Distributed reinforcement learning to coordinate current sharing and voltage restoration for islanded DC microgrid

Liu, Zifa; Luo, Yimo; Zhuo, Ranqun; Jin, Xin

doi:10.1007/s40565-017-0323-y

Cited by 22 publications

(11 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A policy gradient method was applied to make decisions with limited market information. For current and voltage control, [58] integrate the consensus method and deep reinforcement learning to coordinate distributed generators in an island microgrid. The distributed reactive power optimization was solved by the collaborative equilibrium Qlearning to minimize operating cost and carbon emission [59].…”

Section: Category 3 Surrogate Modelmentioning

confidence: 99%

Review of Learning-Assisted Power System Optimization

Ruan,

Zhong,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Machine learning, with a dramatic breakthrough in recent years, is showing great potential to upgrade the power system optimization toolbox. Understanding the strength and limitation of machine learning approaches is crucial to answer when and how to integrate them in various power system optimization tasks. This paper pays special attention to the coordination between machine learning approaches and optimization models, and carefully evaluates to what extent such data-driven analysis may benefit the rule-based optimization. A series of typical references are selected and categorized into four kinds: the boundary parameter improvement, the optimization option selection, the surrogate model and the hybrid model. This taxonomy provides a novel perspective to understand the latest research progress and achievements. We further discuss several key challenges and provide an in-depth comparison on the features and designs of different categories. Deep integration of machine learning approaches and optimization models is expected to become the most promising technical trend.

show abstract

Section: Category 3 Surrogate Modelmentioning

confidence: 99%

Review of Learning-Assisted Power System Optimization

Ruan,

Zhong,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In a transient period of turning-off and turning-on of a semiconductor, switching energy loss occurs which is a summation of turn on and off switching energy losses, and it is demonstrated in (9). E sw (n)= E swon (n) + E swoff (n) (9) where E sw,on is switch-on energy losses and E sw,off is switchoff energy losses. Switch-on and switch-off energy losses are also related to semiconductor current and T j , which is explained in (10).…”

Section: Semiconductor Power Loss Comparison Of Selected Icsmentioning

confidence: 99%

Evaluation of Feasible Interlinking Converters in a Bipolar Hybrid Microgrid

Najafi

Viki

Shahparasti

2020

Journal of Modern Power Systems and Clean Energy

View full text Add to dashboard Cite

A bipolar hybrid microgrid is a new topology which benefits from the advantages of both alternating current (AC) and direct current (DC) microgrids. Interlinking AC/DC converter is the key of this topology which has the following characteristics: being able to provide two equal pole voltages in DC side; complying with the standards of current quality at AC side; being able to control active and reactive power independently in AC side, and transmitting bidirectional power. In this paper, two categories of power converters including single-stage and two-stage converters are proposed for this topology. A new cost-effective control strategy is added to the control of general grid-connected converter for each interlinking converter, and the control of autonomous DC-link pole voltage for both candidates is achieved. Detailed simulations based on the designed control strategies are conducted to validate the function of control strategies under the operation conditions of different DC sides. The performances of two selected interlinking converters with balanced and unbalanced DC loads are analyzed. Suggested power quality of microgrid and total harmonic distortion (THD) analysis are demonstrated in grid-tied and islanded modes. Eventually, semiconductor power loss simulations based on a closed-loop thermal network simulation are conducted. Thereby, the mutual effects of power loss and initial junction temperature are investigated.

show abstract

“…In [6], the RL method is used for reactive power control. In [7], voltage restoration for an islanded microgrid is achieved via a distributed RL method. In [8], an application for disturbance classification is proposed based on image embedding and convolutional neural network (CNN).…”

Section: Introductionmentioning

confidence: 99%

Mitigating Multi-Stage Cascading Failure by Reinforcement Learning

Zhu

Liu

2019

2019 IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia)

View full text Add to dashboard Cite

This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL) method. Firstly, the principles of RL are introduced. Then, the Multi-Stage Cascading Failure (MSCF) problem is presented and its challenges are investigated. The problem is then tackled by the RL based on DC-OPF (Optimal Power Flow). Designs of the key elements of the RL framework (rewards, states, etc.) are also discussed in detail. Experiments on the IEEE 118-bus system by both shallow and deep neural networks demonstrate promising results in terms of reduced system collapse rates. Index Terms-cascading failure, convolutional neural network, deep learning, optimal power flow, reinforcement learning.I.

show abstract

Distributed reinforcement learning to coordinate current sharing and voltage restoration for islanded DC microgrid

Cited by 22 publications

References 31 publications

Review of Learning-Assisted Power System Optimization

Review of Learning-Assisted Power System Optimization

Evaluation of Feasible Interlinking Converters in a Bipolar Hybrid Microgrid

Mitigating Multi-Stage Cascading Failure by Reinforcement Learning

Contact Info

Product

Resources

About