摘要
针对当前电力系统配电网结算管理过程中的结算工程量与实际工程量不遵从问题,提出了一种基于改进随机森林算法的低压配电网工程信息识别技术。该技术通过分析配电网结算过程中工程信息的特点,采用核主成分分析算法提取配电网工程信息的数据特征,从而构建工程信息数据的特征向量。同时将随机森林模型作为基础分类模型并输入特征向量,根据分类性能对随机森林中的决策树进行精确加权,并针对参数选取问题引入粒子群算法优化随机森林的参数,进而输出分类识别结果。实验结果表明,所提出的改进随机森林算法能够有效识别异常工程信息,且与其他算法相比其具有更为优异的识别准确率及识别效率。
Aiming at the non⁃compliance between the settlement quantities and the actual quantities in the settlement management of distribution network in power system,a low voltage distribution network engineering information identification technology based on improved Random Forest(RF)algorithm is proposed.By analyzing the characteristics of engineering information in the process of distribution network settlement,the kernel principal component analysis algorithm is used to extract the characteristics of distribution network engineering information data,so as to construct the feature vector of engineering information data.The random forest model is used as the basic classification model and input the feature vector,and the decision tree in random forest is accurately weighted according to the classif⁃ication performance.Aiming at the problem of parameter selection,particle swarm optimization algorithm is introduced to optimize the parameters of random forest,and then the classification and recognition results are output.The experimental results show that the improved random forest algorithm proposed in this paper can effectively identify abnormal engineering information,and has better recognition accuracy and efficiency than other algorithms.
作者
刘士李
周远科
施晓敏
高象
LIU Shili;ZHOU Yuanke;SHI Xiaomin;GAO Xiang(Economic and Technological Research Institute,State Grid Anhui Electric Power Co.,Ltd.,Hefei 230601,China;State Grid Anhui Electric Power Co.,Ltd.,Hefei 230061,China)
出处
《电子设计工程》
2023年第20期177-181,共5页
Electronic Design Engineering
基金
国网安徽省电力有限公司咨询项目(B11209210006)。
关键词
随机森林
工程信息
核主成分分析
精确加权
分类识别
低压配电网
Random Forest
engineering information
kernal principal component analysis
accurately we⁃ighted
classification and identification
low voltage distribution network
作者简介
刘士李(1982-),男,安徽霍邱人,硕士,高级经济师。研究方向:电网工程技术经济。
