基于预估-校正综合BP神经网络的短期光伏功率预测

针对现有光伏功率预测结果精度低、无法反映功率变动范围等问题，提出考虑不确定性的短期光伏功率综合预测方法。建立基于预估-校正综合BP神经网络的光伏功率点预测模型和考虑不确定性的光伏功率区间预测模型。结合某光伏电站历史数据对所提方法的正确性和有效性进行验证，算例分析表明，基于预估-校正综合BP神经网络的光伏功率点预测模型有效提高了光伏功率预测的精准度，考虑不确定性的光伏功率区间预测模型准确反映了光伏功率的变化趋势和范围。

Short-term Photovoltaic Power Forecasting Based on Predict-correct Combination BP Neural Network

Targeting the problems of low prediction precision for photovoltaic power forecasting and the uncertain range of power change， the paper proposes a comprehensive method of short-term photovoltaic power forecasting considering the uncertainty， and establishes the photovoltaic power point prediction model based on a predict-correct combination BP neural network as well as the photovoltaic power interval prediction model considering the uncertainty. The correctness and effectiveness of the proposed method are verified with the historical data from a photovoltaic power station， the example analysis shows that the photovoltaic power point prediction model based on the predict-correct combination BP neural network can effectively improve the precision of the photovoltaic power prediction， and the photovoltaic power interval prediction model considering the uncertainty can accurately determine the changing trend and range of the photovoltaic power.