Differentiable Power-Flow Optimization

2026-03-30

AI Summary

This study addresses the growing complexity of power grids with high renewable penetration, where traditional AC power flow methods like Newton-Raphson face scalability limitations and purely data-driven models lack physical consistency. The work proposes a novel approach that embeds AC power flow computation within a differentiable simulation framework, enabling end-to-end gradient-based optimization from power imbalances to simulation parameters. Implemented in PyTorch, the solver leverages GPU acceleration, sparse tensors, and batch processing to significantly enhance computational efficiency while preserving physical constraints. The method demonstrates strong applicability in time-series analysis, N-1 security assessment, and rapid contingency screening, offering superior scalability, batch-processing capability, and computational speed.

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.

Problem

• power-flow optimization
• renewable energy integration
• scalability
• physical constraints
• AC power flow

Innovation

• Differentiable Simulation
• AC Power Flow
• Gradient-based Optimization
• GPU Acceleration
• Sparse Tensor