# Data-driven Modeling for Distribution Grids Under Partial Observability

arXiv: https://arxiv.org/abs/2108.08350 · HTML: https://mlsanity.com/paper/2108.08350/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 18 Aug 2021.

## Builds on (most cited first, 13 of 13)

- [Urban MV and LV Distribution Grid Topology Estimation via Group Lasso](https://mlsanity.com/paper/1611.01845/) (2016)
- [On Identification of Distribution Grids](https://mlsanity.com/paper/1711.01526/) (2017)
- [Load-Flow in Multiphase Distribution Networks: Existence, Uniqueness, Non-Singularity and Linear Models](https://mlsanity.com/paper/1702.03310/) (2017)
- [Graph Algorithms for Topology Identification using Power Grid Probing](https://mlsanity.com/paper/1803.04506/) (2018)
- [Convex Relaxations and Linear Approximation for Optimal Power Flow in Multiphase Radial Networks](https://mlsanity.com/paper/1406.3054/) (2014)
- [PaToPaEM: A Data-Driven Parameter and Topology Joint Estimation Framework for Time Varying System in Distribution Grids](https://mlsanity.com/paper/1812.06619/) (2018)
- [Data-driven Voltage Regulation in Radial Power Distribution Systems](https://mlsanity.com/paper/1901.03173/) (2019)
- [Voltage Analytics for Power Distribution Network Topology Verification](https://mlsanity.com/paper/1707.06671/) (2017)
- [Joint Estimation of Topology and Injection Statistics in Distribution Grids with Missing Nodes](https://mlsanity.com/paper/1804.04742/) (2018)
- [Hybrid Voltage Control in Distribution Networks Under Limited Communication Rates](https://mlsanity.com/paper/1707.07094/) (2017)
- [A Learning-to-Infer Method for Real-Time Power Grid Multi-Line Outage Identification](https://mlsanity.com/paper/1710.07818/) (2017)
- [Data-driven Coordination of Distributed Energy Resources for Active Power Provision](https://mlsanity.com/paper/1804.00043/) (2018)
- [Enhancing the Spatio-temporal Observability of Grid-Edge Resources in Distribution Grids](https://mlsanity.com/paper/2102.07801/) (2021)

## Abstract (arXiv)

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.