一种计及空间相关性的光伏电站历史出力数据的修正方法

针对光伏系统渗透率增高对电力系统稳定运行带来的严峻挑战,考虑到光伏功率预测技术精度高度依赖于数据精度的问题,提出一种基于人工神经网络的光伏电站历史出力数据修正方法。利用人工神经网络在建立复杂非线性映射关系的优越性,引入皮尔逊相关系数对数据进行降维处理,选择与目标光伏电站出力相关性高的电站作为基准光伏电站,并结合光伏出力的空间相关性特征与基准光伏电站的出力数据对目标光伏电站失准及缺失数据进行修正,以解决由人为因素或数据采集系统老旧带来的光伏数据失准问题,并通过山东省聊城市的光伏历史出力数据对所提方法进行分析验证。

Correction method for historical output data of photovoltaic power plant considering spatial correlation based on artificial neural network

The increase of photovoltaic(PV)system penetration rate brought great challenges to the stable operation of power system. Considering that the accuracy of photovoltaic power prediction was highly dependent on data accuracy, this paper proposed a correction method for historical output data of photovoltaic power plant by taking the advantages of strong ability of artificial neural network in mapping complex nonlinear relations. Person correlation coefficient was employed to select reference PV plants for dimensionality reduction. The inaccurate and missing data of photovoltaic power station could be identified and corrected by taking the spatial correlation characteristics of PV output into consideration based on the output power of reference PV plants, which could solve the problem of PV data inaccuracy caused by human factors or data acquisition system aging. The proposed method was analyzed and verified by the historical output data of Liaocheng City in Shandong Prvoince.