Progressive Construction of k-identifiable Networks

Since the inception of networking technology, network topology design has been a fundamental step for any interconnected system. This classical problem has diverse forms due to various design criteria. One special criterion, the ease of monitoring the network (termed as monitorability of the network), has recently attracted much attention in the era of Industry 4.0 when many complex private networks need to be built for new industrial services. This paper extends a quantitative measure of network monitorability, k-identifiability, based on which a new form of network topology design problem is formulated. We prove that this network design problem is intractable. To solve it, we systematically analyze the topological features that are helpful for reducing the complexity of network construction. Based on the analysis, we propose a dual-heuristic method that runs two heuristics in parallel and selects the better topology as the preliminary design result. Moreover, we design an integrated algorithm that reduces unnecessary edges as the final design result. We compare our dual-heuristic algorithm with the theoretical optimal solution in small-scale networks where the brute-force search is feasible. The results demonstrate the near-optimality of our method. We also illustrate the capability of our method in designing large-scale networks.