Performance and Quality of Experience of Remote Access Laboratories

Abstract

Remote Access Laboratories have become important learning and teaching tools. This research presents a performance study that targets a specific remote-access architecture in a university environment. The system provides authenticated and mediated global remote access to virtual machines as well as hardware systems, which drive physical experiments. This paper presents system performance results that have been obtained with a set of automated and user-based tests. Key aims of the study were: To gain a better understanding of traffic that is caused by experiment usage; to get an indication of expected user performance; and to develop a measure to predict Quality of Experience, based on easily measurable Quality of Service parameters. The study emulates access bandwidth, round trip times of typical usage scenarios and provides results that allow classifying expected user performance. It demonstrates that failure rate is excellent measure of usability. Thin-client and remote desktop architectures are popular to separate the location of users and the actual data processing and use similar structures. Results of this study can be applied to these applications as well.