摘要
本文针对含大规模并网光伏电站配电网中电能损耗的问题,提出一种基于决策树算法的分布式光伏系统的方法。首先,分析了大规模光伏系统入网对配电网产生的影响;然后介绍了用于优化光伏系统配置的决策树算法,建立了基于决策树算法的电能损失估计模型;其次,采用基于ID3和J48的决策树算法,对于不同规模的光伏系统,确定其满足配电网的最小功率损失的最佳位置和规模,使用配电网历史真实数据进行模拟,并通过WEKA工具箱进行了可视化。最后,总结了决策树算法在配电系统中的应用效果。本文将决策树算法与GA MATLAB工具箱和DIGSILENT/Power Factory软件相比,证明决策树算法结果更精确且计算快速。本文所提方法的能够减少配电网的电能损失并为入网光伏系统的位置和容量进行优化。
In this paper,a method based on decision tree algorithm for distributed PV systems is proposed for the problem of power loss in the distribution network containing large-scale grid-connected PV power plants.Firstly,the impact of large-scale PV systems on the distribution network generated by grid connection is analyzed.Then the decision tree algorithm used to optimize the configuration of PV systems is introduced,and the power loss estimation model based on the decision tree algorithm is established;secondly,the decision tree algorithm based on ID3 and J48 is used to determine the optimal location and size of PV systems of different sizes to meet the minimum power loss of the distribution network,using the distribution network Historical real data were simulated and visualized by WEKA toolbox.Finally,the effectiveness of the decision tree algorithm in the distribution system is summarized.In this paper,the decision tree algorithm is compared with GA MATLAB toolbox and DIGSILENT/Power Factory software,and it is demonstrated that the decision tree algorithm results are more accurate and fast to compute.The proposed method is able to reduce the power loss in the distribution network and to optimize the location and capacity of the incoming PV system.
作者
丁亮
梁骏
李仁杰
赵平珂
DING Liang;LIANG Jun;LI Renjie;ZHAO Pingke(State Grid Hefei Power Supply Company,Hefei 230000,China;Zhongneng Bowang(Beijing)Technology Co.,Ltd.,102400)
出处
《自动化与仪器仪表》
2025年第7期286-290,共5页
Automation & Instrumentation
基金
国网合肥供电公司科技项目(SGAHHF00JY WT2201740)。
关键词
决策树算法
光伏系统
配电网
优化配置
decision tree algorithm
photovoltaic system
distribution network
optimal allocation
