Fault Tolerance of Small World Network Architecture

Abstract

The most important elements in a massive VLSI parallel network are the component of networks. The key in the network is to execute the communication between a lot of nodes faultlessly while securing the scalability. Small World Network is a network which allows communication between two arbitrary nodes where hopping over a small number of nodes is possible, in a network with a huge number of nodes. Each connection path is selected as follows: The first node in the sequence is selected by a random number system by the node, under some constraints, such as choosing the smallest average passing length, or having a large clustering coefficient. There are a lot of examples of the small world network in action today, such as the neuronal connection, the metabolic pathway, social networks, and airline routes. A feature of small-world networks is that average path length is small. Thus the small-world network falls between regular and random networks. We introduced a parallel VLSI architecture featuring a random connection in Small World Network. The lower blocks are used for computation and the upper block is used for connection between every lower block. Both the upper block and lower blocks are randomly rewired using small world connection to get the shortest paths between all node pairs. In general, a link fault might negatively affect network dependability such as the no. of faulty network components, and also negatively affect network scalability such as the segmentation of the entire system, and the no. of faulty network segments. We concluded that small world connection helps to prevent the tendency to have faults.