可再生能源发电功率预测方法及装置、系统、存储介质
By acquiring multi-source datasets, screening target meteorological influencing factors, constructing a graph structure, and using graph neural networks for data fusion, the bias problem caused by neglecting factors in existing photovoltaic power generation prediction methods is solved, improving the accuracy and stability of predictions and adapting to different photovoltaic power station layouts and meteorological conditions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- BEIJING PAUWAY ENERGY & TECH CO LTD
- Filing Date
- 2026-05-06
- Publication Date
- 2026-07-17
AI Technical Summary
Existing photovoltaic power generation forecasting methods ignore various factors such as temperature, weather changes, and equipment status, resulting in a large deviation between the forecast results and the actual power generation, which affects the accuracy of photovoltaic power generation forecasting.
By acquiring multi-source datasets, target meteorological influencing factors are screened out, a graph structure is constructed, and graph neural networks are used to adjust temporal and spatial correlations. Data fusion is then performed, and predictions are made in conjunction with different photovoltaic power prediction models.
It significantly improves the accuracy and stability of photovoltaic power generation prediction, enhances the model's adaptability to complex and ever-changing actual operating environments, reduces input noise, and adapts to the layout differences of different photovoltaic power plants and the dynamic changes in meteorological conditions.
Smart Images
Figure CN122136827B_ABST