一种日前风光发电功率场景生成方法、虚拟装置及计算机可读介质
By analyzing the statistical characteristics of wind and solar power generation data and the fluctuation level of meteorological factors, a conditional label vector is constructed. A generative adversarial network is used to generate a prediction error sequence, which solves the problem of regional resource characteristics and prediction error influence in the day-ahead wind and solar power generation scenario generation, improves the scenario generation accuracy, and enhances the stability of the power system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA AGRI UNIV
- Filing Date
- 2023-06-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies fail to fully consider the regional resource characteristics and the conditional dependence of prediction errors in the generation of current wind and solar power generation scenarios, resulting in insufficient scenario generation accuracy and difficulty in meeting the stable operation requirements of the power system.
By analyzing the statistical characteristics and similarity of wind and solar power generation data, and combining the level of meteorological factor fluctuations to create a stratified structure, a conditional label vector is constructed. A generative adversarial network is then used to train a generative model to generate a prediction error sequence that meets the conditional characteristics. This sequence is then superimposed on the predicted value to construct a day-ahead wind and solar power generation scenario.
It improves the accuracy and universality of the scene generation model, enabling it to better cope with the uncertainties of new energy sources and enhance the safe and stable operation of the power system.
Smart Images
Figure CN117060374B_ABST