Uncertainty Quantification in LV State Estimation Under High Shares of Flexible Resources

TL;DR

This paper investigates how flexibility activations in power systems affect low-voltage state estimation accuracy and demonstrates that Bayesian neural networks can effectively quantify and adapt to this uncertainty, improving robustness.

Contribution

It introduces a systematic approach to quantify flexibility-induced uncertainty in LVSE using Bayesian neural networks, comparing it with quantile regression and highlighting its advantages.

Findings

Frequent flexibility activations worsen LVSE accuracy without secondary measurements.

BNN extends prediction intervals during activations, capturing voltage drops.

BNN enhances interpretability of uncertainty sources.

Abstract

The ongoing electrification introduces new challenges to distribution system operators (DSOs). Controllable resources may simultaneously react to price signals, potentially leading to network violations. DSOs require reliable and accurate low-voltage state estimation (LVSE) to improve awareness and mitigate such events. However, the influence of flexibility activations on LVSE has not been addressed yet. It remains unclear if flexibility-induced uncertainty can be reliably quantified to enable robust DSO decision-making. In this work, uncertainty quantification in LVSE is systematically investigated for multiple scenarios of input availability and flexibility utilization, using real data. For that purpose, a Bayesian neural network (BNN) is compared to quantile regression. Results show that frequent flexibility activations can significantly deteriorate LVSE performance, unless secondary substation measurements are available. Moreover, it is demonstrated that the BNN captures flexibility-induced voltage drops by dynamically extending the prediction interval during activation periods, and that it improves interpretability regarding the cause of uncertainty.