Multicast Congestion Control for Multimedia Collaborative Applications in Packet Switched Networks Emad Mohamed * Hussein Abdel-Wahab Computer Science Department Old Dominion University Norfolk, VA 23529 USA emohamed@uaeu.ac.ae, wahab@cs.odu.edu * The author has moved to the College of Information Technology, United Arab Emirates University. Abstract We investigate the problem of congestion control for multicast traffic over datagram packet switched networks and present an end-to-end solution to it. The focus of our study is on multimedia collaborative applications. The group members of such applications, typically, span a heterogeneous inter-network, where routers and links may vary widely in their capabilities. Recently, two end-to-end approaches have been introduced for multicast congestion control: hierarchical multicast (a window based approach), and multiple groups (a rate based approach). In this paper, we introduce a new end-to-end technique for multicast congestion control that utilizes multiple groups and is window based. We have conducted an analytical study to evaluate our work, which shows encouraging results compared to other techniques. 1. Introduction The success of many components of multimedia collaborative applications depends heavily on the performance of the underlying network. For example, a timely delivery of the data to the different participants of a collaborative session is essential to many components such as audio and video. Also, a low packet loss helps increase the quality of the perceived audio and video streams. In many situations some parts of the network may get congested, degrading the overall performance of the network. For best effort networks where there is no admission control for network traffic, all applications running over the network should cooperate to avoid congestion and control it would it happen [10]. In this paper, we consider end-to-end solutions for congestion control in multicast communications for multimedia collaborative applications over datagram packet switched networks. Normally, the participants of a collaborative session may span the entire network, which we assume heterogeneous (routers differ in capabilities and links differ in bandwidths) and dynamics (workload varies with time). We introduce a solution for controlling congestion by organizing the destinations into multiple multicast groups based on the capabilities of the destinations and their network paths from the source. Finally, we present an analytic study to evaluate our solution. The rest of this paper is organized as follows. General principles of congestion control are given in Section 2. Section 3 is an introduction to multicast congestion control. In Section 4, we present our new technique. In Section 5, we give a model for multicast congestion control and we present an analytical study that evaluates various approaches to this problem. Section 6 presents the conclusions for this work. 2. Principles and techniques of congestion control Figure 1. Congestion: incoming traffic ≥ outgoing traffic Congestion occurs when the incoming traffic at a node approaches or exceeds that of the outgoing traffic (Figure. 1). In such case, the length of the queue at this node grows indefinitely. Since routers’ queues are of finite lengths, some of the incoming traffic may get dropped. The problem gets even worse when the sources try to compensate for the lost packets and level up their transmission rates. Increasing the queue size may not help much, as it has been shown in a previous study that even with an infinite queue size congestion gets worse, since by router Incoming Outgoing traffic