# Data quality challenges in existing distribution network datasets

arXiv: https://arxiv.org/abs/2308.00487 · HTML: https://mlsanity.com/paper/2308.00487/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2023.

## Built on by (most cited first, 1 of 1)

- [Enabling Scalable Topology Inference in Distribution Systems via Constrained Multi-Source Inference](https://mlsanity.com/paper/2607.20480/) (2026)

## Abstract (arXiv)

Existing digital distribution network models, like those in the databases of network utilities, are known to contain erroneous or untrustworthy information. This can compromise the effectiveness of physics-based engineering simulations and technologies, in particular those that are needed to deliver the energy transition. The large-scale rollout of smart meters presents new opportunities for data-driven system identification in distribution networks, enabling the improvement of existing data sets. Despite the increasing academic attention to system identification for distribution networks, researchers often make troublesome assumptions on what data is available and/or trustworthy. In this paper, we highlight some differences between academic efforts and first-hand industrial experiences, in order to steer the former towards more applicable research solutions.