Differentiable Power-Flow Optimization

TL;DR

The paper introduces Differentiable Power-Flow (DPF), a GPU-accelerated, scalable, and differentiable simulation method for AC power-flow problems, enhancing efficiency and applicability in modern power grid analysis.

Contribution

It reformulates AC power-flow as a differentiable simulation enabling gradient-based optimization, scalable to large systems, and suitable for time-series and contingency analyses.

Findings

DPF achieves faster computations than traditional Newton-Raphson methods.

DPF enables efficient gradient-based parameter identification.

DPF is well-suited for batch processing and time-series analysis.

Abstract

With the rise of renewable energy sources and their high variability in generation, the management of power grids becomes increasingly complex and computationally demanding. Conventional AC-power-flow simulations, which use the Newton-Raphson (NR) method, suffer from poor scalability, making them impractical for emerging use cases such as joint transmission-distribution modeling and global grid analysis. At the same time, purely data-driven surrogate models lack physical guarantees and may violate fundamental constraints. In this work, we propose Differentiable Power-Flow (DPF), a reformulation of the AC power-flow problem as a differentiable simulation. DPF enables end-to-end gradient propagation from the physical power mismatches to the underlying simulation parameters, thereby allowing these parameters to be identified efficiently using gradient-based optimization. We demonstrate that DPF provides a scalable alternative to NR by leveraging GPU acceleration, sparse tensor representations, and batching capabilities available in modern machine-learning frameworks such as PyTorch. DPF is especially suited as a tool for time-series analyses due to its efficient reuse of previous solutions, for N-1 contingency-analyses due to its ability to process cases in batches, and as a screening tool by leveraging its speed and early stopping capability. The code is available in the authors' code repository.