A Novel Fault Diagnosis and Accurate Localization Method for a Power System Based on GraphSAGE Algorithm DOI Open Access
Fang Wang,

Zhijian Hu

Electronics, Journal Year: 2025, Volume and Issue: 14(6), P. 1219 - 1219

Published: March 20, 2025

Artificial intelligence (AI)-based fault diagnosis methods have been widely studied for power grids, with most research focusing on interval localization rather than precise point identification. In cases involving long-distance transmission lines or underground cables, merely locating the is insufficient. This paper presents a novel and method systems utilizing Graph Sample Aggregated (GraphSAGE) algorithm. A model are developed based system topology, identifying k-order adjacent nodes at both ends of interval. information then used to construct an accurate model. Leveraging strong inductive learning capability GraphSAGE, proposed effectively captures impact surrounding nodes, enabling localization. Experimental results demonstrate that offers high accuracy, localization, robust performance. The shows significant applicability in real-world scenarios, maintaining performance economic value across varying network topologies incomplete data collection.

Language: Английский

Comprehensive Examination of Thermal Energy Storage through Advanced Phase Change Material Integration forOptimized Buildings Energy Management and Thermal Comfort DOI Creative Commons
Muhammad Arslan,

Esha Ghaffar,

Amir Sohail

et al.

Energy and Built Environment, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

1
Power system stability with high integration of RESs and EVs: Benefits, challenges, tools, and solutions DOI
Ahmed Mohammed Saleh, István Vokony, Muhammad Waseem

et al.

Energy Reports, Journal Year: 2025, Volume and Issue: 13, P. 2637 - 2663

Published: Feb. 14, 2025

Language: Английский

Citations

0
An Evaluation of the Power System Stability for a Hybrid Power Plant Using Wind Speed and Cloud Distribution Forecasts DOI Creative Commons
Théodore Desiré Tchokomani Moukam, Akira Sugawara, Yuancheng Li

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(6), P. 1540 - 1540

Published: March 20, 2025

Power system stability (PSS) refers to the capacity of an electrical maintain a consistent equilibrium between generation and consumption electric power. In this paper, PSS is evaluated for “hybrid power plant” (HPP) which combines thermal, wind, solar photovoltaic (PV), hydropower in Niigata City. A new method estimating its PV also introduced based on NHK (the Japan Broadcasting Corporation)’s cloud distribution forecasts (CDFs) land ratio settings. Our objective achieve frequency (FS) while reducing CO2 emissions sector. So, according results terms FS variable. Six-minute autoregressive wind speed prediction (6ARW) support used (WP). One-hour GPV farm (1HWF) computed from Grid Point Value (GPV) data. The predicted using modelling CDFs. accordance with daily curve time, we can thermal planning. Actual data are measured every 10 min 1 min, respectively, controlled. simulation electricity fluctuations within ±0.2 Hz requirements Tohoku Electric Network Co,. Inc. testing evaluation days. Therefore, proposed supplies optimally stably contributing reductions emissions.

Language: Английский

Citations

0
A Novel Fault Diagnosis and Accurate Localization Method for a Power System Based on GraphSAGE Algorithm DOI Open Access
Fang Wang,

Zhijian Hu

Electronics, Journal Year: 2025, Volume and Issue: 14(6), P. 1219 - 1219

Published: March 20, 2025

Artificial intelligence (AI)-based fault diagnosis methods have been widely studied for power grids, with most research focusing on interval localization rather than precise point identification. In cases involving long-distance transmission lines or underground cables, merely locating the is insufficient. This paper presents a novel and method systems utilizing Graph Sample Aggregated (GraphSAGE) algorithm. A model are developed based system topology, identifying k-order adjacent nodes at both ends of interval. information then used to construct an accurate model. Leveraging strong inductive learning capability GraphSAGE, proposed effectively captures impact surrounding nodes, enabling localization. Experimental results demonstrate that offers high accuracy, localization, robust performance. The shows significant applicability in real-world scenarios, maintaining performance economic value across varying network topologies incomplete data collection.

Language: Английский

Citations

0