In this thesis, the problem of congestion control in computer communication networks is studied. The method employed consists of a combination of a dynamic routing policy that minimizes the delay, and buffer management schemes to control the flow of data. These schemes include (1) Complete Sharing, (2) Square Root Sharing, and (3) Sharing with Minimum Allocation.

Document studies the broad area of flow control and sequencing in computer communication networks. A special use of message sequencing is shown to reduce to a Markov process. A more general sequencing model is also studies; only approximate results are obtained in this case. The author formally shows that an end-to-end flow control scheme in computer communication networks can be modeled as a closed network of queues. He also introduces and analyzes a flow control scheme based on limiting the permit generation rates. It turns out that this scheme is very effective. More importantly, this scheme involves essentially no computational complexity. This allows us to measure and adjust the network performance with little difficulty. The simplicity also allows us to incorporate more realistic aspects of network protocols such as piggy-back acknowledgement, time-out and gate functions into our analysis. Two simple but effective distributed dynamic flow control schemes are proposed and analyzed. It is shown that with either of these two schemes, a network can respond well to the dynamically changing environment.

As the number of processor cores and IP blocks integrated on a single chip is steadily growing, a systematic approach to design the communication infrastructure becomes necessary. Different variants of packed switched on-chip networks have been proposed by several groups during the past two years. This book summarizes the state of the art of these efforts and discusses the major issues from the physical integration to architecture to operating systems and application interfaces. It also provides a guideline and vision about the direction this field is moving to. Moreover, the book outlines the consequences of adopting design platforms based on packet switched network. The consequences may in fact be far reaching because many of the topics of distributed systems, distributed real-time systems, fault tolerant systems, parallel computer architecture, parallel programming as well as traditional system-on-chip issues will appear relevant but within the constraints of a single chip VLSI implementation.