Multimodal Knowledge Fusion and Ontological Reasoning for Distributed Energy Resources in Power Systems: A Semantic-Driven Framework
Keywords:
Knowledge Graph, Basic Formal Ontology, Cross-modal Reasoning, Fault Diagnosis, Semantic-Driven FrameworkAbstract
Distributed Energy Resources (DERs) generate heterogeneous operational information spanning sensor measurements, equipment topology, engineering documents, and maintenance requirements. Although existing power-system monitoring and data-fusion methods can process individual data sources effectively, their outputs are often represented and analyzed independently, limiting the ability to relate numerical anomalies to their physical and operational context. This paper proposes a semantic-driven multimodal knowledge fusion framework that integrates heterogeneous DER information through a unified ontological representation. The framework comprises four layers: Data, Ontology, Information, and Knowledge. A top-level DER ontology aligned with the BFO provides a common semantic structure for representing facilities, equipment, processes, events, operational states, technical requirements, regulations, and organizations. Modality-specific information extraction methods transform textual documents, engineering information, and multivariate sensor streams into structured entities and events, which are subsequently reconciled through entity matching and multi-view entity alignment and integrated into a Knowledge Graph. The framework is demonstrated using a fault-diagnosis case study involving a 1 MW photovoltaic sub-array. By combining CIM-derived equipment topology, an operational threshold extracted from an OEM manual, and real-time SCADA sensor events, the Knowledge Graph associates simultaneous power-loss symptoms across ten PV strings with their common upstream inverter. Cross-modal reasoning further identifies an inverter temperature exceeding the derating threshold, tracing the observed alarm pattern to inverter thermal derating and producing a targeted cooling-fan inspection recommendation. The results demonstrate how ontology-mediated knowledge fusion can transform fragmented multimodal observations into a traceable diagnostic reasoning chain, providing a foundation for explainable fault diagnosis and knowledge-driven maintenance in heterogeneous DER environments.
References
Arp, R.; Smith, B.; Spear, A.D. Building Ontologies with Basic Formal Ontology. The MIT Press, 2015. https://doi.org/10.7551/mitpress/9780262527811.001.0001
Chasseray, Y.; Barthe-Delanoë, A.-M.; Négny, S.; Le Lann, J.-M. Knowledge Extraction from Textual Data and Performance Evaluation in an Unsupervised Context. Information Sciences 2023, 629, 324–343. https://doi.org/10.1016/j.ins.2023.01.150
Chen, D.; Chen, L.; Yang, Y.; et al. A Knowledge-Driven Approach for Automated Fire Safety Compliance Checking in Operational Buildings. Knowledge-Based Systems 2026, 336, 115156. https://doi.org/10.1016/j.knosys.2025.115156
Chen, D.; Chen, L.; Zhang, Y.; Lin, S.; Ye, M.; Sølvsten, S. Automated Fire Risk Assessment and Mitigation in Building Blueprints Using Computer Vision and Deep Generative Models. Advanced Engineering Informatics 2024, 62, 102614. https://doi.org/10.1016/j.aei.2024.102614
Dogdu, E.; Ozbayoglu, A.M.; Benli, O.; et al. Ontology-Centric Data Modelling and Decision Support in Smart Grid Applications: A Distribution Service Operator Perspective. In Proceedings of the 2014 IEEE International Conference on Intelligent Energy and Power Systems (IEPS), 2014; pp. 198–204. https://doi.org/10.1109/IEPS.2014.6874179
Han, X.; Jiang, J.; Zhang, C.; Wen, Z.; Chen, G.; Liu, Y. Research on Quality Problems Management of Electric Power Equipment Based on Knowledge–Data Fusion Method. IET Generation, Transmission & Distribution 2020, 14(5), 745–751. https://doi.org/10.1049/iet-gtd.2019.0832
