Reinforcement learning to maximize wind turbine energy generation

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 249, P. 123502 - 123502

Published: Feb. 19, 2024

Language: Английский

---

Potentiometry of wind, solar and geothermal energy resources and their future perspectives in Iran

Environment Development and Sustainability, Journal Year: 2024, Volume and Issue: unknown

Published: March 9, 2024

Language: Английский

---

A Comprehensive Review of Machine Learning Models for Optimizing Wind Power Processes

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 3758 - 3758

Published: March 29, 2025

Wind energy represents a solution for reducing environmental impact. For this reason, research studies the elements that propose optimizing wind production through intelligent solutions. Although there are address optimization of turbine performance or other indirectly related factors in production, remains topic insufficiently explored and synthesized literature. This how machine learning (ML) techniques can be applied to optimize production. aims study systematic applications ML identify analyze key stages optimized Through research, case highlighted by which methods proposed directly target issue power process turbines. From total 1049 articles obtained from Web Science database, most studied models context artificial neural networks, with 478 papers identified. Additionally, literature identifies 224 have random forest 114 incorporated gradient boosting about power. Among these, 60 specifically addressed aspect allows identification gaps The notes previous focused on forecasting, fault detection, efficiency. existing addresses indirect component performance. Thus, paper current discusses algorithms processes, future directions increasing efficiency turbines integrated predictive methods.

Language: Английский

---

A grouping strategy for reinforcement learning-based collective yaw control of wind farms

Theoretical and Applied Mechanics Letters, Journal Year: 2024, Volume and Issue: 14(1), P. 100491 - 100491

Published: Jan. 1, 2024

Reinforcement learning (RL) algorithms are expected to become the next generation of wind farm control methods. However, as farms continue grow in size, computational complexity collective will exponentially increase with growth action and state spaces, limiting its potential practical applications. In this Letter, we employ a RL-based approach multi-agent deep deterministic policy gradient optimize yaw manoeuvre grouped turbines farms. To reduce complexity, according strength wake interaction. Meanwhile, improve efficiency, each subgroup is treated whole controlled by single agent. Optimized results show that proposed method can not only power production but also significantly efficiency.

Language: Английский

---

Dynamic wake steering control for maximizing wind farm power based on a physics-guided neural network dynamic wake model

Physics of Fluids, Journal Year: 2024, Volume and Issue: 36(8)

Published: Aug. 1, 2024

Wake effect is a significant factor contributing to power loss in wind farms. Studies have shown that wake steering control can mitigate this loss. Currently, farm strategies primarily utilize fixed yaw due limitations the accuracy and efficiency of dynamic models. However, fails fully exploit improvement potential control. Therefore, study, we first propose model for farms based on physics-guided neural network (PGNN) approach. This predict flow field within real time using instantaneous inflow speed turbine operational states. Then, by employing PGNN as predictive model, strategy method proposed. To quantify advantages proposed strategy, both are tested with 3 × 2 layout. Results from large eddy simulations demonstrate increases output 11.51% compared 6.56% increase achieved

Language: Английский

---

Large eddy simulation and linear stability analysis of active sway control for wind turbine array wake

Physics of Fluids, Journal Year: 2024, Volume and Issue: 36(7)

Published: July 1, 2024

The convective instability of wind turbine wakes allows specific upstream forcing to amplify downstream, leading increased wake meandering and replenishment, thereby providing a theoretical basis for active control. In this study, the sway control—a strategy previously proven enhance recovery at single level—is analyzed array level. similarity differences between individual are using large eddy simulations linear stability analysis, considering both uniform turbulent inflow conditions. For cases with inflow, reveal significant motion in induced by control amplitude 1% rotor diameter, consistent previous studies standalone wakes. Nevertheless, sensitive frequency extends down St = 0.125 below limit > 0.2 wake, optimal becomes suboptimal array. Linear analysis reveals underlying mechanism shift as changes shear-layer due overlap downstream is capable provide fast estimation frequencies. When turbulence intensity increases, gain reduced, underscoring importance low-turbulence environment successfully implementing reduction response captured if base flow accounts faster expansion caused turbulence.

Language: Английский

---

Data-driven wind farm flow control and challenges towards field implementation: A review

Renewable and Sustainable Energy Reviews, Journal Year: 2025, Volume and Issue: 216, P. 115605 - 115605

Published: March 31, 2025

Language: Английский

---

Wind Farm Design with 15 MW Floating Offshore Wind Turbines in Typhoon Regions

Journal of Marine Science and Engineering, Journal Year: 2025, Volume and Issue: 13(4), P. 687 - 687

Published: March 28, 2025

Floating Offshore Wind Turbines (FOWTs) are gaining traction as a solution for harnessing wind energy in deepwater regions where traditional fixed-bottom turbines may not be viable due to water depth. This paper investigates the feasibility and optimization of floating farm tropical cyclone (typhoon) region, using IEA 15 MW turbine semi-submersible floaters. Because extreme environment, FOWT’s mooring system requires nine catenary chains 3 × pattern, which has large footprint. One challenge design is fitting FOWTs limited area minimizing wake effects. research compares linear layout an offset grid layout, focusing on effects spacing dynamics. The results show that while maintains optimal power generation without loss, although resulting 2% offers greater spatial efficiency larger-scale projects. findings highlight importance balancing with optimization, particularly offshore farms. study explores use Gauss–Curl hybrid model modeling, methodology employed provides insights into FOWT placement arrangement. result concludes containing twelve (12) units can achieve 7.0 MW/km2 density required by regulatory government agency. It proves technical congested systems region.

Language: Английский

---

Multiple aerial/ground vehicles coordinated spraying using reinforcement learning

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 151, P. 110686 - 110686

Published: April 8, 2025

Language: Английский

---

Investigations into deep Reinforcement Learning for wind farm set-point optimisation

Expert Systems with Applications, Journal Year: 2025, Volume and Issue: unknown, P. 127627 - 127627

Published: April 1, 2025

Language: Английский

---