Data-Driven Distributed Online Learning Control for Islanded Microgrids

Zheng, Dongdong; Madani, Seyed Sohail; Karimi, Alireza

doi:10.1109/jetcas.2022.3152938

Cited by 23 publications

(10 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• When a new PV unit is integrated or removed from the MG, existing PVGs do not need re-tuning. This scalability feature has not been supported by the majority of the existing solutions, e.g., [14], [17], [19], and [21]. • The proposed method provides overvoltage control with <2% error within 1s, among the fastest and high accurate solutions.…”

Section: Comparison With Some Mppt-based Schemesmentioning

confidence: 93%

“…Finally, machine learning tools have been suggested at all control levels, mainly primary, to develop new schemes. Reference [14] presented a data-driven neural network-based droop controller for the power-sharing of DGs, supported by BESS for MG's power balance. As shown in hardware-inthe-loop simulations, this work expedites the transient performance compared with conventional droop controllers.…”

Section: A Background and Motivationmentioning

confidence: 99%

“…• First and foremost, the required PV array voltage shift is analytically defined in this work for each PV system regarding its β. Conversely, most existing MPPT-based controllers determined the power curtailment level through simulation [18]- [25] or data-driven approaches [14], [28], i.e., lack supporting analytical expressions. • When a new PV unit is integrated or removed from the MG, existing PVGs do not need re-tuning.…”

Section: Comparison With Some Mppt-based Schemesmentioning

confidence: 99%

See 2 more Smart Citations

Analytical Overvoltage and Power-Sharing Control Method for Photovoltaic-Based Low-Voltage Islanded Microgrid

Bakhshi-Jafarabadi,

Lekić,

Marvasti

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Overvoltage instability is a growing concern in a standalone low-voltage (LV) microgrid (MG) with non-dispatchable intermittent renewable energies such as residential and commercial photovoltaic generators (PVGs). Several overvoltage controllers used in PV arrays have adopted the concept of standard deviation from the maximum power point (MPP) to curtail the generated power. However, these solutions lack presenting analytical expression for the MPP deviation size, settings tuning independent of the MG's/PV's characteristics, scalability, and accurate power-sharing in the same control structure. To overcome these limitations, this paper proposes a new analytical MPP tracking (MPPT)-based overvoltage and power-sharing control method using the series equivalent resistance of the PV module model. By applying this analytical expression, the size of the PV array voltage shift to the right-hand side of the MPP is obtained in terms of overvoltage level, while all PVGs proportionally curtail the active power output. The effectiveness of the proposed methodology is shown in various low-demand and high-PV generation cases through a real time digital simulator (RTDS) platform. In addition to the fast and accurate performance, the presented method benefits from the straightforward and communication-free structure as it solely exploits the point of common coupling (PCC) voltage. Also, the method's threshold does not require re-tuning after MG restructure, ensuring scalability. Without relying on other microgrid facilities, the proposed methodology is accordingly an effective solution for practical PV-based LV MGs.

show abstract

Section: Comparison With Some Mppt-based Schemesmentioning

confidence: 93%

Section: A Background and Motivationmentioning

confidence: 99%

Section: Comparison With Some Mppt-based Schemesmentioning

confidence: 99%

See 1 more Smart Citation

Analytical Overvoltage and Power-Sharing Control Method for Photovoltaic-Based Low-Voltage Islanded Microgrid

Bakhshi-Jafarabadi,

Lekić,

Marvasti

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The aforementioned approaches have some shortcomings such as lack of accurate decoupling of active and reactive power, dependency on topology and type of microgrids, and requirement for additional sensors and measurements. Hence, some recent approaches aim at further enhancement of the droop controllers through intelligent control schemes [28], [29], [30], [31], [32], [33], [34]. Lin et al [28] proposed a probabilistic wavelet fuzzy neural network algorithm to replace PI-based voltage controller in droop-controlled islanded microgrid for power sharing and load shedding purposes.…”

mentioning

confidence: 99%

“…This paper mainly focuses on frequency control of microgrids rather than power sharing capability, and the proposed method is an offline model-based control scheme that requires a prior understanding of the system model. Authors in [34], proposed a data-driven online learning algorithm based on neural networks to replace the conventional hierarchical droop control framework for voltage/frequency regulation and power sharing control. The drawback of the method is that voltage regulation and reactive power sharing cannot be reached simultaneously and reactive power sharing is prioritized at the expense of higher voltage errors.…”

mentioning

confidence: 99%

Droop-Controlled Bidirectional Inverter-Based Microgrid Using Cascade-Forward Neural Networks

Alzayed

Lemaire

Zarrabian

et al. 2022

IEEE Open J. Circuits Syst.

View full text Add to dashboard Cite

The voltage source inverters in microgrids often rely on the droop control method integrated with voltage and inner current control loops in order to provide a reliable electric power supply. This research aims to present a Cascade-Forward Neural Network (CFNN) droop control method that manages inverter-based microgrids under grid-connected/islanded operating modes. The proposed method operates the inverter in a bi-directional technique for a wide range of battery energy storage systems or any other distributed generation systems. The proposed strategy uses the CFNN to learn the inverter's nonlinear model to achieve accurate demand and reference power tracking under different operating conditions for smart grid applications. Additionally, it reformulates the grid control concept to drive the inverter based on the optimal conditions by considering the power demand, reference power, equipment size, and disturbances. Also, it does not require any tuning procedure. The power tracking and operating performance of the proposed CFNN controller are evaluated through several experimental tests using the power hardware-in-the-loop (PHIL) methodology in different scenarios. All results are matched with the proven conventional strategy to confirm its effectiveness.INDEX TERMS Distributed generation, droop control, inverter-based power system, microgrid, cascadeforward neural network.

show abstract

Intelligent Power Electronic Converters and Control for Microgrids: A Master-Slave Model Predictive Approach

Carnielutti,

Aly,

Norambuena

et al. 2024

Green Energy and Technology

View full text Add to dashboard Cite

Data-Driven Distributed Online Learning Control for Islanded Microgrids

Cited by 23 publications

References 53 publications

Analytical Overvoltage and Power-Sharing Control Method for Photovoltaic-Based Low-Voltage Islanded Microgrid

Analytical Overvoltage and Power-Sharing Control Method for Photovoltaic-Based Low-Voltage Islanded Microgrid

Droop-Controlled Bidirectional Inverter-Based Microgrid Using Cascade-Forward Neural Networks

Intelligent Power Electronic Converters and Control for Microgrids: A Master-Slave Model Predictive Approach

Contact Info

Product

Resources

About