Hu, J.; Hu, W.; Chen, J.; et al. Fault Location and Classification for Distribution Systems Based on Deep Graph Learning Methods. Journal of Modern Power Systems and Clean Energy 2023, 11(1), 35–51. https://doi.org/10.35833/MPCE.2022.000204
InfluxData. InfluxDB. 2024. Available online: https://www.influxdata.com/products/influxdb/
Jiang, J.; Li, M. Entity Alignment Based on Multi-View Interaction Model in Vulnerability Knowledge Graphs. In Web and Big Data; Song, X.; Feng, R.; Chen, Y.; Li, J.; Min, G., Eds.; Lecture Notes in Computer Science, Vol. 14332; Springer, 2024. https://doi.org/10.1007/978-981-97-2390-4_34
Jie, Y.; Ji, X.; Yue, A.; et al. Combined Multi-Layer Feature Fusion and Edge Detection Method for Distributed Photovoltaic Power Station Identification. Energies 2020, 13(24). https://doi.org/10.3390/en13246742
Jing, L.; Zhao, M.; Li, P.; Xu, X. A Convolutional Neural Network Based Feature Learning and Fault Diagnosis Method for the Condition Monitoring of Gearbox. Measurement 2017, 111, 1–10. https://doi.org/10.1016/j.measurement.2017.07.017
Li, F.; Bai, W.; Liu, S.; Zhang, Y.; Guo, M. Grid resource data differentiation standard based on CIM model. Scientific Reports 2025, ahead of print. https://doi.org/10.1038/s41598-025-03420-x
Liu, M.; Chen, D.; Li, X.; Su, H.; Zhou, X. Voltage Control Strategy for Distribution Network Based on Incremental Learning and Knowledge Fusion. In Proceedings of the 2024 12th International Conference on Smart Grid (icSmartGrid), 2024; pp. 589–596. https://doi.org/10.1109/icSmartGrid61824.2024.10578128
López, G.; Custodio, V.; Moreno, J.I.; Sikora, M.; Moura, P.; Fernández, N. Modeling Smart Grid Neighborhoods with the ENERsip Ontology. Computers in Industry 2015, 70, 168–182. https://doi.org/10.1016/j.compind.2015.01.008
Luo, C.; Feng, Y.; Wu, K.; Zhou, J.; Wu, S.; Guo, X. Research on Multi-Source Data Fusion Standardization and User Electricity Knowledge Map Construction Technology of Distribution Network. In Proceedings of the 2023 IEEE 6th International Electrical and Energy Conference (CIEEC), 2023; pp. 209–214. https://doi.org/10.1109/CIEEC58067.2023.10166241
Lv, X.; Zhao, S.; Yu, X.; Zhao, B. Residential Floor Plan Recognition and Reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021; pp. 16717–16726.
Ma, K.; Tian, M.; Tan, Y.; et al. Ontology-Based BERT Model for Automated Information Extraction from Geological Hazard Reports. Journal of Earth Sciences 2023, 34, 1390–1405. https://doi.org/10.1007/s12583-022-1724-z
Nguyen, B.L.H.; Vu, T.V.; Nguyen, T.-T.; Panwar, M.; Hovsapian, R. Spatial-Temporal Recurrent Graph Neural Networks for Fault Diagnostics in Power Distribution Systems. IEEE Access 2023, 11, 46039–46050. https://doi.org/10.1109/ACCESS.2023.3273292
Pan, D.; Song, Z.; Nie, L.; Wang, B. Satellite Telemetry Data Anomaly Detection Using Bi-LSTM Prediction Based Model. In Proceedings of the 2020 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), 2020; pp. 1–6. https://doi.org/10.1109/I2MTC43012.2020.9129010
Qin, Q.; Zhao, S.; Liu, C. A BERT-BiGRU-CRF Model for Entity Recognition of Chinese Electronic Medical Records. Complexity 2021, 2021(1), 6631837. https://doi.org/10.1155/2021/6631837
Tomasevic, N.M.; Batic, M.C.; Blanes, L.M.; Keane, M.M.; Vranes, S. Ontology-Based Facility Data Model for Energy Management. Advanced Engineering Informatics 2015, 29(4), 971–984. https://doi.org/10.1016/j.aei.2015.09.003
Wang, H.; Huang, C.; Yu, H.; Zhang, J.; Wei, F. Method for Fault Location in a Low-Resistance Grounded Distribution Network Based on Multi-Source Information Fusion. International Journal of Electrical Power & Energy Systems 2021, 125, 106384. https://doi.org/10.1016/j.ijepes.2020.106384
Wang, S.; Pang, A.; Tian, D.; Zhang, J. Ontology Development and Knowledge Modelling for Photovoltaic Power Stations. In Proceedings of the 2024 5th International Conference on Computer Engineering and Application (ICCEA), 2024; pp. 1824–1831.
