Design Method of Robust Networks against Performance Deterioration during Failures

When a link or node failure occurs in a network, flows are detoured and therefore the hop counts of the flows increase. This increase could drastically deteriorate the quality of a network. The flow hop length stability as well as network connectivity is important for network reliability. We investigate a network design method that improves stability and connectivity of a network during a failure with a limited investment cost. We formalize a network design problem, prove that this problem is NP-complete, and propose an approximation algorithm. In addition, we evaluate the performance of the algorithm by using publicly available data for 39 backbone networks of commercial ISPs and networks generated by two well-known models. The results show that the proposed algorithm provides effective solutions from a practical viewpoint in sufficiently small computation time.