环境扰动测量下新能源电力系统惯量在线评估方法、系统及设备
By constructing an active power-frequency dynamic model and using an adaptive gradient descent algorithm to optimize the loss function, the problems of model dependence and hyperparameter sensitivity in the online inertia assessment of new energy power systems are solved, achieving high-precision and robust inertia assessment and supporting frequency security early warning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- EAST CHINA BRANCH OF STATE GRID CORP
- Filing Date
- 2025-12-04
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to achieve non-intrusive online assessment of the inertia of new energy power systems without significant disturbances or external signal injection. Furthermore, data-driven methods are highly dependent on mathematical models, sensitive to hyperparameters, and exhibit poor numerical stability, leading to large errors in the assessment results.
A dynamic model of active power and frequency of a new energy power system under environmental disturbances is constructed. An adaptive gradient descent algorithm is used to optimize the loss function. The equivalent inertia of the system is determined through iterative optimization. Frequency and active power deviation data are collected by phasor measurement units to realize online evaluation of inertia.
It achieves high-precision inertia assessment without large disturbances or external signal injection, reduces dependence on mathematical models, and improves the accuracy and robustness of assessment results. It is suitable for real-time inertia assessment at the unit level and regional level and supports frequency safety early warning.
Smart Images
Figure CN121965583B_ABST