赵庆明

• 1:贵州电网有限责任公司电网规划研究中心

摘要(Abstract)：

针对低压配网接线方式复杂和线损率难以准确计算的问题,本文提出一种基于近邻传播聚类算法和随机森林回归模型的台区线损率计算方法。基于线路损耗模型提出了台区线损率预测计算的电气特征指标,并利用主成分分析方法提取适用于聚类分析的主特征参数,然后采用近邻传播聚类算法对数据进行聚类分析。在此基础上,采用随机森林回归算法对每类聚类数据进行样本的训练学习,并利用包外数据进行预测。以某地区614个台区样本进行仿真计算,仿真结果验证了本文所提算法的有效性和正确性,并且计算精度要优于多元线性回归算法。

关键词(KeyWords)： 线损率;低压台区;电气特征指标;近邻传播算法;随机森林回归

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 赵庆明

DOI: 10.19635/j.cnki.csu-epsa.000492

参考文献(References)：

• [1]李滨，罗发，黄柳军，等（Li Bin,Luo Fa,Huang Liujun,et al）.地市级电网多维度线损管理对标评价体系构建（Construction of multi-dimensional benchmarking evaluation system for line loss management of the power grid of city-level)[J].电力系统及其自动化学报（Proceedings of the CSU-EPSA),2018,30(6):23-30.
• [2]刘庭磊，王韶，张知，等（Liu Tinglei,Wang Shao,Zhang Zhi,et al）.采用负荷电量计算低压配电台区理论线损的牛拉法（Newton-Raphson method for theoretical line loss calculation of low-voltage distribution transformer district by using he load electrical energy)[J].电力系统保护与控制（Power System Protection and Control),2015,43(19):143-148.
• [3]李亚，刘丽平，李柏青，等（Li Ya,Liu Liping,Li Baiqing,et al）.基于改进K-Means聚类和BP神经网络的台区线损率计算方法（A method for calculating the line loss rate of stations based on improved K-Means clustering and BP neural network)[J].中国电机工程学报（Proceedings of the CSEE),2016,36(17):4543-4552.
• [4]姜惠兰，安敏，刘晓津，等（Jiang Huilan,An Min,Liu Xiaojin,et al）.基于动态聚类算法径向基函数网络的配电网线损计算（The calculation of energy losses in distribution systems based on RBF network with dynamic clustering algorithm)[J].中国电机工程学报（Proceedings of the CSEE),2005,25(10):35-39.
• [5]邹云峰，梅飞，李悦，等（Zou Yunfeng,Mei fei,Li Yue,et al）.基于数据挖掘技术的台区合理线损预测模型研究（Prediction model research of reasonable line loss for transformer district based on data mining technology)[J].电力需求侧管理（Power Demand Side Management),2015,17(4):25-29.
• [6]张裕，赵庆明，李庆生，等.利用K-means聚类算法对台区线损率预测计算方法：中国，2018115008019[P].
• [7]周志华.机器学习[M].北京：清华大学出版社，2016.
• [8]肖宇，于剑（Xiao Yu,Yu Jian）.基于近邻传播算法的半监督聚类（Semi-supervised clustering based on affinity propagation algorithm)[J].软件学报（Journal of Software),2008,19(11):2803-2813.
• [9]王开军，张军英，李丹，等（Wang Kaijun,Zhang Junying,Li Dan,et al）.自适应仿射传播聚类（Adaptive propagation clustering)[J].自动化学报（Acta Automatic Sinica),2007,33(12):1242-1246.
• [10]邢艳，周勇（Xing Yan,Zhou Yong）.基于互近邻一致性的近邻传播聚类算法（Affinity propagation based on K-mutual nearest neighbor consistency)[J].计算机应用研究（Application Research of Computers),2012,29(7):2524-2526.
• [11]Frey B J,Dueck D.Clustering by passing messages between data points[J].Science,2007,315(5814):972-976.
• [12]Breiman L.Random forests[J].Machine Learning,2001,45(1):5-32.
• [13]吴潇雨，和敬涵，张沛，等（Wu Xiaoyu,He Jinghan,Zhang Pei,et al）.基于灰色投影改进随机森林算法的短期负荷预测（Power system short-term load forecasting based on improved random forest with grey relation projection)[J].电力系统自动化（Automation of Electric Power Systems),2015,39(12):50-55.
• [14]胡青，孙才新，杜林，等（Hu Qing,Sun Caixin,Du Lin,et al）.核主成分分析与随机森林相结合的变压器故障诊断方法（Transformer fault diagnosis method using random forests and kernel principle component analysis)[J].高电压技术（High Voltage Engineering),2010,36(7):1725-1729.
• [15]王守相，周凯，苏运（Wang Shouxiang,Zhou Kai,Su Yun）.基于随机森林算法的台区合理线损率的估计方法（Line loss rate estimation method of transformer district based on random forest algorithm)[J].电力自动化设备（Electric Power Automation Equipment),2017,37(11):39-45.