Since the high penetration of distributed energy sources complicates the dynamics of electrical power systems,accurate dynamic models are indispensable for study on the transient behavior of the microgrid(MG).In some ...Since the high penetration of distributed energy sources complicates the dynamics of electrical power systems,accurate dynamic models are indispensable for study on the transient behavior of the microgrid(MG).In some practices,the lack of full detailed information results in failure of dif-ferential equation based dynamic modeling,which leads to a demand for a black-box MG modeling method.It is a critical challenge to maintain the effectiveness of the black-box model under a wide operating range and various fault conditions.In this paper,inspired by the mathematical equivalence between the recurrent neural network(RNN)and differential-algebraic equations(DAEs),a dynamic equivalent modeling method,using long short-term memory(LSTM),is presented to tackle this challenge.At first,the modeling equivalence and advantages of our basic idea are explained.Then,modeling procedures,including data preparation and design guidelines,are presented.Finally,the proposed method is applied to a multi-microgrid testing system for performance evaluation.The results,under various scenarios,reveal that the proposed modeling method has an adequate capability for representing the dynamic behaviors of a black-box MG under grid fault and operating point changing conditions.Index Terms-Deep learning,dynamic behavior,dynamic equivalent model,microgrid,neural network.展开更多
The emerging novel energy infrastructures,such as energy communities,smart building-based microgrids,electric vehicles enabled mobile energy storage units raise the requirements for a more interconnective and interope...The emerging novel energy infrastructures,such as energy communities,smart building-based microgrids,electric vehicles enabled mobile energy storage units raise the requirements for a more interconnective and interoperable energy system.It leads to a transition from simple and isolated microgrids to relatively large-scale and complex interconnected microgrid systems named multi-microgrid clusters.In order to efficiently,optimally,and flexibly control multi-microgrid clusters,cross-disciplinary technologies such as power electronics,control theory,optimization algorithms,information and communication technologies,cyber-physical,and big-data analysis are needed.This paper introduces an overview of the relevant aspects for multi-microgrids,including the out-standing features,architectures,typical applications,existing control mechanisms,as well as the challenges.展开更多
基金supported in part by the Science Search Foundation of Liaoning Educational Department(No.LQGD2020002).
文摘Since the high penetration of distributed energy sources complicates the dynamics of electrical power systems,accurate dynamic models are indispensable for study on the transient behavior of the microgrid(MG).In some practices,the lack of full detailed information results in failure of dif-ferential equation based dynamic modeling,which leads to a demand for a black-box MG modeling method.It is a critical challenge to maintain the effectiveness of the black-box model under a wide operating range and various fault conditions.In this paper,inspired by the mathematical equivalence between the recurrent neural network(RNN)and differential-algebraic equations(DAEs),a dynamic equivalent modeling method,using long short-term memory(LSTM),is presented to tackle this challenge.At first,the modeling equivalence and advantages of our basic idea are explained.Then,modeling procedures,including data preparation and design guidelines,are presented.Finally,the proposed method is applied to a multi-microgrid testing system for performance evaluation.The results,under various scenarios,reveal that the proposed modeling method has an adequate capability for representing the dynamic behaviors of a black-box MG under grid fault and operating point changing conditions.Index Terms-Deep learning,dynamic behavior,dynamic equivalent model,microgrid,neural network.
基金supported by VILLUM FONDEN under the VILLUM Investigator Grant(No.25920):Center for Research on Microgrids(CROM)www.crom.et.aau.dk。
文摘The emerging novel energy infrastructures,such as energy communities,smart building-based microgrids,electric vehicles enabled mobile energy storage units raise the requirements for a more interconnective and interoperable energy system.It leads to a transition from simple and isolated microgrids to relatively large-scale and complex interconnected microgrid systems named multi-microgrid clusters.In order to efficiently,optimally,and flexibly control multi-microgrid clusters,cross-disciplinary technologies such as power electronics,control theory,optimization algorithms,information and communication technologies,cyber-physical,and big-data analysis are needed.This paper introduces an overview of the relevant aspects for multi-microgrids,including the out-standing features,architectures,typical applications,existing control mechanisms,as well as the challenges.
