Microgrid Equivalent Modeling Based on Long Short-Term Memory Neural Network

Changchun Cai,Weili Dai,Haolin Liu,Jie Chen,Zhixiang Deng,Yuan Tao

doi:10.1109/access.2020.2966238

Changchun Cai, Weili Dai + Show 4 more

Open Access

https://doi.org/10.1109/access.2020.2966238

Copy DOI

Abstract

Models of electrical equipment components are the basis of the transient stability studies of power system with multi-microgrids. Microgrid is a small local power system contains different electrical components which connected into distribution network through the Point of Common Couple(PCC). In order to simplify the grid-connect model of microgrid in power system stability study, a data-driven equivalent modeling method for microgrid based on Long Short-Term Memory(LSTM) recurrent neural network is proposed in this paper. LSTM recurrent neural network is the state-of-the-art models for a variety machine learning problems, and the dynamic behaviors of microgrid under grid-connect mode are presented by the LSTM recurrent neural network. The training data set should contain the dynamic behaviors of all components, the current and power of PCC are collected as the training data set during the faults for the parameter estimation of LSTM. Based on the measurement data set, a LSTM recurrent neural network structure with four inputs and two outputs is designed. During the training process, the real and imaginary parts of the current at present and previous time are taken as the input of the network, and errors of the output active and reactive power between equivalent model and detailed model of microgrid is taken as the evaluation index of the equivalent model method. An AC microgrid contains different distributed generations and load is built in DIgSILENT, and the accuracy of the proposed method is verified by comparing the equivalent model with the original detailed system.

Highlights

Nowadays, the problems of environmental pollution and greenhouse guide governments to develop renewable energy-based distributed generation system
TEST NETWORK A microgrid including renewable energy distributed generation and distribution network is built in the DIgSILENT to verify the accuracy and validity the proposed equivalent model and the modeling method
In this paper, an equivalent modeling method for microgrid based on LSTM recurrent neural network is proposed

Summary

Introduction

The problems of environmental pollution and greenhouse guide governments to develop renewable energy-based distributed generation system. VOLUME 8, 2020 the continuous increasing of the penetrance of renewable distributed generations(DGs) and the wide use of power electronics facilities, there are new challenges for the operation and control of distribution networks [1]–[4]. High penetrance of microgrid will bring the voltage and frequency problems in distribution network when microgrid are grid-connect operational mode. Components model is the basis of the stability analysis of the distribution network. For the stability studies of distribution network with high penetration of microgrid, the detailed model and dynamic behaviors of microgrid should be concerned as a major component. An accurate dynamic equivalent model of microgrid with simple construction and low computation burden is needed for the stability study of distribution network [7]

Objectives

Results

Conclusion