Smart distribution network operating condition recognition based on big data analysis

Abstract

In order to guarantee the power quality and the highly efficient operation of the power network, a reliable operating condition recognition system of distribution networks is necessary. To solve the problem of multi-condition recognition, an operating condition recognition system based on the workflow of decision-making tree is proposed. Big data of waveforms acquired by an online recording system is transformed into characteristics through time-domain, frequency-domain and wavelet transformation, and ANN(Artificial Neural Networks) models is automatically built with the training of those characteristics of waveform data. As shown by the experimental results, this recognition system can accurately recognize operating conditions and improve the automatic operating capacity of distribution networks.