.png){kind=icon}
.png){kind=icon}
Return
Neuro-Dynamic State Estimation for Networked Microgrids
.png){kind=icon}
OA
AI
DOI：10.1109/TIA.2024.3371956.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The increasing integration of distributed energy resources (DERs) brings complicated dynamics in networked microgrids (NMs), calling for high-fidelity dynamic state estimation (DSE) of NMs. Traditional DSE, which requires accurate physical models of the entire NMs, is becoming increasingly unattainable. This paper devises neuro-dynamic state estimation (Neuro-DSE), a learning-based DSE algorithm to track the dynamics of inverter-interfaced NMs with unknown subsystems. The process and contributions include: 1) a data-driven Neuro-DSE algorithm is established for NMs with partially unidentified dynamic models by incorporating the neural-ordinary-differential-equations (ODE-Net) into Kalman filters; 2) a self-refined Neuro-DSE$<^>{+}$ method is devised to tackle limited and noisy measurements. Specifically, Kalman filters are embedded into ODE-Net training for automatic filtering, augmenting, and correcting effects; 3) a Neuro-KalmanNet-DSE algorithm is derived to relieve the model mismatch scenarios by integrating KalmanNet with Neuro-DSE. Numerical simulations carried out on typical four-microgrid NMs reveal that Neuro-DSE can track the dynamics under various control modes (e.g., droop/secondary controls) and components. Its variants increase the accuracy of Neuro-DSE under limited measurement and model mismatch scenarios.
Keywords:
Heuristic algorithms
Power system dynamics
Kalman filters
Physics
State estimation
Noise measurement
Current measurement
Networked microgrids
neuro-dynamic state estimation
Kalman filter
neural ordinary differential equations
KalmanNet
Journal
IF:
4.5
Papers:
1.1W
Citations:
3.5W