考虑分布式新能源出力不确定性的虚拟电厂概率可行域构建方法  

Construction Method for Probability-based Feasible Region of Virtual Power Plant Considering Uncertainty of Distributed Renewable Energy Output

作　　者：焦治杰 王小君[1] 刘曌 和敬涵[1] 司方远 管金昱 JIAO Zhijie;WANG Xiaojun;LIU Zhao;HE Jinghan;SI Fangyuan;GUAN Jinyu(School of Electrical Engineering,Beijing Jiaotong University,Beijing 100044,China;NARI Technology Co.,Ltd.,Nanjing 211106,China)

机构地区：[1]北京交通大学电气工程学院,北京市100044 [2]国电南瑞科技股份有限公司,江苏省南京市211106

出　　处：《电力系统自动化》2024年第18期129-138,共10页Automation of Electric Power Systems

基　　金：国家重点研发计划资助项目(2022YFB2403400)。

摘　　要：分布式新能源出力的不确定性严重影响虚拟电厂聚合可行域的准确刻画,需精准计算虚拟电厂的可调能力以提升电力系统的平衡能力。文中提出了面向虚拟电厂的分布式新能源出力不确定性概率模型及基于多概率变量的可信概率可行域构建方法。首先,基于集成学习与共形分位数回归方法,提出了能够描述新能源出力异方差时间序列的不确定性概率模型。其次,研究了闵可夫斯基和方法与优化方法求解可行域的特点,分析了新能源出力约束和网络约束对虚拟电厂可行域的影响,进一步提出了基于分布式新能源出力概率区间的虚拟电厂概率可行域构建方法。最后,考虑风光耦合特性,优化了虚拟电厂概率可行域构建方法,通过协调各分布式新能源出力概率区间置信度,得出虚拟电厂概率可行域整体的置信水平。算例验证结果表明,所提方法能够准确刻画虚拟电厂的可调能力。The uncertainty of distributed renewable energy output significantly affects the accurate characterization of the feasible region for virtual power plant aggregation.It is necessary to accurately calculate the adjustable capacity of virtual power plants to enhance the balancing capability of the power system.This paper proposes a probability model for the uncertainty of distributed renewable energy output in virtual power plants and a construction method of the credible probability-based feasible region based on multiple probability variables.Firstly,based on the ensemble learning and conformal quantile regression methods,an uncertainty probability model is proposed to describe the heteroscedastic time series of renewable energy output.Secondly,the characteristics of Minkowski sum and optimization methods for solving feasible region are studied,and the influences of renewable energy output constraints and network constraints on the feasible region of the virtual power plant are analyzed.Then,this paper proposes a construction method for the probability-based feasible region of the virtual power plant based on output probability intervals of distributed renewable energy.Finally,considering the coupling characteristics of wind and photovoltaic power,the construction method for the probability-based feasible region of the virtual power plant is optimized.By coordinating the confidence coefficients of the output probability intervals of each distributed renewable energy,an overall confidence level of the probability-based feasible region of the virtual power plant is obtained.The case verification results show that the proposed method can accurately characterize the adjustable capacity of virtual power plants.

关 键 词：虚拟电厂 灵活性资源 可行域 不确定性 集成学习 分位数回归 

分 类 号：TM73[电气工程—电力系统及自动化]