配用电系统高级量测体系与数据应用方法研究
发布时间：2018-11-18 18:32
【摘要】：在电力领域“大数据时代”到来的背景下,本文针对配用电系统,按照数据采集、数据清洗、数据应用三层逻辑结构,建立了一套应用理论和工程实践方法。数据采集指的是基于IPv6的高级量测体系架构和组网技术研究。高级量测体系是一套完整的体系,可实现对电力消费者的能源消费的进行量测、读取、存储和分析功能,包括配套的的传感、通信和软件系统。IPv6技术是互联网的发展方向,提出了将IPv6技术与高级量测体相结合的组网方案。针对基于无线传感网络技术的智能电表,为了更好地将IPv6技术进行部署,对两者的互联方式进行了研究,提出了将整个智能电表网络虚拟为一个IPv6网络接入点的设计思想,并给出了通信组网的具体实现方法。使得6Lo WPAN无线智能电表网络能够直接接入IPv6有线网络,实现两个网络间任意点与点的互联,将配用电系统“最后一公里”互联网化,相关组网方案已经用于试点项目,可为后续的大数据应用提供了技术支持。数据清洗指的是针对配电变压器的数据清洗方法研究。配用电变压器作为配用电系统的关键环节,由于分布面广、网络结构复杂、运行环境恶劣等客观条件的制约,其数据在实际运行中常存在大量异常和缺失情况。为了解决上述问题,以现实中的配电变压器数据为研究样本,首先分析了配电变压器数据异常和数据丢失两类情况的产生原因,之后采用小样本数据进行算法研究,针对配电变压器数据异常问题提出基于Kernel Smoothing技术的异常数据识别方法,针对配电变压器数据丢失问题提出了基于Pearson相关系数与回归模型相结合的缺失数据恢复方法。为验证所提方法能够满足TB级数据的运算效率,采用6台服务器搭建Spark并行计算结构,对大样本的配电变压器数据进行了异常数据的识别和缺失数据的恢复,相关结果证明了所提方法的实际价值。该数据清洗方法不光适用于配电变压器数据,可应用于解决配用电系统的其他数据问题。数据清洗是数据应用的第一步,为开发更多数据应用方法开辟了道路。数据应用指的在前面数据采集和数据清洗的基础上,对配用电系统数据应用方法进行研究。高级量测系统采集的数据是配用电系统的基础数据,具有多源异构、规模巨大的特点,呈现出大数据的特征。利用智能电表数据,进行数据挖掘,结合电气专业基本知识,采用相关分析等统计学方法,可以为电力行业解决实际工程问题,为各种利益相关方创造效益。提出了基于智能电表数据的用户与台区关系拓扑校验方法研究,可为配电网运行维护节省大量的投入成本,实现资产管理智能化,文中以现实数据作为算例,证明了方法的实际价值。
[Abstract]:Under the background of "big data era" in electric power field, this paper establishes a set of application theory and engineering practice method according to the three-layer logical structure of data acquisition, data cleaning and data application. Data acquisition refers to the research of advanced measurement architecture and networking technology based on IPv6. Advanced measurement system is a complete system, which can measure, read, store and analyze the energy consumption of electric power consumers, including the matching sensing, communication and software systems. IPv6 technology is the development direction of the Internet. A scheme of combining IPv6 technology with advanced measurement is proposed. Aiming at the intelligent meter based on wireless sensor network technology, in order to better deploy IPv6 technology, the interconnection mode between them is studied, and the design idea of virtual IPv6 network access point is put forward. The realization method of communication network is also given. The 6Lo WPAN wireless intelligent meter network can be directly connected to the IPv6 wired network, to realize the interconnection of any point and point between the two networks, to make the distribution system "the last kilometer" of the Internet, and the related networking scheme has been used in the pilot project. Can provide technical support for subsequent big data application. Data cleaning refers to the study of data cleaning method for distribution transformers. As the key link of power distribution system, due to the restriction of objective conditions, such as wide distribution, complex network structure and poor operating environment, there are often a large number of anomalies and deficiencies in the actual operation of the distribution transformer. In order to solve the above problem, taking the distribution transformer data in reality as the research sample, this paper first analyzes the causes of the abnormal data and the data loss of the distribution transformer, and then uses the small sample data to carry on the algorithm research. In order to solve the problem of abnormal data of distribution transformer, a method of identifying abnormal data based on Kernel Smoothing technology is put forward, and a method of recovering missing data based on Pearson correlation coefficient and regression model is proposed to solve the problem of data loss of distribution transformer. In order to verify that the proposed method can meet the operational efficiency of TB level data, six servers are used to construct the Spark parallel computing structure, and the abnormal data and the missing data are identified and recovered from the large sample distribution transformer data. The results show that the proposed method is of practical value. The data cleaning method is not only suitable for distribution transformer data, but also can be used to solve other data problems of distribution system. Data cleaning is the first step of data application, which opens the way for developing more data application methods. Data application refers to the data application method of distribution system based on data acquisition and data cleaning. The data collected by the advanced measurement system is the basic data of the power distribution system. It has the characteristics of multi-source heterogeneity and huge scale, showing the character of big data. Using intelligent meter data, data mining, combined with electrical professional basic knowledge, using statistical methods such as correlation analysis, can solve practical engineering problems for power industry, and create benefits for various stakeholders. In this paper, the topology checking method of user-to-station relationship based on intelligent ammeter data is proposed, which can save a lot of input cost for distribution network operation and maintenance, and realize intelligent asset management. The actual data is taken as an example in this paper. The practical value of the method is proved.
【学位授予单位】：华北电力大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TM76
[Abstract]:Under the background of "big data era" in electric power field, this paper establishes a set of application theory and engineering practice method according to the three-layer logical structure of data acquisition, data cleaning and data application. Data acquisition refers to the research of advanced measurement architecture and networking technology based on IPv6. Advanced measurement system is a complete system, which can measure, read, store and analyze the energy consumption of electric power consumers, including the matching sensing, communication and software systems. IPv6 technology is the development direction of the Internet. A scheme of combining IPv6 technology with advanced measurement is proposed. Aiming at the intelligent meter based on wireless sensor network technology, in order to better deploy IPv6 technology, the interconnection mode between them is studied, and the design idea of virtual IPv6 network access point is put forward. The realization method of communication network is also given. The 6Lo WPAN wireless intelligent meter network can be directly connected to the IPv6 wired network, to realize the interconnection of any point and point between the two networks, to make the distribution system "the last kilometer" of the Internet, and the related networking scheme has been used in the pilot project. Can provide technical support for subsequent big data application. Data cleaning refers to the study of data cleaning method for distribution transformers. As the key link of power distribution system, due to the restriction of objective conditions, such as wide distribution, complex network structure and poor operating environment, there are often a large number of anomalies and deficiencies in the actual operation of the distribution transformer. In order to solve the above problem, taking the distribution transformer data in reality as the research sample, this paper first analyzes the causes of the abnormal data and the data loss of the distribution transformer, and then uses the small sample data to carry on the algorithm research. In order to solve the problem of abnormal data of distribution transformer, a method of identifying abnormal data based on Kernel Smoothing technology is put forward, and a method of recovering missing data based on Pearson correlation coefficient and regression model is proposed to solve the problem of data loss of distribution transformer. In order to verify that the proposed method can meet the operational efficiency of TB level data, six servers are used to construct the Spark parallel computing structure, and the abnormal data and the missing data are identified and recovered from the large sample distribution transformer data. The results show that the proposed method is of practical value. The data cleaning method is not only suitable for distribution transformer data, but also can be used to solve other data problems of distribution system. Data cleaning is the first step of data application, which opens the way for developing more data application methods. Data application refers to the data application method of distribution system based on data acquisition and data cleaning. The data collected by the advanced measurement system is the basic data of the power distribution system. It has the characteristics of multi-source heterogeneity and huge scale, showing the character of big data. Using intelligent meter data, data mining, combined with electrical professional basic knowledge, using statistical methods such as correlation analysis, can solve practical engineering problems for power industry, and create benefits for various stakeholders. In this paper, the topology checking method of user-to-station relationship based on intelligent ammeter data is proposed, which can save a lot of input cost for distribution network operation and maintenance, and realize intelligent asset management. The actual data is taken as an example in this paper. The practical value of the method is proved.
【学位授予单位】：华北电力大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TM76
【参考文献】
相关期刊论文 前10条
1 刁赢龙;盛万兴;刘科研;何开元;孟晓丽;;大规模配电网负荷数据在线清洗与修复方法研究[J];电网技术;2015年11期
2 栾文鹏;王兵;周宁;郭志民;;基于量测数据的低压配电网精确建模[J];电网技术;2015年11期
3 赵磊;栾文鹏;王倩;;应用AMI数据的低压配电网精确线损分析[J];电网技术;2015年11期
4 王亚东;高岩;金锋;;智能电表数据分析及应用综述研究[J];信息技术;2015年02期
5 张东霞;苗新;刘丽平;张焰;刘科研;;智能电网大数据技术发展研究[J];中国电机工程学报;2015年01期
6 严英杰;盛戈v，
本文编号：2340809
本文链接：https://www.wllwen.com/kejilunwen/dianlidianqilunwen/2340809.html
