Differentially Private Algorithms for Synthetic Power System Datasets
This work addresses privacy concerns for power system operators by enabling secure data sharing, though it is incremental as it applies existing differential privacy mechanisms to a specific domain.
The authors tackled the problem of sharing power system data by developing differentially private algorithms to generate synthetic datasets, which preserve accuracy for downstream models while controlling privacy loss, achieving results that maintain utility for optimization and machine learning tasks.
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.