Real-Time Monitoring and Fault Diagnosis Technology of Virtual Power Plant

Yue Guo, Xiangyu Yuan, Zhaofeng Guo, Botao Wang, Xiang Li2025 · DOI

Abstract

In this paper, the real-time monitoring and fault diagnosis technology of virtual power plant (VPP) is deeply discussed to solve the challenges of safe, stable and efficient operation brought by its scale expansion and system complexity. Real-time monitoring provides decision-making basis for operators through data acquisition, transmission, processing and visualization, optimizes energy distribution and scheduling, and improves energy utilization efficiency. Fault diagnosis technology can quickly identify fault types, locate fault locations and take repair measures to reduce downtime and maintenance costs. In this paper, a three-tier architecture design of “edge layer-platform layer-application layer” is proposed, which covers core functional modules such as data acquisition, state awareness and anomaly warning. Multisource data fusion technology optimizes data processing, dynamic state evaluation model quantifies operation state through equipment health index, and data-driven fault diagnosis technology adopts mixed diagnosis method, which combines mechanism model, migration learning and knowledge map reasoning to meet the diagnosis needs of different types of faults. The verification case shows that the consumption rate of renewable energy is increased from 85% to 93 %, the average fault location time is shortened from 45 minutes to 8 minutes, the false alarm rate is reduced from 12.5 % to 3.2 %, and the annual operating income is increased from 12 million yuan to 14.3 million yuan, which significantly improves the reliability and economic benefits of the system and promotes the digital transformation of the power industry.
BibTeX
@misc{guo2025real,
  author = {Yue Guo and Xiangyu Yuan and Zhaofeng Guo and Botao Wang and Xiang Li},
  title = {{Real-Time Monitoring and Fault Diagnosis Technology of Virtual Power Plant}},
  year = {2025},
  doi = {10.1109/telepe66277.2025.00011},
}

Loading related content...

Figure