ABSTRACT Regarding the time‐series scenario generation of regional wind power, conventional methods face challenges in accurately characterizing the variation patterns of the wind power under installed capacity expansion. To address this issue, this paper presents a historical meteorological data‐driven regional wind power scenario generation approach, which can generate time‐series regional wind power scenarios under historical weather conditions and expected wind power capacity expansion. First, wind power aggregation points (WPAPs) in the study region are selected based on the consistency of the wind turbine models and wind speeds among wind farms. Then, the wind speed spatial distribution in the study region is classified into several patterns, and a dual‐layer convolutional neural network (DCNN) is designed to model the dependence of the regional wind power on wind speeds and installed capacities at WPAPs for each pattern. Finally, the expected installed capacities of wind power are aggregated to WPAPs to enable the trained DCNN models to generate regional wind power scenarios driven by the historical weather data. By means of the meteorological reanalysis data, the proposed approach can provide time‐series regional wind power scenarios with heterogeneity and a high degree of credibility for long‐term planning. Case studies in Shandong Province, China, are carried out to verify the effectiveness of the proposed approach.
Qian et al. (Thu,) studied this question.