Graph Partition Based Traffic Balance in Industrial Network

The traffic load balancing problem in switched industrial Ethernet is a key component of QoS performance, which is shown to be equivalent to a multi-constraint optimization problem: the network design should minimize the amount of inter-network communication time, and simultaneously balance the communication time and network size evenly over the resultant sub-networks. To solve this optimization problem, a graph partitioning strategy is proposed, which can give a good network solution by partitioning a graph- based representation of industrial network. In the experiments the network partitions obtained by graph partitioning strategy are compared with those obtained by a random partitioning method. The experimental results show the graph partitioning strategy is significantly better than those obtained by random partitioning method.