DC/DC Power Converter Control-Based Deep Machine Learning Techniques: Real-Time Implementation

被引:91
作者
Hajihosseini, Mojtaba [1 ]
Andalibi, Milad [1 ]
Gheisarnejad, Meysam [2 ]
Farsizadeh, Hamed [3 ]
Khooban, Mohammad-Hassan [4 ]
机构
[1] Shiraz Univ, Sch Elect & Comp Engn, Shiraz 7194684471, Iran
[2] Islamic Azad Univ, Najafabad Branch, Dept Elect Engn, Esfahan 8514143131, Iran
[3] Shiraz Univ Technol, Dept Elect & Elect Engn, Shiraz 7194684471, Iran
[4] Aarhus Univ, DIGIT, Dept Engn, DK-8200 Aarhus, Denmark
关键词
Constant power loud (CPL); dc-dc buck-boost converter; deep reinforcement learning (DRL); ultralocal model (ULM); SLIDING-MODE CONTROL;
D O I
10.1109/TPEL.2020.2977765
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The recent advances in power plants and energy resources have extended the applications of buck-boost converters in the context of dc microgrids (MGs). However, the implementation of such interface systems in the MG applications is seriously threatened with instability issues imposed by the constant power loads (CPLs). The objective is that without the accurate modeling information of a dc MG system, to develop a new adaptive control methodology for voltage stabilization of the dc-dc converters feeding CPLs with low ripples. To achieve this goal, in this letter, the deep reinforcement learning (DRL) technique with the Actor- Critic architecture is incorporated into an ultralocal model (ULM) control scheme to address the destabilization effect of the CPLs under the reference voltage variations. In the suggested control approach, the feedback controller gains of the ULM controller are considered as the adjustable controller coefficients, which will be adaptively designed by the DRI, technique through online learning of its neural networks (NNs). It is proved that the suggested scheme will ensure the rigorous stability of the power electronic system, for simultaneous effects of CPL and reference voltage changes, by adaptively adjusting the ULM controller gains. To appraise the merits and usefulness of the suggested adaptive methodology, some dSPACE MicroLabBox outcomes on a real-time testhed of the dc-dc converter feeding a CPL are presented.
引用
收藏
页码:9971 / 9977
页数:7
相关论文
共 18 条
[1]   On the control of robot manipulator: A model-free approach [J].
Abouaissa, Hassane ;
Chouraqui, Samira .
JOURNAL OF COMPUTATIONAL SCIENCE, 2019, 31 :6-16
[2]  
[Anonymous], [No title captured]
[3]  
[Anonymous], IEEE T CIRCUITS SY 2
[4]   A New Adaptive Type-II Fuzzy-Based Deep Reinforcement Learning Control: Fuel Cell Air-Feed Sensors Control [J].
Gheisarnejad, Meysam ;
Boudjadar, Jalil ;
Khooban, Mohammad Hassan .
IEEE SENSORS JOURNAL, 2019, 19 (20) :9081-9089
[5]   Deep reinforcement learning-based joint task offloading and bandwidth allocation for multi-user mobile edge computing [J].
Huang, Liang ;
Feng, Xu ;
Zhang, Cheng ;
Qian, Liping ;
Wu, Yuan .
DIGITAL COMMUNICATIONS AND NETWORKS, 2019, 5 (01) :10-17
[6]   Amplitude Death Solutions for Stabilization of DC Microgrids With Instantaneous Constant-Power Loads [J].
Huddy, Stanley R. ;
Skufca, Joseph D. .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2013, 28 (01) :247-253
[7]   A New Intelligent Hybrid Control Approach for DC-DC Converters in Zero-Emission Ferry Ships [J].
Khooban, Mohammad Hassan ;
Gheisarnejad, Meysam ;
Farsizadeh, Hamed ;
Masoudian, Ali ;
Boudjadar, Jalil .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2020, 35 (06) :5832-5841
[8]   Design of Quadratic D-Stable Fuzzy Controller for DC Microgrids With Multiple CPLs [J].
Mardani, Mohammad Mehdi ;
Vafamand, Navid ;
Khooban, Mohammad Hassan ;
Dragicevic, Tomislav ;
Blaabjerg, Frede .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2019, 66 (06) :4805-4812
[9]   Robust sliding-mode control of dc/dc boost converter feeding a constant power load [J].
Singh, Suresh ;
Fulwani, Deepak ;
Kumar, Vinod .
IET POWER ELECTRONICS, 2015, 8 (07) :1230-1237
[10]   GPIO-Based Robust Control of Nonlinear Uncertain Systems Under Time-Varying Disturbance With Application to DCDC Converter [J].
Sun, Jiankun ;
Yang, Jun ;
Zheng, Wei Xing ;
Li, Shihua .
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 2016, 63 (11) :1074-1078