Day-ahead wind-solar power generation power scene generation method, virtual device and computer readable medium

The invention relates to a day-ahead wind and light generation power scene generation method considering regional resource characteristics. According to the method, resource characteristics of a region and condition dependency of prediction errors are considered, and distribution of the prediction errors under different conditions divided according to prediction data and meteorological factor fluctuation levels is obtained. And scene layering is carried out based on prediction errors under different conditions, more accurate prediction error distribution estimation is obtained, the scene generation model is established under supervision of prediction error distribution under different conditions, and the precision of the scene generation model can be improved. 本发明涉及一种考虑区域资源特性的日前风光发电功率场景生成方法。该方法考虑区域的资源特性及预测误差的条件相依性，得到根据预测数据和气象因子波动水平划分的不同条件下预测误差的分布。并基于不同条件下的预测误差进行场景分层，得到更准确的预测误差分布估计，在不同条件下的预测误差分布的监督下建立场景生成模型，可以提高场景生成模型的精度。