Fault-Tolerant Routing in Hypercube Networks by Avoiding Faulty Nodes
This addresses fault tolerance in multiprocessor systems, but it appears incremental as it builds on existing neural routing methods with a focus on reducing neuron count.
The paper tackles the problem of fault-tolerant routing in hypercube networks for multiprocessor systems by introducing the Fault Avoidance Routing (FAR) method, which uses a Hopfield neural network to keep messages away from faulty nodes, resulting in excellent performance in larger networks and those with high faulty node densities.
Next to the high performance, the essential feature of the multiprocessor systems is their fault-tolerant capability. In this regard, fault-tolerant interconnection networks and especially fault-tolerant routing methods are crucial parts of these systems. Hypercube is a popular interconnection network that is used in many multiprocessors. There are several suggested practices for fault tolerant routing in these systems. In this paper, a neural routing method is introduced which is named as Fault Avoidance Routing (FAR). This method keeps the message as far from the faulty nodes as possible. The proposed method employs the Hopfield neural network. In comparison with other neural routing methods, FAR requires a small number of neurons. The simulation results show that FAR has excellent performance in larger interconnection networks and networks with a high density of faulty nodes.