Source-Load Scenario Controllable Generation Method Combined with Speculative Sampling Acceleration

As the proportion of new energy generation in the power system increases fastly, the impact of the source side on the power system continues to rise, resulting in complex spatiotemporal uncertainty of source and load, which brings difficulties to the operation and dispatch of the power system. Source-load scenario generation technology quantifies and models the uncertainties of both the generation side and the load side, providing scientific decision support for the planning, operation, and scheduling of power systems. This paper first proposes a method for generating controllable source-load scenarios based on the diffusion model, combining the Contrastive Language-Image Pre-training model and the Variational Auto-Encoder to enrich scenario information, enriching the randomness of the generated scenarios. Secondly, based on speculative sampling acceleration, a diffusion model acceleration method for denoising is designed to save computational costs in scenario generation. Verification through case studies shows that the proposed scenario generation method effectively achieves controllable generation of four different scenarios. The denoising process acceleration method based on speculative sampling can achieve a <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 7. 7 6 \%}$</tex> acceleration with a 7.09 % loss in quality.