Learning local cascading failure pattern from massive network failure data

This article proposes a novel multivariate point process regression model for a large-scale physically distributed network infrastructure with two failure modes, i.e. primary failures caused by the long-term usage and degradation of assets, and cascading failures triggered by primary failures in a short period. We exploit large-scale field pipe failure data from a UK-based water utility to support the rationale of considering the two failure modes. The two modes are not self-revealed in the data. To make the inference of the large-scale problem possible, we introduce a time window for cascading failures, based on which the likelihood of the pipe failure process can be decomposed into two parts, one for the primary failures and the other for the cascading failure processes modulated by the primary failure processes. The window length for cascading failures is treated as a tuning parameter, and determined through maximizing the likelihood based on all failure data. To illustrate the effectiveness of the model, two case studies are presented based on real data from the UK-based water utility. Interesting features of the cascading failures are identified from massive field pipe failure data. The results provide insights on advanced modelling and practical decision-making for both researchers and practitioners.