Fuzzy priority based overlay multicast

Among the existing overlay multicast protocols, the Priority-based directed minimum Spanning Tree (PST) is designed for Distributed Interactive Applications (DIAs), and it uses priority to quantify the relationship between two nodes and guarantees the nodes with high priority receiving data in a short delay. Since the priority is calculated only from the distance between the nodes' avatars, and the available bandwidth (avail-bw) of nodes is not considered in multicast tree building, PST cannot use avail-bw efficiently and in some cases the priority might be calculated inaccurately. In this paper we propose a novel overlay multicast protocol named Fuzzy priority based Overlay Multicast (FOM), which adopts a fuzzy mechanism to accurately calculate the priority by taking all the attributes of avatars into consideration, and utilizes priority, delay, and avail-bw synthetically to build multicast trees. When avail-bw is insufficient to build a multicast tree, a priority based filtering mechanism is implemented to rebuild it. The simulation results show that with group number and observation region increasing, FOM has the best performance on tree build rates, mean relative delay penalty, and mean bandwidth usage percentage, and it is more suitable for DIAs than protocols ALMI and PST.

[1]  Samir Khuller,et al.  Balancing minimum spanning and shortest path trees , 1993, SODA '93.

[2]  Jörg Widmer,et al.  Priority-based distribution trees for application-level multicast , 2003, NetGames '03.

[3]  Chungnan Lee,et al.  Supporting large-scale distributed simulation using HLA , 2000, TOMC.

[4]  Constantinos Dovrolis,et al.  Bandwidth requirement and state consistency in three multiplayer game architectures , 2003, NetGames '03.

[5]  Jun Yu,et al.  A fuzzy grouping mechanism for distributed interactive simulation , 2005, IEEE International Conference on Communications, 2005. ICC 2005. 2005.

[6]  Shervin Shirmohammadi,et al.  An end-to-end communication architecture for collaborative virtual environments , 2001, Comput. Networks.

[7]  Stefan Saroiu,et al.  A Measurement Study of Peer-to-Peer File Sharing Systems , 2001 .

[8]  Tianying Chang,et al.  Scalable and efficient update dissemination for distributed interactive applications , 2002, Proceedings 22nd International Conference on Distributed Computing Systems.

[9]  Bu-Sung Lee,et al.  A survey of application level multicast techniques , 2004, Comput. Commun..

[10]  Jiang Li,et al.  DigiMetro - an application-level multicast system for multi-party video conferencing , 2004, IEEE Global Telecommunications Conference, 2004. GLOBECOM '04..

[11]  Sankar K. Pal,et al.  Fuzzy Mathematical Approach to Pattern Recognition , 1986 .

[12]  Kenneth L. Calvert,et al.  Modeling Internet topology , 1997, IEEE Commun. Mag..

[13]  Zhen Liu,et al.  Stateless Application-Level Multicast for Dynamic Group Communication , 2004, Eighth IEEE International Symposium on Distributed Simulation and Real-Time Applications.

[14]  kc claffy,et al.  Bandwidth estimation: metrics, measurement techniques, and tools , 2003, IEEE Netw..

[15]  Peter Steenkiste,et al.  Evaluation and characterization of available bandwidth probing techniques , 2003, IEEE J. Sel. Areas Commun..

[16]  Stephen John Turner,et al.  An alternative time management mechanism for distributed simulations , 2005, TOMC.

[17]  Srinivasan Seshan,et al.  A case for end system multicast , 2002, IEEE J. Sel. Areas Commun..

[18]  Dinesh C. Verma,et al.  ALMI: An Application Level Multicast Infrastructure , 2001, USITS.

[19]  Michael Zyda,et al.  Multicast grouping for data distribution management , 2002, Simul. Pract. Theory.

[20]  Venkata N. Padmanabhan,et al.  Some findings on the network performance of broadband hosts , 2003, IMC '03.

[21]  Samir Khuller,et al.  Balancing Minimum Spanning and Shortest Path Trees , 1993, SODA.