Assessing the Use of Reinforcement Learning for Integrated Voltage/Frequency Control in AC Microgrids

Younesi, Abdollah; Shayeghi, Hossein; Siano, Pierluigi

doi:10.3390/en13051250

Cited by 16 publications

(8 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We denote ∆P L in (17) as the deviations of other power injections, such as loads (negative power injection), the outputs of renewable energy resources, the charging/discharging power of energy storage systems, etc. Depending on the actual problem setting, ∆P L can be treated as exogenous states with additional dynamics, or be included in the action a if these power injections are also controlled for FR [60], [61].…”

Section: A Frequency Regulationmentioning

confidence: 99%

See 1 more Smart Citation

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Chen

Tang

et al. 2022

IEEE Trans. Smart Grid

184

View full text Add to dashboard Cite

With large-scale integration of renewable generation and distributed energy resources, modern power systems are confronted with new operational challenges, such as growing complexity, increasing uncertainty, and aggravating volatility. Meanwhile, more and more data are becoming available owing to the widespread deployment of smart meters, smart sensors, and upgraded communication networks. As a result, data-driven control techniques, especially reinforcement learning (RL), have attracted surging attention in recent years. This paper provides a comprehensive review of various RL techniques and how they can be applied to decision-making and control in power systems. In particular, we select three key applications, i.e., frequency regulation, voltage control, and energy management, as examples to illustrate RL-based models and solutions. We then present the critical issues in the application of RL, i.e., safety, robustness, scalability, and data. Several potential future directions are discussed as well.

show abstract

Section: A Frequency Regulationmentioning

confidence: 99%

“…• Integration with Existing Controllers. References [60], [61] use the DRL-based controller as a supervisory or supplementary controller to existing PID-based FR controllers, to improve the dynamical adaptivity with baseline performance guarantee. More discussions are provided in Section IV-D.…”

Section: A Frequency Regulationmentioning

confidence: 99%

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Chen

Tang

et al. 2022

IEEE Trans. Smart Grid

184

View full text Add to dashboard Cite

show abstract

“…Generally, Adaptive fuzzy controllers perform well at broad working points and in non-linear systems, but their correctness depends on the membership functions and fuzzy rule bases [16]. Learning-based approaches that are simple to incorporate into various systems depend on the calibre of the training data [17]. According to the literature, master-slave controllers have also performed well in the LFC objectives [7,18].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Because the input of RES‐based power generation units is reliant on weather conditions and has inherent uncertainties, this will impact their output power and, in turn, the dynamics of the system [17]. While the system load changes Δ P L are assumed in 50 seconds according to Figure 7a, the output power fluctuations of RES‐based units (Δ P WTG and Δ P DSPG ) are also considered according to Figure 7b.…”

Section: Simulation and Numerical Studymentioning

confidence: 99%

TFODn‐FOPI multi‐stage controller design to maintain an islanded microgrid load‐frequency balance considering responsive loads support

Shayeghi

Rahnama

Bizon

2023

IET Generation Trans & Dist

Self Cite

View full text Add to dashboard Cite

Modern electrical power system design will increase renewable energy sources (RES) dominance. Rotating masses, the main source of inertia in power systems, have been greatly decreased in renewable energy producing systems. Thus, load–frequency equilibrium is an important indicator of these systems' performance and safety. This work introduces a fractional‐order (FO) operator‐based cascade control structure for islanded microgrid (μG) load‐frequency control (LFC). The structure utilizes a tilt–FO derivative with filter (TFODn) in the first level to reduce noise. The second level implements the proportional integral (PI) controller's FO form (FOPI), making it a tilt–FO derivative with a filter cascaded to the FOPI controller (TOFDn‐FOPI). The optimal controller parameters for quick dynamic responses with low frequency fluctuation are determined using a unique cost function and prairie dog optimization (PDO) algorithm. The LFC control loops have frequency deviation‐based responsive loads (RL). Control signal delays, RES output changes, parameter uncertainties, and cyber vandalism are examined. Laboratory‐scale tests also assessed the controller's practicality. The proposed controller outperforms standard and FO type proportional integral derivative (PID) and PD‐PI controllers. The TFODn‐FOPI controller is suitable for complicated closed‐loop systems like islanded μGs due to its faster error clearing, reduced RL capacity, and superior time and frequency domain indicators.

show abstract

“…In order to obtain a more precise control of the voltage u dc , we can use more complex control algorithms of the adaptive [16], robust [17,18], and predictive [19] types, but also intelligent control algorithms, such as fuzzy [20], neuro-fuzzy [21], genetics [22], particle swarm optimization (PSO) [23], and reinforcement learning [24].…”

Section: Introductionmentioning

confidence: 99%

Fractional-Order Control of Grid-Connected Photovoltaic System Based on Synergetic and Sliding Mode Controllers

Nicola¹,

Nicola

2021

Energies

View full text Add to dashboard Cite

Starting with the problem of connecting the photovoltaic (PV) system to the main grid, this article presents the control of a grid-connected PV system using fractional-order (FO) sliding mode control (SMC) and FO-synergetic controllers. The article presents the mathematical model of a PV system connected to the main grid together with the chain of intermediate elements and their control systems. To obtain a control system with superior performance, the robustness and superior performance of an SMC-type controller for the control of the udc voltage in the DC intermediate circuit are combined with the advantages provided by the flexibility of using synergetic control for the control of currents id and iq. In addition, these control techniques are suitable for the control of nonlinear systems, and it is not necessary to linearize the controlled system around a static operating point; thus, the control system achieved is robust to parametric variations and provides the required static and dynamic performance. Further, by approaching the synthesis of these controllers using the fractional calculus for integration operators and differentiation operators, this article proposes a control system based on an FO-SMC controller combined with FO-synergetic controllers. The validation of the synthesis of the proposed control system is achieved through numerical simulations performed in Matlab/Simulink and by comparing it with a benchmark for the control of a grid-connected PV system implemented in Matlab/Simulink. Superior results of the proposed control system are obtained compared to other types of control algorithms.

show abstract

Assessing the Use of Reinforcement Learning for Integrated Voltage/Frequency Control in AC Microgrids

Cited by 16 publications

References 59 publications

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

Reinforcement Learning for Selective Key Applications in Power Systems: Recent Advances and Future Challenges

TFODn‐FOPI multi‐stage controller design to maintain an islanded microgrid load‐frequency balance considering responsive loads support

Fractional-Order Control of Grid-Connected Photovoltaic System Based on Synergetic and Sliding Mode Controllers

Contact Info

Product

Resources

About