摘要
分布式电源由于其出力存在不确定性的特点对配电网的规划有着明显的影响,为使规划结果更加合理,需对其出力的不确定性进行建模。首先利用改进的条件生成对抗网络模型对风电和光伏出力的不确定性进行建模,在模型中加入月份标签信息以生成具有时序特性的风电和光伏出力场景,并通过K-means聚类方法对生成的大量场景进行聚类。其次,建立了以年综合费用最小为目标的分布式电源优化配置模型,通过二阶锥松弛方法将模型转换为混合整数二阶锥规划问题快速求解。最后,通过IEEE 33节点算例系统验证构建模型的有效性。
Distributed generation has a significant impact on the planning of distribution network due to its characteristics of uncertainty.In order to make the planning results more reasonable,it is necessary to model the uncertainty of its output.Firstly,the improved conditional generative adversarial networks model is used to model the uncertainty of wind power and photovoltaic output,the month label information is added to the model to generate wind power and photovoltaic output scenarios with timing characteristics,and a large number of scenes are clustered by K-means clustering method.Secondly,a distributed generation optimal allocation model aiming at minimizing the annual comprehensive cost is established,and the model is transformed into a mixed integer second-order cone programming problem by the second-order cone relaxation method.Finally,the effectiveness of the model is verified by an IEEE33-bus example system.
作者
胡攀
邓坤
HU Pan;DENG Kun(College of Electrical Engineering,Guizhou University,Guiyang 550025,China)
出处
《智能计算机与应用》
2022年第5期81-88,共8页
Intelligent Computer and Applications
关键词
不确定性
条件生成对抗网络
K-MEANS聚类
优化配置
二阶锥规划
uncertainty
conditional generative adversarial networks
K-means
optimal allocation
second-order cone programming
作者简介
胡攀(1997-),男,硕士研究生,主要研究方向:电力系统规划;邓坤(1996-),男,硕士研究生,主要研究方向:储能配置。
