.png){kind=icon}
.png){kind=icon}
Return
Selective state-space models for Koopman-based data-driven distribution system state estimation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.epsr.2026.113562.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We introduce a model-free topology-agnostic data-driven state estimation framework. • Selective state-space model backbone learns nonlinear temporal evolution of system. • Model captures long-range dependencies from data to solve observability challenges. • Probabilistic estimator learns noise offsets to produce stable state trajectories. • Results highlight robustness to large-scale systems and sampling rate perturbations.
Keywords:
Data driven
Distribution system
Machine learning
State estimation
State-space models
Journal
IF:
4.2
Papers:
1.1W
Citations:
2.2W