作者：钱欣¹, 任东²

作者单位：1. 承德石油高等专科学校，河北 承德 067000;
2. 华北电力大学 高压与电磁兼容北京重点实验室，北京 102206

关键词：直流微网;人工智能;转换器;无传感器控制;电池存储系统

摘要：

为增强直流微电网储能系统无传感器功率控制的稳定性，克服通信延迟对储能系统稳定控制的影响，该文采用离线训练人工神经网络(artificial neural networks, ANN)方法，提出一种适用于直流微电网中储能系统变流器的新型功率控制策略。该控制策略能够有效应对可再生能源的强波动性，减少传感器数量，从而极大降低微网内传感器的安装成本。此外，它还简化控制系统结构，并在提升系统的可靠性和控制效果方面具有明显优势。最后，在Matlab/Simulink中进行离线和在线时域仿真。仿真结果表明：相对于实测值，该文所提方法可将延迟时间缩小18.3%，震荡减小35.8%，百分比误差量缩小4.5%。

ANN power control method for converter in DC microgrid
QIAN Xin¹, REN Dong²
1. Chengde Petroleum College, Chengde 067000, China;
2. Beijing Key Laboratory of High Voltage & Electromagnetic, North China Electric Power University, Beijing 102206, China
Abstract: In order to enhance the stability of sensorless power control of DC microgrid energy storage system and overcome the influence of communication delay on the stability control of energy storage system, the off-line training artificial neural networks (ANN) method is adopted in this paper. A new power control strategy for the converters of energy storage systems in DC microgrids is proposed. This control strategy can effectively deal with the high volatility of renewable energy and reduce the number of sensors, thus greatly reducing the installation cost of sensors in the microgrid. In addition, it also simplifies the control system structure and has obvious advantages in improving the system reliability and control effectiveness. Finally, offline and online time domain simulations are carried out in Matlab/Simulink. The simulation results show that, compared with the measured values, the proposed method can reduce the delay time by 18.3%, the oscillation by 35.8% and the percentage error by 4.5%.
Keywords: DC microgrids;artificial intelligence;converters;sensorless control;battery storage system (BSS)
2022, 48(5):134-141  收稿日期: 2021-03-31;收到修改稿日期: 2021-05-17
基金项目: 河北省科技厅项目（19211601D）
作者简介: 钱欣（1974-），女，河北承德市人，讲师，硕士，研究方向为直流微电网控制技术
参考文献
[1] 陈素霞, 李娜娜. 并联变流器变压器侧高频谐波抑制与移相角计算[J]. 中国测试, 2020, 10: 118-123
[2] KARAMA N, MOAYED A. Energy management for a PEMFC-PV hybrid system[J]. Energy Convers. Manga, 2014, 82: 154-168
[3] LUNA A, MENG L. Online energy management systems for microgrids: experimental validation and assessment framework[J]. IEEE Trans. Power Electron, 2018, 33(3): 2201-2215
[4] HAN Y, LI H. Review of active and reactive power sharing strategies in hierarchical controlled microgrids[J]. IEEE Trans Power Electron, 2017, 32(3): 2427-2451
[5] ULAY S, HAI A. Assessment of technical and financial benefits of AC and DC microgrids based on solar photovoltaic[J]. Electric Eng, 2020, 143: 1-14
[6] DRAEY T, GUERY J. Supervisory control of adaptive-droop regulated DC microgrid with battery[J]. IEEE Trans Power Electron, 2014, 29(2): 695-706
[7] ZUO S, ALTUM T. Distributed resilient secondary control of DC microgrids against unbounded attacks[J]. IEEE Trans Smart Grid, 2020, 11(5): 3850-3859
[8] HU J, XU Y. A model predictive control strategy of PV-Battery microgrid under variable power generations and load conditions[J]. Appl Energy, 2018, 221: 195-203
[9] JING W, HUNG C. Battery supercapacitor hybrid energy storage system in standalone DC microgrids: a review[J]. IET Renew Power Genre, 2017, 11(4): 461-169
[10] 黄德明,陈为. 基于镜像法的变压器空心管型绕组损耗计算[J]. 磁性材料及器件, 2021, 52(5): 42-46
[11] GOU C, MORE J. Coordinating storage and demand response for microgrid emergency operation[J]. IEEE Trans Smart Grid, 2016, 4(4): 1898-1908
[12] SINGER V, RPTI R. HIL co-simulation of finite set-model predictive control using FPGA for a three-phase VSI system[J]. Energies, 2018, 11(4): 909
[13] SHA Q, GUER J. Distributed secondary control for islanded microgrids—A novel approach[J]. IEEE Trans Power Electron, 2014, 29(2): 1018-1031
[14] MOHA A, REF S. AC microgrid control and management strategies: evaluation and review[J]. IEEE Power Electron Mag, 2019, 6(2): 18-31
[15] 孙佃升, 章跃进. 自抗扰控制和高频信号注入的内嵌式永 磁同步电机无位置传感器控制[J]. 控制理论与应用, 2017, 34(4): 508-514