• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

电力建设 ›› 2020, Vol. 41 ›› Issue (3): 47-53.doi: 10.3969/j.issn.1000-7229.2020.03.006

• 主动配电系统源-网-荷-储交互运行 • 上一篇    下一篇

基于空间相关性的分布式光伏出力预测

张家安1, 王琨玥1,陈建2,郭凌旭2,黄潇潇2,范瑞卿2,李志军1   

  1. 1.河北工业大学人工智能与数据科学学院, 天津市300130;2.国网天津市电力公司,天津市300010
  • 出版日期:2020-03-01
  • 作者简介:张家安(1975),男,通信作者,博士,讲师,主要研究方向为新能源发电系统及其智能化、电力系统建模与仿真; 王琨玥(1996),男,硕士研究生,主要研究方向为新能源容量规划; 陈建(1981),男,硕士,高级工程师,主要研究方向为电力系统自动化; 郭凌旭(1974),男,硕士,高级工程师,主要研究方向为电力系统自动化; 黄潇潇(1990),女,硕士,工程师,主要研究方向为配电网规划与运行; 范瑞卿(1984),男,硕士,工程师,主要研究方向为配电网规划与运行; 李志军(1964),男,博士,教授,主要研究方向为新能源发电系统及其智能化。

Research on Prediction of Distributed Photovoltaic Output Considering Spatial Relevance

ZHANG Jiaan1, WANG Kunyue1, CHEN Jian2, GUO Lingxu2, HUANG Xiaoxiao 2, FAN Ruiqing2, LI Zhijun1   

  1. 1. School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China; 2.State Grid Tianjin Electric Power Company, Tianjin 300010, China
  • Online:2020-03-01

摘要: 随着分布式光伏在配电网的渗透率不断上升,其出力波动将成为调度运行中不可忽略的一项不确定因素。基于同一地区光伏出力变化的相关性,提出一种基于空间相关性的分布式光伏出力预测方法。先对同一地区集中式、分布式光伏出力历史数据做无遮归一化,以无遮系数表征光伏出力不确定性;再由K-means聚类方法对天气情况分类,建立基于Copula函数的各类天气工况下光伏出力的相关性模型;最后根据集中式光伏出力信息实现分布式光伏出力预测。以我国北部某城市光伏电站数据为算例,验证了该方法的有效性。

关键词: 分布式光伏, 出力预测, 空间相关性, Copula

Abstract: With the increasing proportion of distributed photovoltaic (DPV) power in distribution network, the fluctuation of its power output will become a non-negligible uncertain factor in power grid dispatch and operation. On the basis of the correlation of photovoltaic power generation in one region, a prediction method for distributed photovoltaic output is proposed on the basis of spatial correlation. Firstly, the historical data of centralized and distributed photovoltaic output in the same region are normalized to uncovered coefficient which represents the randomness of photovoltaic output. Then, the weather conditions are classified by K-means clustering. According to Copula theory, the correlation model of photovoltaic output under various weather conditions is established. Finally, the distributed photovoltaic output is predicted according to the information of centralized photovoltaic output. The validity of the proposed method is verified by using an example of a photovoltaic power station in a city of northern China.

Key words: distributed photovoltaic, output prediction, spatial relevance, Copula

中图分类号: