Knowledge Graph for Power Grid Dispatching of Digital Homes based on Graph Convolutional Network

With the wide deployment of numerous digital media equipment into home and life, power grid dispatching (PGD) systems, as the energy source of digital media equipment, generate a large amount of data. Those data are stored in large volumes, various types, separate features, and lacking unified data specifications, making it harder to organize and learn. In view of the above challenges, inspired by the knowledge graph models which hold strong power for knowledge representing and reasoning, this paper constructs a knowledge graph model for power grid dispatching regulations with graph convolutional network (KGPGD). Specifically, in the context of the massive growth of grid dispatching data, knowledge extraction methods are used to obtain the entity words and relation words in the specification from the smart grid dispatching control system. The dataset of technical specifications of the smart grid dispatching control system is the real-world provided by the Northeast Branch of State Grid Corporation of China. And then a domain knowledge graph is automatically constructed to study domain-oriented big data of PGD. At the same time, the graph convolutional neural network model is utilized to learn the power grid dispatching knowledge graph features. KGPGD provides a reference basis and decision support for the formulation of the technical specifications of the power grid dispatching system of digital homes.