| 引用本文: | 韩 晓,王 涛,韦晓广,等.考虑阵列间时空相关性的超短期光伏出力预测[J].电力系统保护与控制,2024,52(14):82-94.[点击复制] |
| HAN Xiao,WANG Tao,WEI Xiaoguang,et al.Ultrashort-term photovoltaic output forecasting considering spatiotemporal correlation between arrays[J].Power System Protection and Control,2024,52(14):82-94[点击复制] |
|
| 摘要: |
| 随着我国光伏产业建设步伐的加快，光伏出力预测对于优化电网调度和提高新能源消纳的意义日益凸显。基于光伏站点中不同阵列之间的空间相关性和光伏功率输出的时序特性，提出一种基于图卷积神经网络和长短期记忆网络(graph convolution network and long short-term memory, GCN-LSTM)的超短期光伏出力预测方法。该方法首先以图的形式刻画出光伏站点中不同阵列的连接关系。然后利用图卷积神经网络(graph convolution network, GCN)实现图模型的空间特征提取，并得到包含不同阵列之间空间特征的时序信息。最后将时序数据输入长短期记忆网络(long short-term memory, LSTM)进行光伏出力预测。实验结果表明，基于GCN-LSTM的光伏出力预测方法具有较高的精确性与稳定性，在一定程度上弥补了基于时序信息预测方法的固有缺陷，并且展现出在大规模电站上的良好应用前景。 |
| 关键词: 光伏发电 超短期预测 时空相关性 图卷积神经网络 长短期记忆网络 |
| DOI：10.19783/j.cnki.pspc.231395 |
| 投稿时间：2023-10-23修订日期：2024-02-27 |
| 基金项目:国家重点研发计划项目资助(2021YFB2601500)；成都市科技局揭榜挂帅科技项目资助(2023-JB00-00002-SN) |
|
| Ultrashort-term photovoltaic output forecasting considering spatiotemporal correlation between arrays |
| HAN Xiao1,WANG Tao1,WEI Xiaoguang2,WANG Jun1 |
| (1. School of Electrical Engineering and Electronic Information, Xihua University, Chengdu 610039, China;
2. School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China) |
| Abstract: |
| Photovoltaic (PV) output forecasting is crucial for optimizing power grid dispatching and enhancing new energy consumption, especially with the rapid development of the PV industry in China. To capture the spatial correlation among different arrays in a PV site and the temporal dynamics of PV power outputs, a novel ultra-short-term PV output forecasting method based on a graph convolutional network and long short-term memory (GCN-LSTM) network is proposed. The proposed method first constructs a graph model to represent the connection relationships of different arrays on the PV site. Then the graph convolutional network is used to extract spatial features from the graph model to obtain time series data that incorporate the spatial relationships among different arrays. Finally, time series data is input into the LSTM network to perform PV output prediction. Experiments demonstrate that the GCN-LSTM-based PV output forecasting method achieves high accuracy and stability, which makes up for the inherent limitations of prediction methods based on time series data and shows promising application potential in large-scale power plants. |
| Key words: photovoltaic power generation ultra-short-term forecasting spatio-temporal correlation graph convolution network long short-term memory network |
