Physics-Aware LLM-Based Probabilistic Wind Power Scenario Generation under Extreme Icing Conditions

TL;DR

This paper introduces a physics-aware LLM framework for generating realistic wind power scenarios during extreme icing, improving resilience planning in power systems.

Contribution

It combines physical modeling, multimodal tokenization, and causal Transformer architecture to produce physically consistent wind power scenarios under icing conditions.

Findings

Reproduces icing-induced power degradation accurately.

Generates high-fidelity, physically consistent wind power scenarios.

Enhances resilience assessment for renewable power systems.

Abstract

Accurately characterizing wind power uncertainty under icing and post-disaster conditions remains a critical challenge for resilient power system operation. To address this issue, this paper proposes a physics-aware large language model (LLM) framework for probabilistic wind power scenario generation under extreme icing conditions. The proposed framework integrates supervisory control and data acquisition (SCADA)-based physical modeling, multimodal tokenization, and a causal Transformer architecture trained in an autoregressive manner. A physics-aware decoding scheme effectively enforces rated power limits and ramping constraints on the generated trajectories while preserving stochastic diversity. Case studies using real wind turbine data show that the proposed method reproduces icing-induced power degradation and temporal variability observed during extreme weather. The resulting scenarios are physically consistent and high-fidelity, thereby significantly enhancing resilience assessment and recovery planning in renewable-integrated power systems.