Control Strategy of a Hybrid Renewable Energy System Based on Reinforcement Learning Approach for an Isolated Microgrid

Phan, Bao Chau; Lai, Ying Chih

doi:10.3390/app9194001

Cited by 37 publications

(23 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…RL is a heuristic intelligent technique consisting of environment, agent, action, rewards, penalties, and states [128]. RL aims to learn how to maximize the rewards for the agent based on the rewards or penalties of its actions in predefined environment states [129].…”

Section: A Power-sharingmentioning

confidence: 99%

“…RL aims to learn how to maximize the rewards for the agent based on the rewards or penalties of its actions in predefined environment states [129]. Different studies implement RL to optimize the schedule of DGs or DSs based on their predicted product, energy price, and load demand [128], [130], [129], [131]- [133]. FLC is another intelligent control technique which emulates human decision making [134].…”

Section: A Power-sharingmentioning

confidence: 99%

See 1 more Smart Citation

Recent Contributions, Future Prospects and Limitations of Interlinking Converter Control in Hybrid AC/DC Microgrids

et al. 2021

View full text Add to dashboard Cite

This work analyzes interlinking converter control in hybrid AC/DC microgrids. The paper addresses the state-of-the-art general hybrid microgrid structure. The key power electronics topologies are used as bidirectional interface converters in the AC and DC parts. Different control structures of hybrid microgrids are categorized, followed by the classification of the main control functions, their control strategies, and the control techniques and a summary of their positive and negative aspects and applications. Control functions, their strategies and techniques are classified in the interlinking-converter based. Finally, overall control objectives, time-scaled control structures, and their strategies are outlined. The prospects, main challenges, research gaps, and the trend of the hybrid microgrid structure and control are reviewed and summarized in the conclusions.

show abstract

Section: A Power-sharingmentioning

confidence: 99%

Section: A Power-sharingmentioning

confidence: 99%

Recent Contributions, Future Prospects and Limitations of Interlinking Converter Control in Hybrid AC/DC Microgrids

et al. 2021

View full text Add to dashboard Cite

show abstract

“…PV solar cells generally have a p-n junction which is fabricated in a thin layer of semiconductor materials to convert the solar irradiation into electricity [30]. It is important to employ a reliable solar cell model to simulate a PV system.…”

Section: Mathematical Model Of Pv Modulementioning

confidence: 99%

“…When connecting output terminals of a PV array with a DC-DC converter, the array voltage can be controlled by changing the duty cycle D, which is a pulse width modulation (PWM) signal and is executed by the MPPT controller to regulate the voltage at which maximum power is obtained. The calculation of the duty cycle for a DC-DC boost converter is given by [30]…”

Section: Pv System Introductionmentioning

confidence: 99%

A Deep Reinforcement Learning-Based MPPT Control for PV Systems under Partial Shading Condition

Phan

Lai

Lin

2020

Sensors

View full text Add to dashboard Cite

On the issues of global environment protection, the renewable energy systems have been widely considered. The photovoltaic (PV) system converts solar power into electricity and significantly reduces the consumption of fossil fuels from environment pollution. Besides introducing new materials for the solar cells to improve the energy conversion efficiency, the maximum power point tracking (MPPT) algorithms have been developed to ensure the efficient operation of PV systems at the maximum power point (MPP) under various weather conditions. The integration of reinforcement learning and deep learning, named deep reinforcement learning (DRL), is proposed in this paper as a future tool to deal with the optimization control problems. Following the success of deep reinforcement learning (DRL) in several fields, the deep Q network (DQN) and deep deterministic policy gradient (DDPG) are proposed to harvest the MPP in PV systems, especially under a partial shading condition (PSC). Different from the reinforcement learning (RL)-based method, which is only operated with discrete state and action spaces, the methods adopted in this paper are used to deal with continuous state spaces. In this study, DQN solves the problem with discrete action spaces, while DDPG handles the continuous action spaces. The proposed methods are simulated in MATLAB/Simulink for feasibility analysis. Further tests under various input conditions with comparisons to the classical Perturb and observe (P&O) MPPT method are carried out for validation. Based on the simulation results in this study, the performance of the proposed methods is outstanding and efficient, showing its potential for further applications.

show abstract

“…One of the most promising learning-based EMS methods is the reinforcement learning (RL) paradigm [22], in which an agent learns the dynamics of the microgrid by interacting with its components. Several works have demonstrated successful implementations of reinforcement learning-based EMSs in different microgrid architectures, either within a single agent [23]- [25] or multi-agent framework [26]- [29]. However, the basic and most popular RL methods, such as Q-learning [30], face several challenges related to inefficient data usage, high dimensionality, state space continuity, and transition function uncertainty.…”

Section: Introductionmentioning

confidence: 99%

Deep reinforcement learning for energy management in a microgrid with flexible demand

Nakabi

Toivanen

2021

Sustainable Energy, Grids and Networks

133

View full text Add to dashboard Cite

In this paper, we study the performance of various deep reinforcement learning algorithms to enhance the energy management system of a microgrid. We propose a novel microgrid model that consists of a wind turbine generator, an energy storage system, a set of thermostatically controlled loads, a set of priceresponsive loads, and a connection to the main grid. The proposed energy management system is designed to coordinate among the different flexible sources by defining the priority resources, direct demand control signals, and electricity prices. Seven deep reinforcement learning algorithms were implemented and are empirically compared in this paper. The numerical results show that the deep reinforcement learning algorithms differ widely in their ability to converge to optimal policies. By adding an experience replay and a semi-deterministic training phase to the well-known asynchronous advantage actor-critic algorithm, we achieved the highest model performance as well as convergence to near-optimal policies.

show abstract

Control Strategy of a Hybrid Renewable Energy System Based on Reinforcement Learning Approach for an Isolated Microgrid

Cited by 37 publications

References 44 publications

Recent Contributions, Future Prospects and Limitations of Interlinking Converter Control in Hybrid AC/DC Microgrids

Recent Contributions, Future Prospects and Limitations of Interlinking Converter Control in Hybrid AC/DC Microgrids

A Deep Reinforcement Learning-Based MPPT Control for PV Systems under Partial Shading Condition

Deep reinforcement learning for energy management in a microgrid with flexible demand

Contact Info

Product

Resources

About