基于数据关联分析的低压配电网拓扑识别方法

文中介绍了一种基于数据关联分析的低压配电网拓扑识别方法。基于低压配电网停电事件、恢复上电事件及地理位置信息将待识别低压配电网划分为单一配电变压器停电台区、由于10kV配电线路停电引起的多个配变停电台区和未停过电台区，在每类台区内筛选特征电压序列，并利用Tanimoto相似度系数计算各分组内配电变压器、分支箱、表箱、用户智能电表之间相关性和非相关性，从而实现低压配电网拓扑识别；结合同一配电变压器台区内停电与带电状态、停电时长、地理位置、供电半径等台区拓扑校验规则对识别出的拓扑进行校验。通过实际案例证明文章提出的方法能够解决现有基于大数据挖掘方法计算量大、计算结果不准确、无法校验等问题，实现了配电变压器台区拓扑的高效、准确识别，提升了配电网的信息化水平和数据质量。

Topology identification method of low voltage distribution network based on data association analysis

This paper introduces a topology identification method of low-voltage distribution network based on data association analysis. The low-voltage distribution network to be identified is divided into single distribution transformer station area power cut, multiple distribution transformer station areas power cut due to 10kV distribution line blackout and non power cut station areas based on low-voltage distribution network blackout event, restoration power on event and geographic location information. Filter the characteristic voltage sequence in each type of station area, and Tanimoto similarity coefficient is used to calculate the correlation and non correlation between distribution transformer, branch box, meter box and smart meter in each group, so as to achieve the topology identification of the low-voltage distribution network. And then the identified topology can be verified by combining the topology verification rules of the same distribution transformer station area has the same of outage and live state, outage duration, geographical location, power supply radius and so on. Through the actual case, it is proved that the method proposed in this paper can solve the problems of large amount of calculation, inaccuracy of calculation results, and inability to verify based on the existing big data mining methods. It realizes the efficient and accurate identification of distribution transformer substation topology, and improves the information level and data quality of distribution network.