RAPTOR: RAndom-projection Physics-informed Transient sOlveR

Petros Ellinas; Benjamin Vilmann; Spyros Chatzivasileiadis; Johanna Vorwerk

eess.SYAug 31, 2026

RAPTOR: RAndom-projection Physics-informed Transient sOlveR

Authors: Petros Ellinas, Benjamin Vilmann, Spyros Chatzivasileiadis, Johanna Vorwerk

Organizations: Department of Wind and Energy Systems, Technical University of Denmark, Lyngby, Denmark

Abstract

The complexity of time-domain simulation of modern power systems has increased significantly because converter-based resources introduce control dynamics that must be simulated alongside slower system-level and fast electromagnetic dynamics. The resulting wide range of timescales may force classical time-domain solvers to use small timesteps, complicate the solution of nonlinear equations at each timestep, and reduce solver reliability under strongly nonlinear and multi-timescale transient conditions. This paper introduces RAPTOR, a first-of-its-kind time-domain simulation framework for power system dynamic simulations. At its core, RAPTOR introduces a new integration technique that represents the unknown trajectory of hybrid differential-algebraic equations (DAEs) over a time interval using a physics-informed random-projection neural network (PIRPNN) built from fixed Gaussian radial basis functions (RBFs). A nonlinear solver, e.g., Newton-Raphson, determines how to combine the fixed RBFs so that the resulting trajectory satisfies the governing equations. By combining RBFs with broad and localized shapes, RAPTOR can represent complex multi-timescale behavior over comparatively long time intervals. This enables larger effective simulation advances, fewer overall nonlinear solver iterations, and faster integration over long time horizons. Numerical studies on stiff RMS models, IEEE 9-, 14-, 39-, 57-, and 118-bus RMS simulation benchmarks, and EMT test cases show that RAPTOR accurately finds solutions with substantially fewer sequential simulation advances while offering superior accuracy-runtime performance. With speedups of over 10x in certain cases, these results showcase RAPTOR's potential to outperform long-standing and widely used integration methods, such as the Radau method and the trapezoidal rule.

Figures & tables

Fig. 2 : Workflow of the RAPTOR solver, including interval proposal, PIRPNN coefficient initialization, nonlinear residual minimization, residual-based acceptance, and PI-based interval-length update.

Figure 2

Relative Speed Up
Metric	IEEE 9	IEEE 14	IEEE 39	IEEE 57	IEEE 118
State MAE ( $10^{-8}$ )	5.44	8.54	18.7	9.70	2.42
$\|V\|$ MAE ( $10^{-8}$ )	1.65	2.52	6.60	1.81	0.671
Time [ms]	26.0	39.0	80.9	62.0	311.5
Intervals	28	22	27	23	32
BDF ( $\times$ )	2.79	2.45	1.91	1.96	2.19

TABLE I : IEEE RMS DAE benchmark performance for

t_{f}=1

s. Errors are RAPTOR MAEs, and speedup of RAPTOR is relative to the fastest accuracy-qualified configuration of each solver.

Numerical Integration

See all 24 papers

Predicting Power-System Dynamic Trajectories with Foundation Models
Apr 16, 2026Haoran Li, Lihao Mai, Chenhan Xiao +2Neural Surrogate Modeling Zero-Shot Time Series Forecasting
School of Electrical, Computer and Energy Engineering at Arizona State University, Tempe, AZ 85281 USA · MOVEJ Analytics, Dayton, OH 45324 USA
The Physics Is the Network: Fast, Training-Free Neural Emulation
Oct 14, 2026Luka Todorovic, Kaushal Gianchandani, Sai RavelaNeural PDE Solvers Neural Surrogate Modeling
Department of Mathematics and Department of Statistics, University of Michigan, Ann Arbor, MI · NASA Postdoctoral Program Fellow, NASA Goddard Institute for Space Studies, New York, NY · Department of Earth, Atmospheric, and Planetary Sciences, Massachusetts Institute of Technology, Cambridge, MA
Transolver- $σ$ : Joint Spectral-Physical Subspace Modeling for Neural PDE Solving
Sep 29, 2026Haonan Shangguan, Hang Zhou, Haixu Wu +3Fourier Neural Operator Neural PDE Solvers
School of Software, BNRist, Tsinghua University · MIT CSAIL

Apr 16, 2026J/K move · Enter open · S save

Predicting Power-System Dynamic Trajectories with Foundation Models

Haoran Li, Lihao Mai, Chenhan Xiao, Erik Blasch+1

School of Electrical, Computer and Energy Engineering at Arizona State University, Tempe, AZ 85281 USA · MOVEJ Analytics, Dayton, OH 45324 USA

Neural Surrogate Modeling Zero-Shot Time Series Forecasting Time-Series Foundation Models Power Systems

Open paper AskPDF arXiv

As power systems transition toward renewable-rich and inverter-dominated operations, accurate time-domain dynamic analysis becomes increasingly critical. Such analysis supports key operational tasks, including transient stability assessment, dynamic security analysis, contingency screening, and post-fault trajectory evaluation. In practice, these tasks may operate under several challenges, including unknown and time-varying system parameters, privacy constraints on data sharing, and the need for fast online inference. Existing learning-based approaches are typically trained for individual systems and therefore lack generalization across operating conditions and physical parameters. Hence, this paper proposes LArge Scale Small ODE (LASS)-ODE-Power, a learning framework for general-purpose time-domain prediction. The proposed approach leverages large-scale pretraining on more than 40 GB of DAE or ordinary differential-equation (ODE) trajectories to learn transferable representations. The resulting model supports trajectory prediction from short measurement prefixes across diverse dynamic regimes, including electromechanical and inverter-driven systems. Hence, the model can be directly used without data sharing in a zero-shot setting. In addition, the proposed architecture incorporates parallel and linearized computation to achieve fast inference. Moreover, to enhance task-specific performance in power systems, a specialized fine-tuning strategy is developed based on approximately 1 GB of heterogeneous power-system dynamic data. Extensive experiments over diverse power-system simulation scenarios demonstrate that LASS-ODE-Power consistently outperforms existing learning-based models in trajectory prediction accuracy with efficient inference.

Abstract

Numerical Integration

Explore similar work

Predicting Power-System Dynamic Trajectories with Foundation Models

The Physics Is the Network: Fast, Training-Free Neural Emulation

Transolver-σσσ: Joint Spectral-Physical Subspace Modeling for Neural PDE Solving

Transolver- $σ$ : Joint Spectral-Physical Subspace Modeling for Neural PDE Solving