Wind Power Scenario Generation based on the Generalized Dynamic Factor Model and Generative Adversarial Network

2025-08-01

AI Summary

To address the challenge of generating statistically faithful long-term wind power scenarios for adequacy assessment, this paper proposes a synergistic generative framework integrating the Generalized Dynamic Factor Model (GDFM) with Generative Adversarial Networks (GANs). The GAN is innovatively employed as a temporal filter to learn dynamic time dependencies from common factors extracted via cross-spectral density analysis, thereby jointly modeling spatiotemporal correlations, waveform morphology, marginal distributions, ramp rates, and power spectral density. Evaluated on real-world Australian wind farm data, the framework significantly improves multi-dimensional statistical fidelity over conventional GDFM and standalone GAN approaches—particularly in reproducing frequency-domain characteristics and extreme ramp events. This advancement provides a more accurate and physically informed scenario generation tool for reliability evaluation of high-penetration wind power systems.

Technology Category

• Natural Language Processing: Generation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

For conducting resource adequacy studies, we synthesize multiple long-term wind power scenarios of distributed wind farms simultaneously by using the spatio-temporal features: spatial and temporal correlation, waveforms, marginal and ramp rates distributions of waveform, power spectral densities, and statistical characteristics. Generating the spatial correlation in scenarios requires the design of common factors for neighboring wind farms and antithetical factors for distant wind farms. The generalized dynamic factor model (GDFM) can extract the common factors through cross spectral density analysis, but it cannot closely imitate waveforms. The GAN can synthesize plausible samples representing the temporal correlation by verifying samples through a fake sample discriminator. To combine the advantages of GDFM and GAN, we use the GAN to provide a filter that extracts dynamic factors with temporal information from the observation data, and we then apply this filter in the GDFM to represent both spatial and frequency correlations of plausible waveforms. Numerical tests on the combination of GDFM and GAN have demonstrated performance improvements over competing alternatives in synthesizing wind power scenarios from Australia, better realizing plausible statistical characteristics of actual wind power compared to alternatives such as the GDFM with a filter synthesized from distributions of actual dynamic filters and the GAN with direct synthesis without dynamic factors.

Problem

• Generate realistic wind power scenarios using spatio-temporal features
• Combine GDFM and GAN to improve spatial and temporal correlation
• Enhance waveform imitation and statistical characteristics accuracy

Innovation

• Combines GDFM and GAN for wind power scenarios
• Extracts dynamic factors with temporal information
• Improves spatial and frequency correlations