Data-driven Modeling for Distribution Grids Under Partial Observability
This work addresses partial observability issues in power distribution grids, which is crucial for monitoring and decision-making, but it appears incremental as it builds on existing methods with specific enhancements.
The paper tackled the problem of partial observability in data-driven modeling of power distribution grids to improve line parameter estimation accuracy, achieving demonstrated accuracy improvements over existing work in both parameter estimation and voltage modeling using real-world load data on the IEEE 123-bus test case.
Accurately modeling power distribution grids is crucial for designing effective monitoring and decision making algorithms. This paper addresses the partial observability issue of data-driven distribution modeling in order to improve the accuracy of line parameter estimation. Inspired by the sparse changes in residential loads, we advocate to regularize the group sparsity of the unobservable injections in a bi-linear estimation problem. The alternating minimization scheme of guaranteed convergence is proposed to take advantage of convex subproblems with efficient solutions. Numerical results using real-world load data on the single-phase equivalent of the IEEE 123-bus test case have demonstrated the accuracy improvements of the proposed solution over existing work for both parameter estimation and voltage modeling.