基于参数灵敏度的概率性光伏功率预测方法及系统
By combining physical models with data-driven models, a photovoltaic power prediction method has been developed, which solves the problems of systematic bias and uncertainty in photovoltaic power generation prediction, achieves high-precision probabilistic prediction, and improves the operational reliability of the power grid and the absorption capacity of photovoltaic power generation.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALIAN POWER SUPPLY COMPANY STATE GRID LIAONING ELECTRIC POWER
- Filing Date
- 2025-12-24
- Publication Date
- 2026-07-17
AI Technical Summary
Existing photovoltaic power prediction technologies suffer from systematic biases and uncertainties, making it impossible to accurately quantify the uncertainties in the prediction process. This leads to difficulties in grid dispatch and losses of curtailed solar power.
By constructing a probabilistic photovoltaic power prediction method based on parameter sensitivity, and combining a physical model with a data-driven model, error correction and uncertainty quantification are performed to generate rigorously calibrated probabilistic prediction information.
It has improved the accuracy and reliability of photovoltaic power generation forecasting, reduced grid security risks and curtailment energy losses, and enhanced the grid's ability to absorb renewable energy.
Smart Images
Figure CN122026309B_ABST
Abstract
Citation Information
Patent Citations
Photovoltaic power station power prediction method based on NWP irradiance correction and error prediction
CN114091317A
Photovoltaic power interval prediction method considering meteorological correlation matching and trend abrupt change perception
CN117895502A