Neuro-Dynamic State Estimation for Networked Microgrids

TL;DR

This paper introduces Neuro-DSE, a novel learning-based dynamic state estimation method for networked microgrids that effectively handles unknown subsystems and noisy measurements using neural ODEs and Kalman filters.

Contribution

It presents a data-driven Neuro-DSE algorithm with self-refinement and integration with KalmanNet, enabling accurate state and parameter estimation in complex microgrid systems.

Findings

Neuro-DSE outperforms traditional methods under noisy conditions.

The algorithms effectively estimate states and unknown parameters.

Case studies validate robustness across various scenarios.

Abstract

We devise neuro-dynamic state estimation (Neuro-DSE), a learning-based dynamic state estimation (DSE) algorithm for networked microgrids (NMs) under unknown subsystems. Our contributions include: 1) a data-driven Neuro-DSE algorithm for NMs DSE with partially unidentified dynamic models, which incorporates the neural-ordinary-differential-equations (ODE-Net) into Kalman filters; 2) a self-refining Neuro-DSE algorithm (Neuro-DSE+) which enables data-driven DSE under limited and noisy measurements by establishing an automatic filtering, augmenting and correcting framework; 3) a Neuro-KalmanNet-DSE algorithm which further integrates KalmanNet with Neuro-DSE to relieve the model mismatch of both neural- and physics-based dynamic models; and 4) an augmented Neuro-DSE for joint estimation of NMs states and unknown parameters (e.g., inertia). Extensive case studies demonstrate the efficacy of Neuro-DSE and its variants under different noise levels, control modes, power sources, observabilities and model knowledge, respectively.