Terminal-pair reliability determines the probabilistic reliability between two nodes of a network, given failure probabilities of all links. The problem has been successfully solved by the path-based partition method, network reduction technique, and the combination of the two. The path-based partition algorithm, however, requires repeated execution of a path-search procedure in an attempt to locally minimize the total number of subproblems generated. In this paper, we propose a cut-based partition algorithm based on the minimum cut separating the source from the remaining network nodes. This cut-based algorithm makes no attempt to locally minimize the number of subproblems. Instead, the algorithm leads to the great reduction of the computation time for the partitioning of each subproblem. Experimental results show the superiority of the cut-based algorithm over the path-based algorithm especially for complex networks. By further employing the network reduction technique, our cut-based partition algorithm outperforms the path-based partition algorithm for all benchmarks and random sparse or dense networks. Based on the cut-based partition algorithm, we further present an incremental method of computing the terminal-pair reliability for hierarchical networks. The incremental method results in minimal recomputation of reliability should the network configuration change.
|Number of pages||5|
|State||Published - 14 Nov 1995|
|Event||Proceedings of the 1995 IEEE Global Telecommunications Conference. Part 2 (of 3) - Singapore, Singapore|
Duration: 14 Nov 1995 → 16 Nov 1995
|Conference||Proceedings of the 1995 IEEE Global Telecommunications Conference. Part 2 (of 3)|
|Period||14/11/95 → 16/11/95|