Adaptive network reliability analysis: Methodology and applications to power grid

TL;DR

This paper introduces ANR-BART, an adaptive surrogate model combining Bayesian Additive Regression Trees and Monte Carlo simulation, to efficiently analyze the reliability of power grid networks, especially for rare failure events.

Contribution

It presents the first adaptive surrogate-based network reliability analysis method using BART, addressing high-dimensional and mixed-variable challenges in power grid reliability assessment.

Findings

ANR-BART provides accurate failure probability estimates.

It significantly reduces computational costs compared to traditional methods.

The approach is robust across various benchmark power grid systems.

Abstract

Flow network models can capture the underlying physics and operational constraints of many networked systems including the power grid and transportation and water networks. However, analyzing reliability of systems using computationally expensive flow-based models faces substantial challenges, especially for rare events. Existing actively trained meta-models, which present a new promising direction in reliability analysis, are not applicable to networks due to the inability of these methods to handle high-dimensional problems as well as discrete or mixed variable inputs. This study presents the first adaptive surrogate-based Network Reliability Analysis using Bayesian Additive Regression Trees (ANR-BART). This approach integrates BART and Monte Carlo simulation (MCS) via an active learning method that identifies the most valuable training samples based on the credible intervals derived by BART over the space of predictor variables as well as the proximity of the points to the estimated limit state. Benchmark power grids including IEEE 30, 57, 118, and 300-bus systems and their power flow models for cascading failure analysis are considered to investigate ANR-BART, MCS, subset simulation, and passively-trained optimal deep neural networks and BART. Results indicate that ANR-BART is robust and yields accurate estimates of network failure probability, while significantly reducing the computational cost of reliability analysis.