Residual Power Flow for Neural Solvers

• URL: http://arxiv.org/abs/2601.09533v1
• Date: Wed, 14 Jan 2026 14:56:25 GMT
• Title: Residual Power Flow for Neural Solvers
• Authors: Jochen Stiasny, Jochen Cremer,
• Abstract summary: This work proposes the Residual Power Flow (RPF) formulation.<n>RPF formulates residual functions based on Kirchhoff's laws to quantify the infeasibility of an operating condition.<n>We propose to learn RPF with neural solvers to exploit their speed.<n>To solve operational tasks, we integrate the neural solver in a Predict-then-Optimise (PO) approach.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The energy transition challenges operational tasks based on simulations and optimisation. These computations need to be fast and flexible as the grid is ever-expanding, and renewables' uncertainty requires a flexible operational environment. Learned approximations, proxies or surrogates -- we refer to them as Neural Solvers -- excel in terms of evaluation speed, but are inflexible with respect to adjusting to changing tasks. Hence, neural solvers are usually applicable to highly specific tasks, which limits their usefulness in practice; a widely reusable, foundational neural solver is required. Therefore, this work proposes the Residual Power Flow (RPF) formulation. RPF formulates residual functions based on Kirchhoff's laws to quantify the infeasibility of an operating condition. The minimisation of the residuals determines the voltage solution; an additional slack variable is needed to achieve AC-feasibility. RPF forms a natural, foundational subtask of tasks subject to power flow constraints. We propose to learn RPF with neural solvers to exploit their speed. Furthermore, RPF improves learning performance compared to common power flow formulations. To solve operational tasks, we integrate the neural solver in a Predict-then-Optimise (PO) approach to combine speed and flexibility. The case study investigates the IEEE 9-bus system and three tasks (AC Optimal Power Flow (OPF), power-flow and quasi-steady state power flow) solved by PO. The results demonstrate the accuracy and flexibility of learning with RPF.

Related papers

• Neural Network Optimal Power Flow via Energy Gradient Flow and Unified Dynamics [0.5076419064097734]
  This paper proposes an Optimal Power Flow solving method based on neural network dynamics and energy gradient flow computation.<n>By constructing an energy function to measure the degree of deviation from the constraint manifold, and guiding networks to learn optimal solutions that simultaneously satisfy power flow constraints and minimize costs through gradient flow.
  arXiv  Detail & Related papers  (2025-12-01T02:59:47Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• QCQP-Net: Reliably Learning Feasible Alternating Current Optimal Power Flow Solutions Under Constraints [4.1920378271058425]
  We propose an innovated computational learning ACOPF, where the input is mapped to the ACOPF network in a computationally efficient manner. We show through simulations that our proposed method achieves superior feasibility rate and cost in situations where the existing-based approaches fail.
  arXiv  Detail & Related papers  (2024-01-11T20:17:44Z)
• Learning Optimal Power Flow Value Functions with Input-Convex Neural Networks [15.791200937436837]
  The Optimal Power Flow (OPF) problem is integral to power systems, aiming to optimize generation while adhering to dispatch constraints. This research explores machine learning (ML) to learn for faster analysis in the online setting while still allowing for coupling into other convex dependent decision problems.
  arXiv  Detail & Related papers  (2023-10-06T21:48:39Z)
• A Multi-Head Ensemble Multi-Task Learning Approach for Dynamical Computation Offloading [62.34538208323411]
  We propose a multi-head ensemble multi-task learning (MEMTL) approach with a shared backbone and multiple prediction heads (PHs) MEMTL outperforms benchmark methods in both the inference accuracy and mean square error without requiring additional training data.
  arXiv  Detail & Related papers  (2023-09-02T11:01:16Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition [67.46012350241969]
  This paper proposes a general acceleration methodology called NeuralStagger. It decomposing the original learning tasks into several coarser-resolution subtasks. We demonstrate the successful application of NeuralStagger on 2D and 3D fluid dynamics simulations.
  arXiv  Detail & Related papers  (2023-02-20T19:36:52Z)
• Unsupervised Deep Learning for AC Optimal Power Flow via Lagrangian Duality [3.412750324146571]
  AC optimal power flow is a fundamental optimization problem in power system analysis. Deep learning based approaches have gained intensive attention to conduct the time-consuming training process offline. This paper proposes an end-to-end unsupervised learning based framework for AC-OPF.
  arXiv  Detail & Related papers  (2022-12-07T22:26:45Z)
• Unsupervised Optimal Power Flow Using Graph Neural Networks [172.33624307594158]
  We use a graph neural network to learn a nonlinear parametrization between the power demanded and the corresponding allocation. We show through simulations that the use of GNNs in this unsupervised learning context leads to solutions comparable to standard solvers.
  arXiv  Detail & Related papers  (2022-10-17T17:30:09Z)
• Learning to Solve the AC-OPF using Sensitivity-Informed Deep Neural Networks [52.32646357164739]
  We propose a deep neural network (DNN) to solve the solutions of the optimal power flow (ACOPF) The proposed SIDNN is compatible with a broad range of OPF schemes. It can be seamlessly integrated in other learning-to-OPF schemes.
  arXiv  Detail & Related papers  (2021-03-27T00:45:23Z)
• Learning to Solve AC Optimal Power Flow by Differentiating through Holomorphic Embeddings [17.338923885534193]
  Alternating current optimal power flow (AC-OPF) is one of the fundamental problems in power systems operation. In this paper, we show efficient strategies that circumvent this problem by differentiating through the operations of a power flow solver. We report a 12x increase in speed and a 40% increase in robustness compared to a traditional solver.
  arXiv  Detail & Related papers  (2020-12-16T18:23:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.