteristics to design innovative techniques to monitor service performance. Techniques for adaptive performance management are also developed. Broader impacts of the project include the publication and dissemination of research results and developed software artifacts. The research enables collaborative research opportunities for students and faculty in the program, as well as undergraduate science and engineering students in South Dakota, an EPSCoR state.
