The up-coming Gbps high-speed networks are expected to support a wide range of communication-intensive, real-time multimedia applications. The requirement for timely delivery of digitized audio-visual information raises new challenges for the next generation integrated-service broadband networks. One of the key issues is the Quality-of-Service (QoS) routing. It selects network routes with sufficient resources for the requested QoS parameters. The goal of routing solutions is two-fold: (1) satisfying the QoS requirements for every admitted connection and (2) achieving the global efficiency in resource utilization. Many unicast/multicast QoS routing algorithms were published recently, and they work with a variety of QoS requirements and resource constraints. Overall, they can be partitioned into three broad classes: (1) source routing, (2) distributed routing and (3) hierarchical routing algorithms. In this paper we give an overview of the QoS routing problem as well as the existing solutions. We present the strengths and the weaknesses of different routing strategies and outline the challenges. We also discuss the basic algorithms in each class, classify and compare them, and point out possible future directions in the QoS routing area.

Multicast services have been increasingly used in large scale continuous media applications. The quality-of-service (QoS) requirements of these continuous media applications prompt the necessity for QoS-driven, constraint-based multicast routing. This article provides a comprehensive overview of existing multicast routing algorithms, protocols, and their QoS extension. In particular, we classify multicast routing problems according to their optimization functions and performance constraints, present basic routing algorithms in each problem class, and discuss their strengths and weakness. We also categorize existing multicast routing protocols, outline the issues and challenges in providing QoS in multicast routing, and point out possible future research directions.

The future Internet is expected to support multicast applications with quality of service (QoS) requirements. To facilitate this, QoS multicast routing protocols are pivotal in enabling new receivers to join a multicast group. However, current routing protocols are either too restrictive in their search for a feasible path between a new receiver and the multicast tree, or burden the network with excessive overhead. We propose QMRP, a new QoS-aware Multicast Routing Protocol. QMRP achieves scalability by significantly reducing the communication overhead of constructing a multicast tree, yet it retains a high chance of success. This is achieved by switching between single-path routing and multiple-path routing according to the current network conditions. The high level design of QMRP makes it operable on top of any unicast routing algorithm in both intra-domain and interdomain. Its responsiveness is improved by using a termination mechanism which detects the failure as well as the succes...

All of the advantages of application-layer overlay networks arise from two fundamental properties: (1) The network nodes in an overlay network, as opposed to lower-layer network elements such as routers and switches, are end systems and have capabilities far beyond basic operations of storing and forwarding; and (2) The overlay topology, residing above a densely connected IP-layer wide-area network, can be constructed and manipulated to suit one's purposes. In this paper, we seek to significantly...

In this report we present our work on a receiver-initiated approach called RIMQoS to support multicast with multiple QoS constraints and dynamic memberships. Assuming link-state information is available, a receiver computes a path to join the multicast tree rooted at the source. It then sends join request along the path to join the group. We first present the operation of our approach in an intra-domain setting with delay constraint. Then we introduce an algebraic formulation for multiple QoS constraints to show how to determine if QoS requirements for a new receiver can be satisfied at an intermediate node along the join path and how to adjust the tree without breaking QoS requirements for existing members if they are not. It attempts to minimize the cost of the tree by letting a node to join the tree via a low-cost path and may later switch to a higher-cost but more QoS stringent path when necessary. Our scheme builds multicast tree incrementally and thus supports fully dynamic memberships. It also supports of heterogeneous receivers seamlessly. Moreover, it can support any number of arbitrary QoS metrics without assuming any dependencies among them, if they satisfy some normal mathematical property. If implemented as a distributed routing protocol, our approach doesn't require any node to have explicit knowledge of the multicast tree topology, thus it scales well for multicast of large group. Simulation studies have been carried out to study its behavior and compare its performance with other schemes.

In this paper, we measure and model the distribution of multicast group members. Multicast research has traditionally been plagued by a lack of real data and an absence of a systematic simulation methodology. Although temporal group properties have received some attention, the location of group members has not been measured and modelled. However, the placement of members can have significant impact on the design and evaluation of multicast schemes and protocols as shown in previous studies. In our work, we identify properties of members that reflect their spatial clustering and the correlation among them (such as participation probability, and pairwise correlation). Then, we obtain values for these properties by monitoring the membership of network games and large audiovideo broadcasts from IETF and NASA. Finally, we provide a comprehensive model that can generate realistic groups. We evaluate our model against the measured data with excellent results. A realistic group membership model can help us improve the effectiveness of simulations and guide the design of group-communication protocols.

Multicast routing algorithms that are capable of providing quality of service (QoS) to its members will play an important role in future communications networks. This paper discusses some fundamental properties of multicast routing subject to multiple QoS requirements. We will show that guaranteeing QoS and optimizing resource utilization are conflicting objectives and require a trade-off. We also present MAMCRA, a Multicast Adaptive Multiple Constraints Routing Algorithm, that guarantees QoS to the multicast members in an efficient, but not always optimal manner.

In Internet multicast, the set of receivers can be dynamic with receivers joining and leaving a group asynchronously and without the knowledge of the source(s). Multicast scoping is one of the methods by which the propagation of multicast packets is controlled in such a dynamic environment. The Internet today uses source-based scoping by which the source determines how far its multicast transmissions will propagate. In this paper we explore the use of receiver-based scoping. In such a scheme a receiver's join request is augmented with one or more scope values. By use of these values, the receiver specifies its wish to join and remain in the multicast group as long as its share of resource usage is within its declared scope. Receiver-based scoping can be used to more directly control an individual multicast receiver's share of the resources used in a multicast session. The paper is concerned with discussion of the design of the receiver-based scoping mechanism and its possible use within multicast applications. We also consider the implementation of the mechanism as an extension to the existing Internet multicast infrastructure and evaluate its use in the context of current MBone sessions.

Many multicast applications, such as video-on-demand and tele-education, desire quality of service (QoS) support from the underlying network. Recently, many QoS-based multicast protocols have been proposed to meet these requirements. However, few of them can achieve high success ratios while keeping good scalability. In this paper, we propose a new QoS-aware Multicast Protocol using Bounded Flooding (QMBF) technique. In this protocol, every network node has the knowledge of local network cell topology as well as QoS state information (collected from bounded ooding messages). QMBF utilizes this knowledge to increase the probability of finding a feasible branch that connects a new member to the multicast tree. It bases on two methods to find such feasible branch: computing partial feasible branches using local network cell information and multiple path searching. The design of QMBF allows it to operate on top of any unicast routing protocol or cooperate with a QoS-based unicast routing protocol.

In this paper, we consider the problem of data dissemination from a source to multiple receivers over application-layer overlay networks, and seek to significantly improve end-toend throughput of data dissemination sessions by constructing topologies of high quality. We propose oEvolve, a distributed algorithm that uses the strategy of progressively and adaptively evolving the overlay topology over time towards high-quality topologies, especially with respect to end-to-end throughput of data dissemination. To validate the effectiveness and efficiency of oEvolve, we present a fully distributed real-world oEvolve implementation over PlanetLab, a global-scale wide-area overlay network testbed. Our implementation consists of a framework of components that involves a high-performance data forwarding engine and a centralized performance monitoring facility.