Physics-Informed Deep Neural Network Method for Limited Observability State Estimation

TL;DR

This paper introduces a physics-informed deep neural network approach for power grid state estimation under limited observability, improving accuracy by incorporating physical grid information into the learning process.

Contribution

The paper proposes a novel DNN-based method that explicitly integrates grid topology and admittance data, enhancing state estimation accuracy in partially observable distribution grids.

Findings

The physics-informed DNN outperforms standard DNN in estimation accuracy.

The proposed method surpasses traditional weighted least squares approaches.

Incorporating physical information significantly improves estimation results.

Abstract

The precise knowledge regarding the state of the power grid is important in order to ensure optimal and reliable grid operation. Specifically, knowing the state of the distribution grid becomes increasingly important as more renewable energy sources are connected directly into the distribution network, increasing the fluctuations of the injected power. In this paper, we consider the case when the distribution grid becomes partially observable, and the state estimation problem is under-determined. We present a new methodology that leverages a deep neural network (DNN) to estimate the grid state. The standard DNN training method is modified to explicitly incorporate the physical information of the grid topology and line/shunt admittance. We show that our method leads to a superior accuracy of the estimation when compared to the case when no physical information is provided. Finally, we compare the performance of our method to the standard state estimation approach, which is based on the weighted least squares with pseudo-measurements, and show that our method performs significantly better with respect to the estimation accuracy.