变电站为中心配电网电压等高线时序态势图片的聚类分析
发布时间：2018-09-07 21:03
【摘要】：基于电气接线图并按特定图形设计的时序态势图,其图形特征是网络结构、运行方式、接入源荷及各类电气元件行为、量测数据等动态潮流的一种高维融合映射。通过基于刻画态势图片的关键但数量有限的图形特征量的聚类分析,从中获取态势图中隐藏的规律和有价值的知识。文中提出变电站为中心的配电网电压等高线时序态势图片的特征向量及其计算算法;探索了基于图片特征向量的态势时序图片聚类分析方法,提出了聚类中心图片(典型图片)的图片相似度、时间离散度及其计算算法。以典型日96幅电压态势时序图为案例,介绍了所提方法的效果以及分析结果,并进行了近两个月的长时序图片聚类的初步应用分析。
[Abstract]:Based on the electrical wiring diagram and designed according to a specific graph, the graph features a high-dimensional fusion mapping of the dynamic power flow, such as network structure, operation mode, access source load and the behavior of various electrical components, measurement data, etc. Based on the clustering analysis of the key but limited number of graphic feature quantities which depict the situation picture, the hidden laws and valuable knowledge in the situation map are obtained. In this paper, the feature vector and its calculation algorithm of voltage contour sequential situation picture of distribution network with substation as the center are proposed, and the clustering analysis method of situation time series picture based on image feature vector is explored. In this paper, the image similarity, time dispersion and algorithm of clustering center picture (typical picture) are proposed. Taking 96 typical daily voltage sequence diagrams as an example, the effect of the proposed method and the analysis results are introduced, and the preliminary application of the long sequence picture clustering in the last two months is analyzed.
【作者单位】： 杭州电子科技大学自动化学院;浙江华云信息科技有限公司;国网绍兴供电公司;
本文编号：2229410
[Abstract]:Based on the electrical wiring diagram and designed according to a specific graph, the graph features a high-dimensional fusion mapping of the dynamic power flow, such as network structure, operation mode, access source load and the behavior of various electrical components, measurement data, etc. Based on the clustering analysis of the key but limited number of graphic feature quantities which depict the situation picture, the hidden laws and valuable knowledge in the situation map are obtained. In this paper, the feature vector and its calculation algorithm of voltage contour sequential situation picture of distribution network with substation as the center are proposed, and the clustering analysis method of situation time series picture based on image feature vector is explored. In this paper, the image similarity, time dispersion and algorithm of clustering center picture (typical picture) are proposed. Taking 96 typical daily voltage sequence diagrams as an example, the effect of the proposed method and the analysis results are introduced, and the preliminary application of the long sequence picture clustering in the last two months is analyzed.
【作者单位】： 杭州电子科技大学自动化学院;浙江华云信息科技有限公司;国网绍兴供电公司;
【相似文献】
相关会议论文 前1条
1 李津津;;配电网无功补偿设备对电压和线损的影响分析[A];2012年云南电力技术论坛论文集（文摘部分）[C];2012年
相关硕士学位论文 前10条
1 刘成峰;阳春配电网电压控制策略与低压电压补偿装置应用研究[D];华南理工大学;2015年
2 高长青;计及DER无功调节能力的主动配电网电压优化控制[D];华北电力大学(北京);2016年
3 张晓敏;配电网电压无功综合治理方法与应用[D];湖南大学;2016年
4 刘倩;并网分布式光伏对配电网电压影响研究[D];东南大学;2016年
5 肖鸿威;工矿企业配电网电压事件监测系统设计[D];西南交通大学;2009年
6 贾德香;基于改进遗传算法的配电网电压无功多目标优化[D];东南大学;2004年
7 赵海;配电网电压稳定性及控制方法的研究[D];沈阳工业大学;2011年
8 路宁;配电网电压无功三级联调控制研究[D];西安科技大学;2012年
9 薛佳佳;基于动态规划算法的有源配电网电压控制研究[D];华北电力大学;2014年
10 陈成;光伏并网对配电网电压分布的影响分析[D];华北电力大学;2011年
，本文编号：2229410
本文链接：https://www.wllwen.com/kejilunwen/zidonghuakongzhilunwen/2229410.html
