Article: Fault diagnosis and self-healing of power line carrier communication enabled by artificial intelligence: smart grid application based on data mining Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.61 pp.24 - 58 Abstract: Aiming at the core problems faced by the power line carrier communication system of smart grid, such as severe channel attenuation, complex and changeable interference sources, delayed fault location and slow self-healing response, and the existing methods have significant shortcomings in reliability, real-time and scene adaptability, this paper proposes an intelligent optimisation scheme based on the integration of data mining and artificial intelligence (IOSDM-AI). Through the multi-model coupling mechanism, the scheme is driven by real-time communication data flow to achieve accurate fault diagnosis, rapid location and adaptive self-healing, while ensuring the stable operation of the system. The results show that the accuracy of IOSDM-AI algorithm is 94.7%, the diagnosis delay is reduced to 108.3 ms, and the missed diagnosis rate and misdiagnosis rate are as low as 0.7% and 2.1%, respectively. The self-healing success rate is 96. 8%, the average self-healing time is reduced to 2.3 s, the communication link stability index is 9.28, and the self-healing strategy execution accuracy (FSE) is 428. Inderscience Publishers - linking academia, business and industry through research

Title: Fault diagnosis and self-healing of power line carrier communication enabled by artificial intelligence: smart grid application based on data mining

Authors: Benrong Wang; Wei Huang

Addresses: School of Information Engineering, Jingdezhen University, JiangXi, 333000, China ' School of Information Engineering, Jingdezhen University, JiangXi, 333000, China

Abstract: Aiming at the core problems faced by the power line carrier communication system of smart grid, such as severe channel attenuation, complex and changeable interference sources, delayed fault location and slow self-healing response, and the existing methods have significant shortcomings in reliability, real-time and scene adaptability, this paper proposes an intelligent optimisation scheme based on the integration of data mining and artificial intelligence (IOSDM-AI). Through the multi-model coupling mechanism, the scheme is driven by real-time communication data flow to achieve accurate fault diagnosis, rapid location and adaptive self-healing, while ensuring the stable operation of the system. The results show that the accuracy of IOSDM-AI algorithm is 94.7%, the diagnosis delay is reduced to 108.3 ms, and the missed diagnosis rate and misdiagnosis rate are as low as 0.7% and 2.1%, respectively. The self-healing success rate is 96. 8%, the average self-healing time is reduced to 2.3 s, the communication link stability index is 9.28, and the self-healing strategy execution accuracy (FSE) is 428.

Keywords: smart grid; power line carrier communication; artificial intelligence; fault diagnosis; self-healing mechanism; data mining.

DOI: 10.1504/IJICT.2026.153942

International Journal of Information and Communication Technology, 2026 Vol.27 No.61, pp.24 - 58

Received: 27 Jan 2026
Accepted: 24 Mar 2026
Published online: 08 Jun 2026 *

Title: Fault diagnosis and self-healing of power line carrier communication enabled by artificial intelligence: smart grid application based on data mining

Keep up-to-date