J Shanghai Jiaotong Univ Sci ›› 2024, Vol. 29 ›› Issue (2): 290-296.doi: 10.1007/s12204-022-2522-6

• Energy and Power Engineering • Previous Articles     Next Articles

Distributed Photovoltaic Real-Time Output Estimation Based on Graph Convolutional Networks


CHEN Liyue1 (陈利跃), HONG Daojian2 (洪道鉴), HE Xing3* (何星), LU Dongqi2 (卢东祁), ZHANG Qian2 (张乾), XIE Nina2 (谢妮娜), XU Yizhou2 (徐一洲), YING Huanghao2 (应煌浩)   

  1. (1. State Grid Zhejiang Electric Power Co., Ltd. Hangzhou 310007, China; 2. State Grid Zhejiang Taizhou Power Supply Company, Taizhou 318000, Zhejiang, China; 3. Department of Automation, School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China)
  2. (1. 国网浙江省电力有限公司,杭州 310007; 2. 国网浙江省电力有限公司台州供电公司,浙江 台州 318000;3. 上海交通大学 自动化系,上海200240)
  • Received:2021-06-16 Accepted:2021-08-10 Online:2024-03-28 Published:2024-03-28

Abstract: The rapid growth of distributed photovoltaic (PV) has remarkable influence for the safe and economicoperation of power systems. In view of the wide geographical distribution and a large number of distributed PV power stations, the current situation is that it is difficult to access the current dispatch data network. According to the temporal and spatial characteristics of distributed PV, a graph convolution algorithm based on adaptive learning of adjacency matrix is proposed to estimate the real-time output of distributed PV in regional power grid. The actual case study shows that the adaptive graph convolution model gives different adjacency matrixes for different PV stations, which makes the corresponding output estimation algorithm have higher accuracy.

Key words: distributed photovoltaic (PV), graph convolution network, power estimation

摘要: 分布式光伏的快速发展,对电力系统的安全经济运行产生了显著影响。由于地理分布广泛,分布式光伏电站数量众多,当前难以接入调度数据网络进行数据采集。根据分布式光伏的时空特性,本文提出了一种基于邻接矩阵自适应学习的图卷积算法,用来估计区域电网中的分布式光伏的实时输出。实际案例研究表明,自适应图卷积模型对不同的光伏电站给出了不同的邻接矩阵,可以获得更高的精度输出估计。

关键词: 分布式光伏,图卷积网络,电力估计

CLC Number: