1.Digital Grid Research Institute Co., Ltd., China Southern Power Grid, Guangzhou 510663, China;2.Zhejiang University-China Southern Power Grid Joint Research Centre on AI, Hangzhou 310058, China;3.College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, China

The combined data-knowledge-driven artificial intelligence method is a better combined method that utilizes the advantages of data-driven and knowledge-driven methods, complementing each other’s strengths and weaknesses. The paper analyzes the characteristics and current situation of the combined-driven methods, classifies and calculates its key application scenarios in power dispatching. The innovation, improvement, and application advantages of combined-driven methods in various scenarios compared to single methods are summarized. Three combined modeling methods for power dispatching combined data-knowledge-driven methods have been summarized: data-driven optimizing knowledge-driven mode, knowledge-driven assisting data-riven mode, and hybrid data-knowledge-driven mode. Finally, the challenging issues in combined modeling are discussed from five dimensions: the balance between accuracy and efficiency, effectiveness, and reliability. The application scenarios of combined-driven methods in power dispatching are discussed and prospected.