Network management based on modeling of cascading effect of failure

Abstract

A system and method of managing a network with assets are described. The method includes generating a directed graph with each of the assets represented as a node, determining individual failure probability of each node, computing downstream failure probability of each node according to an arrangement of the nodes in the directed graph, computing upstream failure probability of each node according to the arrangement of the nodes in directed graph, and computing network failure probability for each node based on the corresponding individual failure probability, the downstream failure probability, and the upstream failure probability. Managing the network is based on the network failure probability of the assets.

What is claimed is: 
     
         1 . A network management system to manage assets of the network, the management system comprising:
 a memory device configured to store instructions; and   a processor configured to process the instructions to compute network failure probability associated with each asset based on determining individual failure probability, upstream failure probability, and downstream failure probability for each asset, and to manage the network based on the network failure probabilities of the assets.   
     
     
         2 . A computer program product comprising:
 a tangible storage medium readable by a processing circuit and storing instructions for execution by the processing circuit to perform a method of managing a network with assets, the method comprising:   generating a directed graph with each of the assets represented as a node;   determining individual failure probability of each node;   computing downstream failure probability of each node according to an arrangement of the nodes in the directed graph;   computing upstream failure probability of each node according to the arrangement of the nodes in directed graph;   computing network failure probability for each node based on the corresponding individual failure probability, the downstream failure probability, and the upstream failure probability; and   managing the network based on the network failure probability of the assets.   
     
     
         3 . The computer program product according to  claim 2 , wherein the method further comprises classifying each node in the directed graph, wherein the network is an electric power network and the classifying each node includes classifying each node as a non-protective electrical asset, a protective electrical asset, or a physical asset. 
     
     
         4 . The computer program product according to  claim 2 , wherein the determining the individual failure probability of each node includes extrapolating from a training model that is trained with historical data. 
     
     
         5 . The computer program product according to  claim 2 , wherein the computing the downstream failure probability for each node is based on a classification of one or more assets downstream of the node. 
     
     
         6 . The computer program product according to  claim 2 , wherein the computing the upstream failure probability for each node involves an iterative process. 
     
     
         7 . The computer program product according to  claim 6 , wherein the computing the upstream failure probability for each node is based on the network failure probability of upstream nodes in a modified directed graph that omits the node. 
     
     
         8 . The computer program product according to  claim 2 , wherein the managing the network based on the network failure probability of the assets includes modifying an inspection and maintenance schedule of the assets based on the network failure probability of the assets. 
     
     
         9 . The computer program product according to  claim 2 , wherein the managing the network based on the network failure probability of the assets includes setting a threshold network failure probability and, when the network failure probability of one of the assets exceeds the threshold network failure probability, managing the one of the assets as a critical asset.