Cross-Correlated Scenario Generation for Renewable-Rich Power Systems Using Implicit Generative Models

Generation of realistic scenarios is an important prerequisite for analyzing the reliability renewable-rich power systems. This paper satisfies this need by presenting end-to-end model-free approach creating representative system on a seasonal basis. A conditional recurrent generative adversarial network serves as main engine scenario generation. Compared to prior generation models that treated variables independently or focused short-term forecasting, proposed implicit model effectively captures cross-correlations exist between considering long-term planning. The validity generated using demonstrated through extensive statistical evaluation and investigation end-application results. It shown analysis abnormal scenarios, which more critical resource planning, benefits most from cross-correlated