Equivalent Modeling of AC/DC Microgrid Connection Based on Improved Extreme Learning Machine

doi:10.3969/j.issn.1008-0198.2022.06.014

Hunan Electric Power ›› 2022, Vol. 42 ›› Issue (6): 83-89.doi: 10.3969/j.issn.1008-0198.2022.06.014

• New technology and Application • Previous Articles Next Articles

Equivalent Modeling of AC/DC Microgrid Connection Based on Improved Extreme Learning Machine

XI Mengrui^1,2, CAI Changchun^1,2, WANG Bin³

1. Jiangsu Key Laboratory of Power Transmission & Distribution Equipment Technology(Hohai University), Changzhou 213022, China;
2. College of The IOT Engineering, Hohai University, Changzhou 213022, China;
3. State Grid Taicang Electric Power Supply Company, Taicang 215400, China

Received:2022-08-20 Revised:2022-10-13 Online:2022-12-25 Published:2023-01-13

Abstract

Abstract: With the increasing number of microgrid connected to distribution network, it brings challenges to the stable operation of distribution network. The equivalent modeling of microgrid is the basis for analyzing the impact of microgrid access and dynamic simulation of distribution network. Based on the theory of non-mechanistic modeling, this paper establishes an AC/DC microgrid grid-connected equivalent model of extreme learning machine with real and imaginary parts of voltage and current as input and power as output. The sparrow search algorithm is used to optimize the input weight and threshold of extreme learning machine to reduce the model accuracy problem caused by the lack of unity of input weight and threshold. Finally, the AC/DC hybrid microgrid model is built on DIgSILENT platform for verification. The simulation results show the effectiveness and accuracy of the proposed equivalent model.

Key words: microgrid, sparrow search algorithm, improved extreme learning machine, AC/DC microgrid, equivalent modeling

CLC Number:

TM727

XI Mengrui, CAI Changchun, WANG Bin. Equivalent Modeling of AC/DC Microgrid Connection Based on Improved Extreme Learning Machine[J]. Hunan Electric Power, 2022, 42(6): 83-89.

References

[1]冯培磊,陈潇雅,徐天奇. 微电网关键技术研究综述[J].水电与抽水蓄能,2020,6(3):45-49.
[2]宋春宁,付栋,李欣.双向全桥DC/DC变换器在直流微电网中的应用[J].电测与仪表, 2020, 57(18): 128-132.
[3]CAI C, LIU H, TAO Y,et al. Microgrid Equivalent Modeling Based on Long Short-Term Memory Neural Network[J]. IEEE Access, 2020,8: 23120-23133.
[4]LI Y, WANG Z, YANG J, et al. Dynamic Equivalence Modeling for Microgrid Cluster by Using Physical-Data-Driven Method[J].IEEE Transactions on Applied Superconductivity,2021,31(8): 1-4.
[5]HUA J, QIAN A, YUAN Y. Dynamic equivalent of microgrid considering flexible components[J]. IET Generation Transmission & Distribution, 2015, 9(13):1688-1696.
[6]PAPADOPOULOS P N, PAPADOPOULOS T A, CROLLA P, et al. Black-box dynamic equivalent model for microgrids using measurement data[J]. IET Generation Transmission & Distribution, 2014, 8(5):851-861.
[7]MITRENTSIS G, LENS H. Data-Driven Dynamic Models of Active Distribution Networks Using Unsupervised Learning Techniques on Field Measurements[J]. IEEE Transactions on Smart Grid,2021,12(4):2952-2965.
[8]SHUAI Z, PENG Y, LIU X, et al. Dynamic Equivalent Modeling for Multi-Microgrid Based on Structure Preservation Method[J]. IEEE Transactions on Smart Grid, 2019,10(4): 3929-3942.
[9]吴忠强,戚松岐,尚梦瑶,等. 基于优化回声状态网络的微电网等效建模[J].计量学报,2021,42(7):923-929.
[10]吴忠强,戚松岐,尚梦瑶,等. 基于优化极限学习机的直流微电网并网等效建模[J].电力自动化设备,2020,40(6):43-49.
[11]MATEVOSYAN J, VILLANUEVA S M, DJOKIC S Z, et al. Aggregated models of wind-based generation and active distribution network cells for power system studies-literature overview[C]// 2011 IEEE Trondheim PowerTech. Trondheim,Norway,2011:1-8.
[12]任志航,李民,马凯琪,等. 交直流混合微电网微元建模与控制[J].电力系统保护与控制,2017,45(21):82-88.
[13]符杨,王晓旭,米阳,等.基于本地自适应调节的交直流混合微电网全局协调控制[J].电测与仪表,2022,59(7):152-162.
[14]胡济洲,奚江惠,宋军英.交直流协控技术在大电网的应用及配置[J].湖南电力,2016,36(6):1-4.
[15]王逸超,陈仲伟,欧名勇,等.利用电动汽车移动储能的微电网经济运行优化策略[J].湖南电力,2018,38(3):38-41,45.
[16]王小川,史峰,郁磊,等. MATLAB神经网络43个案例分析[M].北京:北京航空航天大学出版社,2013.
[17]薛建凯. 一种新型的群智能优化技术的研究与应用——麻雀搜索算法[D].上海:东华大学,2020.
[18]李敦桥.一种混合麻雀搜索算法[J].电脑知识与技术,2021,17(5):232-234.
[19]王以笑,张新昌,路进升,等. 基于DIgSILENT的并网光伏发电系统的建模与仿真[J].电力系统保护与控制,2014,42(3):49-55.
[20]王维栋,栗文义,王蕴敏,等. 基于DIgSILENT的微电网三相不对称交直流潮流仿真研究[J].水电能源科学,2017,35(6):195-198.
[21]赵睿智,丁云飞.基于MEEMD-KELM的短期风电功率预测[J].电测与仪表,2020,57(21):92-98.

Equivalent Modeling of AC/DC Microgrid Connection Based on Improved Extreme Learning Machine

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 2

Recommended Articles

Metrics

Comments

[1]	BAI Penghui, QIN Bin, WANG Xin. Research on Hybrid Energy Storage Control Based on Improved Virtual DC Motor [J]. Hunan Electric Power, 2023, 43(1): 17-22.
[2]	JIA Hao, ZHANG Lian, ZHANG Shangde, ZHAO Mengqi, ZHAO Na, HUANG Wei. Diagnosis of Circuit Breaker Current Characteristics Based on LSSA-BP Neural Network [J]. Hunan Electric Power, 2022, 42(5): 36-41.