An LLM-Enabled Frequency-Aware Flow Diffusion Model for Natural-Language-Guided Power System Scenario Generation

2026-02-23

AI Summary

This work proposes the first natural language–guided framework for power system scenario generation, addressing the limitations of existing methods that rely on fixed-length numerical conditions and struggle to accommodate diverse user requirements. The approach leverages a pre-trained large language model to map user instructions into semantic representations, which are then used by a flow-based diffusion model to efficiently generate high-quality power scenarios. To mitigate frequency deviations, a frequency-aware multi-objective optimization scheme is introduced. Furthermore, a dual-agent training framework is designed to construct text-scenario paired data and establish a semantic evaluation metric. Experiments on large-scale photovoltaic and load datasets demonstrate that the proposed method significantly enhances the controllability, diversity, and semantic consistency of generated scenarios.

Technology Category

• Natural Language Processing: Generation
• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Diverse and controllable scenario generation (e.g., wind, solar, load, etc.) is critical for robust power system planning and operation. As AI-based scenario generation methods are becoming the mainstream, existing methods (e.g., Conditional Generative Adversarial Nets) mainly rely on a fixed-length numerical conditioning vector to control the generation results, facing challenges in user conveniency and generation flexibility. In this paper, a natural-language-guided scenario generation framework, named LLM-enabled Frequency-aware Flow Diffusion (LFFD), is proposed to enable users to generate desired scenarios using plain human language. First, a pretrained LLM module is introduced to convert generation requests described by unstructured natural languages into ordered semantic space. Second, instead of using standard diffusion models, a flow diffusion model employing a rectified flow matching objective is introduced to achieve efficient and high-quality scenario generation, taking the LLM output as the model input. During the model training process, a frequency-aware multi-objective optimization algorithm is introduced to mitigate the frequency-bias issue. Meanwhile, a dual-agent framework is designed to create text-scenario training sample pairs as well as to standardize semantic evaluation. Experiments based on large-scale photovoltaic and load datasets demonstrate the effectiveness of the proposed method.

Problem

• scenario generation
• natural language guidance
• power system
• conditional generation
• user flexibility

Innovation

• LLM-enabled
• flow diffusion
• natural-language-guided
• frequency-aware
• scenario generation