Efficient Capacity-Constrained Multicast in RC-Based P2P Networks Koushik Maddali 1 , Banafsheh Rekabdar 1 , Swathi Kaluvakuri 1 and Bidyut Gupta 1 Department of Computer Science Southern Illinois University Carbondale, IL, USA koushik@siu.edu, brekabdar@cs.siu.edu, swathi.kaluvakuri@siu.edu, bidyut@cs.siu.edu Abstract Application level multicast is independent of router infrastructure unlike router-based IP multicast. The existing DHT-based application level multicast protocols work efficiently as long as there is almost no churn; otherwise, their performances start degrading drastically, because DHT – based architecture cannot handle churn effectively. Besides, most of DHT-based multicast protocols consider single data source and do not consider peer heterogeneity. In this work, we have considered an existing non-DHT based P2P architecture, viz., Residue Class based (RC-based) architecture which has already been shown to perform much better than some well-known DHT-based architectures from the viewpoints of speed of unicast communication and churn handling. We have presented a highly efficient capacity-constrained and any source multicast protocol suitable for the RC-based P2P architecture as mentioned above. Keywords – P2P network; Residue class; Capacity constrained, multicast protocol I. INTRODUCTION Problems associated with the global deployment of multicast-capable routers, lack of support for network management, and also the scalability problem caused by the simultaneous presence of large number of multicast sessions, are some of the main reasons why the deployment of router-based IP multicast has been slow. Consequently, researches have started considering application level multicast as an alternative to IP multicast, because the former one can be deployed fast as it does not depend on router infrastructure [1], [2], [3]. Multicast protocols proposed in [4], [5], [6] focus on designing an EPiC Series in Computing Volume 63, 2019, Pages 121–129 Proceedings of 32nd International Conference on Computer Applications in Industry and Engineering Q. Yuan, Y. Shi, L. Miller, G. Lee, G. Hu and T. Goto (eds.), CAINE 2019 (EPiC Series in Computing, vol. 63), pp. 121–129