Deep Reinforcement Learning-Based Approach for Proportional Resonance Power System Stabilizer to Prevent Ultra-Low-Frequency Oscillations

Zhang, Guozhou; Hu, Weihao; Cao, Dengqing; Huang, Qi; Yi, Jianbo; Chen, Zhe; Blaabjerg, Frede

doi:10.1109/tsg.2020.2997790

Cited by 76 publications

(41 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [102], to guarantee the stability of the system with different wind speeds, a data-driven approach is proposed for the adaptive robust control of static synchronous compensator with additional damper controller (STATCOM-ADC) to address the uncertainty of the system. In [103], the A3C-based agent is proposed for the self-tuning of proportional resonance power system stabilizer (PR-PSS) to enhance the damping of the hydropower dominant system. In [104], an RL-based optimal method is proposed for the control of energy storage system (ESS) in AC-DC microgrid.…”

Section: Operational Controlmentioning

confidence: 99%

Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review

Cao

Zhao

et al. 2020

Journal of Modern Power Systems and Clean Energy

Self Cite

231

View full text Add to dashboard Cite

With the growing integration of distributed energy resources (DERs), flexible loads, and other emerging technologies, there are increasing complexities and uncertainties for modern power and energy systems. This brings great challenges to the operation and control. Besides, with the deployment of advanced sensor and smart meters, a large number of data are generated, which brings opportunities for novel data-driven methods to deal with complicated operation and control issues. Among them, reinforcement learning (RL) is one of the most widely promoted methods for control and optimization problems. This paper provides a comprehensive literature review of RL in terms of basic ideas, various types of algorithms, and their applications in power and energy systems. The challenges and further works are also discussed.

show abstract

Section: Operational Controlmentioning

confidence: 99%

Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review

Cao

Zhao

et al. 2020

Journal of Modern Power Systems and Clean Energy

Self Cite

231

View full text Add to dashboard Cite

show abstract

“…By continuously extracting knowledge from historical data, ML-based methods can generate powerful models to deal with the uncertainty and dynamics of a system without a physical model. The learned models can be generalized to new situations and provide control decisions in real time [22], [23]. Therefore, MLbased methods are promising alternatives with better dynamic performance of real-time optimization of the DN when accurate parameters are unknown [24].…”

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning Based Approach for Optimal Power Flow of Distribution Networks Embedded with Renewable Energy and Storage Devices

Cao

et al. 2021

Journal of Modern Power Systems and Clean Energy

Self Cite

View full text Add to dashboard Cite

This study proposes a deep reinforcement learning (DRL) based approach to analyze the optimal power flow (OPF) of distribution networks (DNs) embedded with renewable energy and storage devices. First, the OPF of the DN is formulated as a stochastic nonlinear programming problem. Then, the multi-period nonlinear programming decision problem is formulated as a Markov decision process (MDP), which is composed of multiple single-time-step sub-problems. Subsequently, the state-of-the-art DRL algorithm, i.e., proximal policy optimization (PPO), is used to solve the MDP sequentially considering the impact on the future. Neural networks are used to extract operation knowledge from historical data offline and provide online decisions according to the real-time state of the DN. The proposed approach fully exploits the historical data and reduces the influence of the prediction error on the optimization results. The proposed real-time control strategy can provide more flexible decisions and achieve better performance than the pre-determined ones. Comparative results demonstrate the effectiveness of the proposed approach. Index Terms--Deep reinforcement learning (DRL), optimal power flow (OPF), wind turbine, distribution network.

show abstract

“…The ultra-low frequency oscillations can be reduced by implementing a high-order polynomial structure. 5 Therefore, the FACT devices are to be implemented in the PV system to inject active power to the grid. Selecting the correct mitigation device is relatively easy for basic load applications.…”

Section: Introductionmentioning

confidence: 99%

An Experimental Investigation on solar PV fed modular STATCOM in WECS using Intelligent controller

Vanaja¹,

Albert

Stonier³

2021

Int Trans Electr Energ Syst

View full text Add to dashboard Cite

This paper describes an optimal way to produce and utilize green power with better energy efficiency. The power quality issues in wind energy conversion systems (WECS) are improved by implementing a photovoltaic (PV) based modular statcom. Modular statcom consist of a modular multilevel inverter (MMI). The peculiar feature of the MMI is that it does not need any auxiliary circuit to provide the negative voltage levels. It is inherent in nature. The DC link of the modular statcom is fed from the PV source, battery, and Flywheel. The excess power obtained from PV and WECS is stored in the battery and Flywheel. Continuous power can be supplied to the load without any interruption is an added advantage of the proposed system. A landsman converter is implemented for the proposed PV system to provide regulated and constant DC supply to the modular statcom.An enhanced second order generalized integrator (ESOGI) with fuzzy logic controller (FLC) is employed to extract the source reference current signal and produce gating pulses for the modular statcom. To verify the performance of the PV-integrated modular statcom, the simulation and experimental studies are performed under specific load conditions. Results show that the proposed system with the ESOGI method reduces the current distortions and satisfies the IEEE-519 standards. K E Y W O R D Ssolar photovoltaic, wind conversion system, enhanced second order generalized integrator, fuzzy logic controller, total harmonic distortion List of Symbols And abbreviations: P m , wind power equation; ρ, intensity of air; N L , number of levels; V p , peak voltage; r, radius of turbine; v, velocity of wind; Cp, power coefficient; λ, tip velocity proportion; β, pitch angle; ω, angular velocity; η, diode ideality factor; k, Boltzmann constant; q, electron charge; φ, irradiance; Tc, cell temperature; egap, band gap; Nc, number of cells in series of the PV module; Cpv, overall heat capacity of the PV module; Kin, transmittance absorption factor of PV module; Kloss, overall heat loss coefficient; Ta, ambient temperature; A, is the area of the PV module; V t , terminal voltage; Q pa Q pb Q pc , in-phase voltage template; Q qa Q qb Q qc , quadrature voltage template; v sab , v sbc v sca , source voltages; I loss , loss component; I qq ,

show abstract

Deep Reinforcement Learning-Based Approach for Proportional Resonance Power System Stabilizer to Prevent Ultra-Low-Frequency Oscillations

Cited by 76 publications

References 25 publications

Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review

Reinforcement Learning and Its Applications in Modern Power and Energy Systems: A Review

Deep Reinforcement Learning Based Approach for Optimal Power Flow of Distribution Networks Embedded with Renewable Energy and Storage Devices

An Experimental Investigation on solar PV fed modular STATCOM in WECS using Intelligent controller

Contact Info

Product

Resources

About