A Measurement-Based Robust Non-Gaussian Process Emulator Applied to Data-Driven Stochastic Power Flow

TL;DR

This paper introduces a robust non-Gaussian process emulator for stochastic power flow analysis, effectively handling outliers in power system data using projection statistics-based weighting, demonstrated on an IEEE 33-Bus system.

Contribution

It develops a robust emulator based on Schweppe-type maximum likelihood estimation that manages outliers in power system measurements for improved stochastic power flow modeling.

Findings

Successfully bounds influence of outliers in power data

Retains good leverage points while mitigating bad ones

Effective on unbalanced radial IEEE 33-Bus system

Abstract

In this paper, we propose a robust non-Gaussian process emulator based on the Schweppe-type generalized maximum likelihood estimator, which is trained on metered time series of voltage phasors and power injections to perform stochastic power flow. Power system data are often corrupted with outliers caused by fault conditions, power outages, and extreme weather, to name a few. The proposed emulator bounds the influence of the outliers using weights calculated based on projection statistics, which are robust distances of the data points associated with the rows vectors of the factor space. Specifically, the developed estimator is robust to vertical outliers and bad leverage points while retaining good leverage points in the measurements of the training dataset. The proposed method is demonstrated on an unbalanced radial IEEE 33-Bus system heavily integrated with renewable energy sources.