# Differentially Private Algorithms for Synthetic Power System Datasets

arXiv: https://arxiv.org/abs/2303.11079 · HTML: https://mlsanity.com/paper/2303.11079/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 20 Mar 2023.

## Builds on (most cited first, 8 of 8)

- [New Oracle-Efficient Algorithms for Private Synthetic Data Release](https://mlsanity.com/paper/2007.05453/) (2020)
- [Learning from Past Bids to Participate Strategically in Day-Ahead Electricity Markets](https://mlsanity.com/paper/1811.06113/) (2018)
- [Differential Privacy for Power Grid Obfuscation](https://mlsanity.com/paper/1901.06949/) (2019)
- [Differential Privacy of Aggregated DC Optimal Power Flow Data](https://mlsanity.com/paper/1903.11237/) (2019)
- [Differentially Private Distributed Optimal Power Flow](https://mlsanity.com/paper/1910.10136/) (2019)
- [Differentially Private Optimal Power Flow for Distribution Grids](https://mlsanity.com/paper/2004.03921/) (2020)
- [Privacy-Preserving Obfuscation for Distributed Power Systems](https://mlsanity.com/paper/1910.04250/) (2019)
- [Privacy-Preserving Convex Optimization: When Differential Privacy Meets Stochastic Programming](https://mlsanity.com/paper/2209.14152/) (2022)

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

- [Constrained Diffusion Models for Synthesizing Representative Power Flow Datasets](https://mlsanity.com/paper/2506.11281/) (2025)

## Abstract (arXiv)

While power systems research relies on the availability of real-world network datasets, data owners (e.g., system operators) are hesitant to share data due to security and privacy risks. To control these risks, we develop privacy-preserving algorithms for the synthetic generation of optimization and machine learning datasets. Taking a real-world dataset as input, the algorithms output its noisy, synthetic version, which preserves the accuracy of the real data on a specific downstream model or even a large population of those. We control the privacy loss using Laplace and Exponential mechanisms of differential privacy and preserve data accuracy using a post-processing convex optimization. We apply the algorithms to generate synthetic network parameters and wind power data.