Intelligent Distribution-Network Fault Handling via Cross-Modal Semantic Fusion and Knowledge-Graph Reasoning
DOI:
https://doi.org/10.4108/ew.13683Keywords:
Power distribution network fault handling, semantic communications, cross-modal fusion, knowledge graph reasoning, deep reinforcement learningAbstract
Power distribution network fault handling imposes stringent requirements on both response timeliness and decision reliability. The high penetration of distributed renewable generation, the widespread deployment of power-electronic devices, and increasing operating-condition fluctuations further intensify the complexity and uncertainty of fault mechanisms. To address the challenges of cross-validating multi-source heterogeneous information, structurally invoking fault-handling knowledge, and balancing latency and accuracy under resource constraints, this paper develops a cross-modal semantic fusion and knowledge-graph reasoning–based fault-handling system, termed CM-SKG. The system takes synchronous phasor measurement unit (PMU) electrical measurements and UAV dual-spectrum inspection images as its primary information sources, and establishes a closed-loop architecture that integrates semantic sensing, transmission, and reasoning. Specifically, task-oriented semantic representations and controllable compression are performed at the edge device; at the edge server, a learnable semantic alignment matrix and a bidirectional interactive attention mechanism are employed for cross-modal fusion, effectively mitigating granularity discrepancies across heterogeneous data and producing consistent fault semantic evidence; at the control center, a fault-handling knowledge graph is introduced for reasoning, mapping fused semantics to executable handling actions, while a tunable reasoning-depth mechanism enables smooth switching between fast response and deeper inference. Furthermore, we propose a semantic communication efficiency (SCE) metric that jointly accounts for cross-modal fusion quality, reasoning reliability, and end-to-end latency, and use it to drive the coordinated optimization of compression ratio, reasoning depth, and computational resources. Online policy learning is realized via a distributional soft actor–critic (DSAC) algorithm. Simulation results demonstrate that CM-SKG significantly improves fault-handling accuracy and decision stability while satisfying real-time constraints.
Downloads
References
[1] R. He, H. Liang, J. Wu, H. Xie, and M. Shahidehpour, “Reliability assessment of cyber-physical distribution system using multi-dimensional information network model,” IEEE Trans. Smart Grid, vol. 14, no. 6, pp. 4683–4692, Nov. 2023.
[2] A. R. Aji, K. M. Banjarnahor, M. S. Hadi, and N. Hariyanto, “Development of FLISR algorithm with additional consideration of reliability index, losses, and load forecasting: Case study in Central Java distribution, Indonesia,” in Proc. 6th Int. Conf. Power Eng. Renew. Energy (ICPERE), Bandung, Indonesia, 2024, pp. 1–5.
[3] B. Moussa, A. Al-Barakati, M. Kassouf, M. Debbabi, and C. Assi, “Exploiting the vulnerability of relative data alignment in phasor data concentrators to time synchronization attacks,” IEEE Trans. Smart Grid, vol. 11, no. 3, pp. 2541–2551, May 2020.
[4] Y. Zhao and Y. He, “Research on application of multimodal data integration in smart grid fault diagnosis,” in Proc. 6th Int. Conf. Electr., Electron. Inf. Commun. Eng. (EEICE), 2025.
[5] J. Zhu, C. Fan, S. Li, K. Nie, J. Li, and Z. He, “SEDNet: Substation equipment detection network with an attention mechanism for UAV automatic power inspection,” IEEE Trans. Instrum. Meas., vol. 74, Art. no. 5036114, 2025.
[6] R. Wang, H. Zhang, S. Zhang, H. Liao, and Z. Zhou, “High-frequency acquisition and low-latency interaction method for distribution network data based on sensing-communication collaboration,” Trans. China Electrotech. Soc., published online, 2025. (in Chinese)
[7] D. Sarathkumar et al., “A technical review on classification of various faults in smart grid systems,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 1055, no. 1, 2021.
[8] N. T. Hoa, C. T. T. Hai, H. L. Hung, N. C. Luong, and D. Niyato, “Joint edge computing and semantic communication in UAV-enabled networks,” IEEE Commun. Lett., vol. 29, no. 1, pp. 80–84, Jan. 2025.
[9] H. Liao, W. Che, Z. Zhou, X. Wang, A. Ali, and M. Guizani, “Electric semantic short packet communication: A green ISAC perspective,” in Proc. IEEE Int. Conf. Commun. (ICC), Montreal, QC, Canada, 2025, pp. 674–679.
[10] T. M. Getu, G. Kaddoum, and M. Bennis, “Semantic communication: A survey on research landscape, challenges, and future directions,” Proc. IEEE, vol. 112, no. 11, pp. 1649–1685, Nov. 2024.
[11] C. E. Shannon and W. Weaver, The Mathematical Theory of Communication. Urbana, IL, USA: Univ. Illinois Press, 1949.
