.png){kind=icon}
.png){kind=icon}
Return
OniOn: An RGCN-Based Ontology Alignment Approach for Energy Data Integration
.png){kind=icon}
PRE
AI
N
A
K
W
V
DOI：10.1007/978-3-031-99554-5_16.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Compared to the other domains, the energy sector relies on a large amount of time series and structured data, which is highly dynamic and distributed. With the growth of energy system research, efficient data integration has become a critical task, particularly in systems such as smart grids with distributed energy resources as well as distributed data sources. Inevitably, energy data resources are diverse and heterogeneous in formats, standards, and structures. These characteristics cause significant challenges for effectively sharing and using energy system data. To address these challenges, we conceptualize an Ontology-Based Data Integration (OBDI) framework. Since energy-related ontologies are quite diverse, according to the diverse energy data resources, we develop a novel ontology matching approach, OniOn. It is based on Relational Graph Convolutional Networks (RGCN) to address semantic differences and overlapping, which supports dynamic and scalable data integration and improves interoperability between different energy systems.
Keywords:
Ontology-based Data Integration
Ontology Matching
Graph Neural Network
Journal
S
IF:
0
Papers:
47
Citations:
0
Organization
Cited Papers