Research on the construction and implementation of power grid fault handling knowledge graphs

Abstract

Power grid fault disposal has important guiding significance for the efficient and orderly emergency work of power grid accidents. The knowledge graph technology is used to extract, express and manage the fault disposal information. It is also used to assist dispatchers in fault handling, which can effectively improve the power grid emergency handling capacity and dispatching intelligence level. The unstructured content in the form of a large number of texts in the power grid dispatching operation link is condensed into a structured knowledge network that can be expressed, operated and reasoned. For example, operating procedures, disposal plans, dispatching rules, etc. A top-down and bottom-up knowledge graph construction method for power grid fault handling is proposed. The knowledge graphs are divided into three categories: entity graph of power grid equipment, logic graph of fault handling and case graph. The data and technical means required for graph construction are described. In the process of practice, the knowledge organization structure, notion types, and relationships between notions of the knowledge graphs are defined to form the model layer of knowledge graph. Finally, according to the function realization of each link, the solution ideas and key technologies are analyzed. So as to realize fault information analysis and discrimination based on knowledge atlas, intelligent aided decision-making and multi-dimensional human–computer interaction.