Integration of Unicast and Multicast Scheduling in Input-Queued Packet Switches With High Scalability
This paper focuses on the scalability problems for high-speed switches, and presents an integrated scheduling algorithm that supports unicast and multicast traffic efficiently in input-queued packet switches. Considering the tradeoff balancing complexity and performance, the proposed integrated algorithm performs without iteration, and reduces the scheduling overhead to O(N) with a two-phase (request-grant) sequential scheduling for unicast and multicast traffic. In addition, it can be implemented in a fully distributed way, which is more suitable for high-speed switches. Simulation results show that the proposed algorithm exhibits a good performance in terms of throughput and average delay, at different traffic compositions under various traffic patterns.