Physics-Conditioned Generative Adversarial Networks for State Estimation in Active Power Distribution Systems with Low Observability

Abstract

A novel method is proposed to address the issue of low-observability in Distribution System State Estimation (DSSE). We first use the historical data at the unobservable locations to construct and train proper Generative Adversarial Network (GAN) models to compensate for lack of direct real-time measurements. We then integrate the trained GAN models, together with the direct synchronized measurements at the observable locations, into the formulation of the DSSE problem. In this regard, we simultaneously take advantage of the forecasting capabilities of the GAN models, the available real-time synchronized measurements, and the DSSE formulations based on physical laws in the power system. As a result, on one hand we conduct a physics-conditioned estimation of the unknown power injections at the unobservable locations; and on the other hand, we also achieve a complete DSSE solution for the understudy low-observable active power distribution system.

Distribution Grid Topology and Parameter Estimation Using Deep-Shallow Neural Network With Physical Consistency

“…To numerically support our claim, we compare our methods with the recent method Physics-conditioned GAN [44] for the MSE error of the hidden state estimation. Specifically, we employ 8760 voltage and power samples for observed nodes and 500 voltage pseudo-measurements for observed and hidden nodes.…”

“…In this subsection, we demonstrate the additional function of our DSN to estimate the voltage of hidden nodes if we have extra pseudo-measurements. In particular, for partiallyobservable systems, pseudo-measurements of hidden regions are often needed to enable state estimation for all hidden states [44]. Namely, one needs to have access to historical data of hidden nodes, which may have low data quality and large errors.…”

“…Namely, one needs to have access to historical data of hidden nodes, which may have low data quality and large errors. Existing work employs the Gaussian mixture model [45], 2-stage clustering [46], NN to process pseudomeasurements [47], [48], and Generative Adversarial Network (GAN) [44] for distribution grid state estimation. With pseudo-measurements, we find that despite the lack of system parameters, our DSN model can also bring accurate hidden state estimation.…”

“…• Physics-conditioned GAN [44]. Physics-conditioned Generative Adversarial Network (GAN) is a cutting-edge method to conduct distribution grid state estimation with pseudo-measurements of hidden nodes.…”

Enhance Unobservable Solar Generation Estimation via Constructive Generative Adversarial Networks

“…[34] firstly leverage the characteristic to generate scenarios of renewable outputs, which can mimic diverse conditions and uncertainties to produce more renewable data. Similarly, the GAN model is used to estimate the unknown power injection at unobservable loads based on the available historical measurements [35], [36]. While the generation from Gaussian noises is insufficient to cover the needs of specific data patterns, conditional inputs are used to restrict the generated data to a particular class like weather conditions of high wind, real-time system configurations of topology/admittances, and electricity market data [34], [35], [37], [38].…”