摘要
针对传统的线损理论计算方法已不适用于含分布式电源的低压台区线损估算的问题,提出一种基于改进布谷鸟搜索K均值(ICS-K-means)聚类算法和小波神经网络(WNN)的有源台区线损估算方法。首先,基于最大互信息系数筛选线损影响因子,建立有源台区线损指标体系;然后,提出改进布谷鸟搜索聚类算法对样本数据集进行聚类,减少对初始聚类中心的依赖;最后,采用小波神经网络对每类聚类数据集进行训练及测试。算例分析验证了所提方法的准确性和有效性。
The traditional theoretical calculation method of line loss is not applicable for the low-voltage transformer district with distributed generations(DGs).A novel method of line loss rate calculation for transformer district with DGs is presented,which is combined with the improved Cuckoo Search K-means clustering algorithm and Wavelet Neural Network.Firstly,the influence factors of line loss are screened based on the maximum information coefficient,and the line loss index system is established.Secondly,an improved Cuckoo Search clustering algorithm is proposed to cluster the sample data set to reduce the dependence on the initial clustering center.Finally,the wavelet neural network is used to train and model each cluster data set to achieve fine line loss calculation.The simulation results show that the proposed method is accurate and effective.
作者
伍栋文
于艾清
俞林刚
朱亮
林顺富
WU Dongwen;YU Aiqing;YU Lingang;ZHU Liang;LIN Shunfu(State Grid Jiangxi Electric Power Research Institute,Nanchang 330096,China;College of Power Engineering,Shanghai University of Electric Power,Shanghai 200090,China)
出处
《智慧电力》
北大核心
2022年第4期8-14,共7页
Smart Power
基金
国家自然科学基金资助项目(51977127)
国家电网公司科技项目(5600-201919168A-0-0-00)。
关键词
线损
有源台区
最大互信息系数
布谷鸟搜索聚类算法
小波神经网络
line loss
transformer district with DGs
maximum information coefficient
Cuckoo Search clustering algorithm
wavelet neural network