Learning Geo-Temporal Non-Stationary Failure and Recovery of Power Distribution

TL;DR

This paper develops a novel geo-temporal non-stationary queue model to analyze large-scale failure and recovery behaviors in power distribution networks during hurricanes, with real data demonstrating different failure and recovery patterns.

Contribution

It introduces a new formulation for the entire failure-recovery lifecycle and develops spatial-temporal models as non-stationary queues, enabling parameter learning from real disaster data.

Findings

Failure rates are similar across networks for different hurricanes but vary geographically.

Both rapid and slow recoveries observed in Hurricane Ike; only slow recovery in Hurricane Sandy.

Model parameters learned effectively from real failure and recovery data.

Abstract

Smart energy grid is an emerging area for new applications of machine learning in a non-stationary environment. Such a non-stationary environment emerges when large-scale failures occur at power distribution networks due to external disturbances such as hurricanes and severe storms. Power distribution networks lie at the edge of the grid, and are especially vulnerable to external disruptions. Quantifiable approaches are lacking and needed to learn non-stationary behaviors of large-scale failure and recovery of power distribution. This work studies such non-stationary behaviors in three aspects. First, a novel formulation is derived for an entire life cycle of large-scale failure and recovery of power distribution. Second, spatial-temporal models of failure and recovery of power distribution are developed as geo-location based multivariate non-stationary GI(t)/G(t)/Infinity queues. Third, the non-stationary spatial-temporal models identify a small number of parameters to be learned. Learning is applied to two real-life examples of large-scale disruptions. One is from Hurricane Ike, where data from an operational network is exact on failures and recoveries. The other is from Hurricane Sandy, where aggregated data is used for inferring failure and recovery processes at one of the impacted areas. Model parameters are learned using real data. Two findings emerge as results of learning: (a) Failure rates behave similarly at the two different provider networks for two different hurricanes but differently at the geographical regions. (b) Both rapid- and slow-recovery are present for Hurricane Ike but only slow recovery is shown for a regional distribution network from Hurricane Sandy.