AUTHOR=Li Chengyu , Yu Jilai , Lv Jiaxin 

TITLE=A Novel Bi-LSTM-Based Method for Thevenin Equivalent Parameter Identification

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.933544

DOI=10.3389/fenrg.2022.933544

ISSN=2296-598X

ABSTRACT=Insufficient power system operation datasets hinder the extensive application of various artificial intelligence algorithms. The solution of the Thevenin equivalent parameters especially depends on the power flow data of the grid. This paper proposes a Kirchhoff circuit laws-based power flow sample generation method, which can overcome the operation state observation difficulty and power flow calculation complexity of the power system. To a large extent, the quality of the sample determines the effect of the machine learning algorithm. This method is different in mechanism from traditional power flow calculation， which is applied to generate the state-based power flow sample datasets by using Kirchhoff circuit laws instead of the iterative calculation of power flow starting from the initial value. In this way, the efficiency of power system sample generation required by machine learning algorithms is enhanced significantly. Besides, This paper finds the power characteristic parameter suitable for Thevenin's equivalent parameter machine learning, that is, the load power differential ratio. Study a clustering method suitable for the Bi-LTSM model for processing power state samples, which can improve learning performance. The case studies demonstrate the sample generation efficiency of this method and verify the learning effect of the Bi-LTSM algorithm.