A multi-agent method for streaming quality monitoring and analysis over media grid

Abstract

Media streaming is a promising technology which enables fast and adaptive delivery of media contents and allows clients to view videos online without waiting for the entire multimedia flies to be completely downloaded. In this paper, we address the issue of streaming quality measurement and assessment over a large scale network. We propose a multi-agent system for streaming quality monitoring and analysis (MASQMA) which can real-time monitor and analyze the quality of media streaming over a large scale EP network. Based on a decentralized infrastructure, such a system is scalable and flexible to meet versatile streaming applications without increasing the processing burden on the current media streaming systems. It allows users to real-time monitor the QoS with a variety of quality metrics. We conduct experiments and study the performance under various situations (e.g., bandwidth fluctuations, packet loss, and frame jitter) which are frequently encountered in Wide Area Networks. The results show the multi-agent architecture is practical and flexible to monitor and analyze streaming quality in real time. © 2007 IEEE.