A novel conditional diffusion model for joint source-load scenario generation considering both diversity and controllability

The intermittency of renewable energy and the volatility of multi-energy loads result in multiple joint source-load uncertainties and source-load spatio-temporal mismatch for the scenario generation of deep decarbonized power systems (DDPSs). To address these challenges, a novel model named conditional diffusion-based scenario generation (CDSG) is proposed for controllable joint source-load scenario generation (controllable-JSLSG). The CDSG model incorporates a specialized scenario noise prediction network that includes a conditional spatio-temporal fusion module (CSTFM) and a conditional scenario noise estimation module (CSNEM). Specifically, the CSTFM is devised to excavate the complex spatio-temporal correlations among source-load scenarios, and the CSNEM is utilized to adaptively learn the weights between condition information and source-load scenarios. Then the pretrained CDSG effectively models the nonlinear and irregular spatio-temporal dynamics of source-load, contributing to the controllability and diversity of the generated source-load scenarios. Results verified on real-world datasets demonstrate that CDSG can generate source-load scenarios satisfying dynamic fluctuation properties and frequency-domain characteristics, and ensuring the complex spatio-temporal correlations can be captured. Moreover, compared with other advanced benchmarks, CDSG achieves optimal diversity while maintaining high-quality, indicating its potential for the generation of realistic and diverse joint source-load scenarios. Finally, an optimal dispatch of DDPS is also simulated to evaluate the practical feasibility of the source-load scenarios generated by CDSG.