Microgrid Stability Improvement Using a Deep Neural Network Controller Based VSG

Mohammadreza, Ghodsi; Tavakoli, Alireza; Samanfar, Amin

doi:10.1155/2022/7539173

Cited by 7 publications

(4 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [72], the LSTM algorithm is applied to mimic the relationship between the inputs and outputs of a VSG control model when a phase-to-phase short circuit fault occurs. And the same idea is applied in [73] by combining the restricted Boltzmann machine (RBM) features and a DNN. With fewer inputs, the proposed controller can suppress the power oscillation and provide a stable frequency.…”

Section: And Rl In Single Vsgmentioning

confidence: 99%

Deep and Reinforcement Learning in Virtual Synchronous Generator: A Comprehensive Review

Ding,

Cao

2024

Energies

View full text Add to dashboard Cite

The virtual synchronous generator (VSG) is an important concept and primary control method in modern power systems. The penetration of power-electronics-based distributed generators in the power grid provides uncertainty and reduces the inertia of the system, thus increasing the risk of instability when disturbance occurs. The VSG produces virtual inertia by introducing the dynamic characteristics of the synchronous generator, which provides inertia and becomes a grid-forming control method. The disadvantages of the VSG are that there are many parameters to be adjusted and its operation process is complicated. However, with the rapid development of artificial intelligence (AI) technology, the powerful adaptive learning capability of AI algorithms provides potential solutions to this issue. Two research hotspots are deep learning (DL) and reinforcement learning (RL). This paper presents a comprehensive review of these two techniques combined with VSG control in the energy internet (EI). Firstly, the basic principle and classification of the VSG are introduced. Next, the development of DL and RL algorithms is briefly reviewed. Then, recent research on VSG control based on DL and RL algorithms are summarized. Finally, some main challenges and study trends are discussed.

show abstract

Section: And Rl In Single Vsgmentioning

confidence: 99%

Deep and Reinforcement Learning in Virtual Synchronous Generator: A Comprehensive Review

Ding,

Cao

2024

Energies

View full text Add to dashboard Cite

show abstract

“…The damping strategy for artificial intelligence (AI) has been the subject of recent research [124][125][126][127]. These intelligent controllers can learn from the system where there are deployed and adapt to improve the system's overall performance in damping oscillations.…”

Section: Artificial Intelligencementioning

confidence: 99%

“…The damping strategy for artificial intelligence (AI) has been the subject of rec search [125][126][127][128]. These intelligent controllers can learn from the system where the deployed and adapt to improve the system's overall performance in damping oscilla A neuro-fuzzy controller (NFC) in form of a fuzzy logic controller (FLC) and ar neural network (ANN) was employed in [35] to replace PSS, and it offered superio tures to the traditional PSS and FACTS damping controllers.…”

Section: Artificial Intelligencementioning

confidence: 99%

Solar, Wind and Their Hybridization Integration for Multi-Machine Power System Oscillation Controllers Optimization: A Review

et al. 2022

View full text Add to dashboard Cite

Massive growth in global electrical energy demand has necessitated a genuine exploration and integration of solar and wind energy into the electrical power mix. This incorporation goes a long way in improving the cumulative generated power capacity of the power system. However, wind and solar photovoltaic (PV) are intermittent in nature, making the provisioning of a good maximum power tracking (MPPT) scheme necessary. Furthermore, the integration is characterized by synchronization challenges and introduces various modes of power system oscillations as it is converter-driven. This greatly affects the overall stability of the integrated power mix. Consequently, various technological models have been designed to address these challenges ranging from MPPT schemes, phase-lock loop (PLL), virtual synchronous generator (VSG), power system stabilizers (PSS), flexible AC transmission system (FACTS), coordinated control and artificial intelligence (AI). In this work, a multi-machine power system model is reviewed for integration stability studies. Various technical solutions associated with the integration are also reviewed. MPPT, PLL, VSG, PSS, FACTS, coordinated control, and various optimization technique schemes used for damping controller design are discussed.

show abstract

“…The authors of [13] considered a comparison of a virtualized synchronous generator (SG) and droop control characteristics during the use of inverter-based distributed generators. Similarly, researchers in [14][15][16] studied the possibility of virtualizing converter operation algorithms to achieve synchronization with a synchronous generator. The above-mentioned virtualization method was adopted in this paper for the invertor-based ESS, with the aim of carrying out a simulation of DG and ESS in parallel operation.…”

Section: Introductionmentioning

confidence: 99%

Emergency Prevention Control as a Means of Power Quality Improvement in a Shipboard Hybrid Electric Power System

Tierielnyk,

Lukovtsev

2024

Energies

View full text Add to dashboard Cite

The problems associated with the greenhouse effect have increased the desire to limit carbon dioxide (CO2) emissions into the atmosphere, including emissions produced by shipboard electrical power systems. This has led to a further search for solutions in this area, such as shipboard hybrid electric power systems (SHEPSs). These systems do not yet have a wide application compared with traditional shipboard electrical power systems for several reasons, including the lack of studies establishing the fault tolerance of such systems. Therefore, in this work, problems related to generated power quality deterioration under large disturbances are studied. To achieve the fault-free operation of SHEPS, an emergency prevention control (EPC) system based on controlled parameter forecasting, along with a system structure and operation algorithm, is developed. The goals of improving electrical power quality are achieved by increasing the control efficiency of the power system’s generating sources. To validate the feasibility of the proposed control system, a computer simulation was carried out after developing a mathematical model of the SHEPS under study. The results of the study show that the use of the proposed EPC system will improve power quality when the controlled parameters are within acceptable limits. At the same time, further research is needed, as the problem of false control action as a consequence of EPC system hardware or software faults remains unstudied.

show abstract

Microgrid Stability Improvement Using a Deep Neural Network Controller Based VSG

Cited by 7 publications

References 62 publications

Deep and Reinforcement Learning in Virtual Synchronous Generator: A Comprehensive Review

Deep and Reinforcement Learning in Virtual Synchronous Generator: A Comprehensive Review

Solar, Wind and Their Hybridization Integration for Multi-Machine Power System Oscillation Controllers Optimization: A Review

Emergency Prevention Control as a Means of Power Quality Improvement in a Shipboard Hybrid Electric Power System

Contact Info

Product

Resources

About