Predicting Power-System Dynamic Trajectories with Foundation Models

2026-04-16

AI Summary

This work addresses the challenge of accurately predicting dynamic trajectories in power systems dominated by high-penetrating renewable energy and inverter-based resources, where traditional methods struggle under time-varying parameters, data privacy constraints, and diverse operating conditions. The authors propose LASS-ODE-Power, a novel framework that introduces the foundation model paradigm to power system dynamics for the first time. Leveraging over 40 GB of trajectory data generated by ordinary differential equations (ODEs), the framework employs large-scale pretraining combined with a parallelized linearized neural network architecture and a tailored fine-tuning strategy. It achieves highly accurate and efficient cross-system trajectory prediction in a zero-shot setting. Experimental results demonstrate that the proposed method significantly outperforms existing learning-based approaches across multiple scenarios, exhibiting superior generalization capability and computational efficiency.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• power-system dynamics
• trajectory prediction
• generalization
• time-domain analysis
• inverter-dominated systems

Innovation

• foundation models
• trajectory prediction
• zero-shot generalization
• ODE-based pretraining
• fast inference