[12] T. M. Getu, G. Kaddoum, and M. Bennis, “Making sense of meaning: Semantic metrics for goal-oriented communication,” IEEE Access, vol. 11, pp. 45456–45492, 2023.
[13] T. M. Getu, G. Kaddoum, and M. Bennis, “Tutorial-cum-survey on semantic and goal-oriented communication: Research landscape, challenges, and future directions,” Apr. 2023, arXiv:2301.12786.
[14] K. B. Letaief, Y. Shi, J. Lu, and J. Lu, “Edge artificial intelligence for 6G: Vision, enabling technologies, and applications,” IEEE J. Sel. Areas Commun., vol. 40, no. 1, pp. 5–36, Jan. 2022.
[15] F. Guo, F. R. Yu, H. Zhang, X. Li, H. Ji, and V. C. M. Leung, “Enabling massive IoT toward 6G: A comprehensive survey,” IEEE Internet Things J., vol. 8, no. 15, pp. 11891–11915, Aug. 2021.
[16] L. U. Khan, I. Yaqoob, M. Imran, Z. Han, and C. S. Hong, “6G wireless systems: A vision, architectural elements, and future directions,” IEEE Access, vol. 8, pp. 147029–147044, 2020.
[17] Y. Xiao, G. Shi, Y. Li, W. Saad, and H. V. Poor, “Toward self-learning edge intelligence in 6G,” IEEE Commun. Mag., vol. 58, no. 12, pp. 34–40, Dec. 2020.
[18] Z. Zhou, X. Chen, E. Li, L. Zeng, K. Luo, and J. Zhang, “Edge intelligence: Paving the last mile of artificial intelligence with edge computing,” Proc. IEEE, vol. 107, no. 8, pp. 1738–1762, Aug. 2019.
[19] L. Zhou, D. Wu, J. Chen, and X. Wei, “Cross-modal collaborative communications,” IEEE Wireless Commun., vol. 27, no. 2, pp. 112–117, Apr. 2020.
[20] M. Chen, M. Liu, W. Wang, H. Dou, and L. Wang, “Cross-modal semantic communications in 6G,” in Proc. IEEE/CIC Int. Conf. Commun. China (ICCC), Dalian, China, 2023, pp. 1–6.
[21] S. Zhang et al., “Knowledge-augmented neural reasoning for multi-hop QA,” in Proc. ACL, 2021, pp. 1234–1244.
[22] C. Chaccour, W. Saad, M. Debbah, Z. Han, and H. V. Poor, “Less data, more knowledge: Building next generation semantic communication networks,” Nov. 2022, arXiv:2211.14343.
[23] Z. Zhang, L. Wang, W. Wu, F. Zhou, and Q. Wu, “Knowledge graph-based explainable and generalized zero-shot semantic communications,” IEEE Wireless Commun. Lett., vol. 14, no. 9, pp. 2977–2981, Sep. 2025.
[24] X. Song, F. Zhou, R. Ding, Z. Qu, Y. Li, Q. Wu, and N. Al-Dhahir, “UAV cognitive semantic communications enabled by knowledge graph for robust object detection,” IEEE Trans. Commun., vol. 73, no. 8, pp. 6052–6067, Aug. 2025.
[25] J. Li, Z. Wang, and F. Luo, “Power equipment knowledge graph for intelligent fault detection,” IEEE Trans. Ind. Informat., vol. 17, no. 12, pp. 8452–8463, 2021.
[26] Z. Sun, H. Lin, and X. Wang, “Dispatch knowledge graph for distributed energy management,” IEEE Trans. Smart Grid, vol. 13, no. 1, pp. 388–400, 2022.
[27] J. Pi, S. Qi, Q. He et al., “Construction and application of knowledge graph for intelligent decision-making of power grid fault handling,” in Proc. IEEE PES Gen. Meeting, 2023, pp. 1–5.
[28] H. Yang et al., “Graph neural networks for knowledge reasoning: Foundations and advances,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 10, pp. 5275–5293, 2022.
[29] T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine, “Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor,” in Proc. ICML, 2018, pp. 1861–1870.
[30] J. Duan, Y. Guan, S. E. Li, Y. Ren, Q. Sun, and B. Cheng, “Distributional soft actor-critic: Off-policy reinforcement learning for addressing value estimation errors,” IEEE Trans. Neural Netw. Learn. Syst., vol. 33, no. 11, pp. 6584–6598, Nov. 2022.
[31] J. Duan, Y. Ren, F. Zhang, J. Li, S. E. Li, Y. Guan, and K. Li, “Encoding distributional soft actor-critic for autonomous driving in multi-lane scenarios [Research Frontier],” IEEE Comput. Intell. Mag., vol. 19, no. 2, pp. 96–112, 2024.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Fangzhou Liu, Yang Zhao, Jiqiao Chen, Ting Luo
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open-access article distributed under the terms of the Creative Commons Attribution CC BY 4.0 license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.
