Input queued (IQ) switches are highly scalable and they have been the focus of many studies from academia and industry. Many scheduling algorithms have been proposed for IQ switches. However, they do not consider the buffer space requirement inside an IQ switch that may render the scheduling algorithms inefficient in practical applications.

In this dissertation, the Queue Length Proportional (QLP) algorithm is proposed for IQ switches. QLP considers both the buffer management and the scheduling mechanism to obtain the optimal allocation region for both bandwidth and buffer space according to real traffic load. In addition, this dissertation introduces the Queue Proportional Fairness (QPF) criterion, which employs the cell loss ratio as the fairness metric. The research in this dissertation will show that the utilization of network resources will be improved significantly with QPF. Furthermore, to support diverse Quality of Service (QoS) requirements of heterogeneous and bursty traffic, the Weighted Minmax algorithm (WMinmax) is proposed to efficiently and dynamically allocate network resources.

Lastly, to support traffic with multiple priorities and also to handle the decouple problem in practice, this dissertation introduces the multiple dimension scheduling algorithm which aims to find the optimal scheduling region in the multiple Euclidean space.