Construction of Dynamic Knowledge Graph for Grid day-ahead Scheduling Optimization Decision

Abstract

As a new generation technology representative of knowledge engineering, knowledge graph is a large-scale semantic network, which has natural advantages in extracting knowledge from multi-source heterogeneous information, complex and highly correlated knowledge representation and reasoning. Based on the analysis of the application status of the grid day-ahead scheduling optimization decision-making technology and the demand for improving the intelligent processing capability, the key technologies and methods for the application of knowledge graph in the grid day-ahead scheduling optimization decision-making are proposed. The key technologies, application ideas and process methods of knowledge graphs are analyzed from the aspects of the design of knowledge ontology framework in the field of day-to-day dispatching of power grids, high-quality phrase mining and entity recognition, relation extraction and knowledge fusion, and scene-based dynamic knowledge graph update. Finally, the application and challenges of knowledge graph in the field of grid day-ahead scheduling in the future are summarized and prospected.