Resilience-Oriented Extreme Weather Conditional Renewable Scenario Generation Based on Diffusion Models and Few-shot Learning
Several natural disasters worldwide have demonstrated that the severity of extreme weather events (EWEs) on power systems can be increased by adversely affecting renewable power. Generating renewable scenarios specific to EWEs is crucial for the effective implementation of resilience-oriented operations and planning in power systems that incorporate a high proportion of renewable energies. Despite the significant progress achieved recently, it remains a formidable challenge to produce high-quality samples from a limited dataset due to the low occurrence probability of EWEs. A conditional diffusion model-based method is firstly introduced to discern spatiotemporal correlations of renewable series assoicated with common conditional like diurnal, season, and temperature without suffering from prevalent issues like statistical assumptions and mode collapse. To guarantee the specificity of the generated samples to EWEs while maintaining diversity, a fine-tuning mechanism is proposed for the pre-trained diffusion models using a few-shot learning technology in conjunction with a self-supervised loss function. The effectiveness of the proposed method is verified on two real-world dataset. Numerical results demonstrate that the scenarios generated by the proposed method exhibit distinct advantages in terms of diversity and EWE-specific consistency. This facilitates scenario-based two-stage robust optimization and enhances the performance of resilience-oriented decisions in out-of-sample scenarios.
Email Address of Submitting Author22060127@zju.edu.cn
Submitting Author's InstitutionZhejiang University
Submitting Author's Country