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

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.

Data-driven modeling of power system dynamics: Challenges, state of the art, and future work

“…Through improvements in model structure and activation functions, methods like RBFNN [138] achieve better fitting results and convergence speeds. Subsequently, widely used methods like RNN [14] , LSTM [140] , and GRU [144] employ time series modeling, enabling better fitting of higher-order dynamics.…”

“…Some classical neural network models: ANN [60,61] , RNN [64] , LSTM [140,141] , GRU [144] , etc. Neural networks combined with fuzzy theory and some new methods: RBFNN [63] , GDFNN [65] , Neural ODE [145] , etc.…”

“…But it is well known that RNN has the problem of vanishing gradient, which means that it only has short-term memory capability. Therefore, Long shortterm memory (LSTM) networks have been promoted in recent years with more complex structures and better performances [140,141] . Ref.…”

Experimental Validation of a Dynamic Equivalent Model for Microgrids

“…Generally, measurement-based methods [21]- [22] are preferred to other approaches since they do not require a detailed a priori knowledge of the real system. In [23]- [25] artificial neural networks (ANNs) are used to identify EDMs for ADNs and microgrids, which can be considered as a special case of ADNs. Prony analysis is applied in [26] and [27].…”