Wang, X.; Zhao, L.; Zhang, S.; Wang, Y.; Qin, D.; Sun, W. Self-Organizing-Map-Based Knowledge Fusion Method for Heterogeneous Ontologies in Power Grid Networks. In Proceedings of the 2020 5th International Conference on Mechanical, Control and Computer Engineering (ICMCCE), 2020; pp. 321–325. https://doi.org/10.1109/ICMCCE51767.2020.00078
Wang, Y.; Bai, X.; Liu, C.; Tan, J. A Multi-Source Data Feature Fusion and Expert Knowledge Integration Approach on Lithium-Ion Battery Anomaly Detection. Journal of Electrochemical Energy Conversion and Storage 2021, 19(2), 021003. https://doi.org/10.1115/1.4051716
Wu, J.; Orlandi, F.; AlSkaif, T.; O’Sullivan, D.; Dev, S. Ontology Modeling for Decentralized Household Energy Systems. In Proceedings of the 2021 International Conference on Smart Energy Systems and Technologies (SEST), 2021; pp. 1–6. https://doi.org/10.1109/SEST50973.2021.9543327
Wu, L.; Zhao, Y.; Qin, W.; et al. Knowledge-Data Fusion Model for Multivariate Load Short-Term Forecasting of Integrated Energy System. Journal of Shanghai Jiaotong University (Science) 2024, ahead of print. https://doi.org/10.1007/s12204-024-2740-1
Xin, Y.; Chen, L.; Yang, Y. Online Knowledge Fusion Method for Fault Diagnosis of Power Plant Equipment. In Proceedings of the 2023 IEEE 11th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2023; Vol. 11, pp. 1236–1240. https://doi.org/10.1109/ITAIC58329.2023.10408849
Xing, X.; Wang, N. Entity Matching Based on Attribute-Aware and Multi-Perspective Similarity Measurement. Journal of Information Science & Engineering 2023, 39(2).
Xu, Y.; Zhang, C.; Xu, Z.; et al. Tolerance Information Extraction for Mechanical Engineering Drawings – a Digital Image Processing and Deep Learning-Based Model. CIRP Journal of Manufacturing Science and Technology 2024, 50, 55–64. https://doi.org/10.1016/j.cirpj.2024.01.013
Yang, L.; Lv, C.; Wang, X.; et al. Collective Entity Alignment for Knowledge Fusion of Power Grid Dispatching Knowledge Graphs. IEEE/CAA Journal of Automatica Sinica 2022, 9(11), 1990–2004. https://doi.org/10.1109/JAS.2022.105947
Yang, Y.; Chen, Z.; Yan, J.; et al. Multi-Source Heterogeneous Information Fusion of Power Assets Based on Knowledge Graph. In Proceedings of the 2019 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI), 2019; pp. 213–218. https://doi.org/10.1109/SOLI48380.2019.8955005
Yoon, J.; Jordon, J.; van der Schaar, M. GAIN: Missing Data Imputation Using Generative Adversarial Nets. In Proceedings of the International Conference on Machine Learning, 2018; pp. 5689–5698.
Yu, Z.; Zhang, C.; Deng, C. An Improved GNN Using Dynamic Graph Embedding Mechanism: A Novel End-to-End Framework for Rolling Bearing Fault Diagnosis Under Variable Working Conditions. Mechanical Systems and Signal Processing 2023, 200, 110534. https://doi.org/10.1016/j.ymssp.2023.110534
Zhang, T.; Tao, L.; Wang, X.; et al. Hierarchical Cognize Framework for the Multi-Fault Diagnosis of the Interconnected System Based on Domain Knowledge and Data Fusion. Expert Systems with Applications 2022, 193, 116503. https://doi.org/10.1016/j.eswa.2022.116503
Downloads
Published
Data Availability Statement
Data will be made available on request.
