Topology Identification of Distribution Networks Using a Split-EM Based Data-Driven Approach

Abstract

To improve the topology observability in power distribution networks (PDNs), a two-stage topology identification framework is proposed to recognize the mixed topologies in a large set of historical data and predict the real-time topology based on the nodal measurements. A split expectation-maximization (split-EM) method is proposed considering the measurement errors to deal with the topology identification problem on the historical batch data, in which the number of topology categories does not need to be given in advance. Based on the topology identification results of historical data, the number of topology categories is reduced. Then, feasible classifiers are trained using machine learning methods to predict the real-time topology efficiently. An error-correcting mechanism is proposed for the real-time identification involving the credibility analysis and the reidentification based on the Bayesian recursion model. Finally, via a practical example, the effectiveness of the proposed models is verified by efficiently identifying the PDN's topologies in both the historical batch data with mixed topologies and real-time measurements. In addition, the partition-based extension application solution of the topology identification models for large-scale PDNs is proposed without extra measurements to relieve the calculation burden and reduce the identification time notably while maintaining the accuracy as the non-partitioned scheme.