Wind farm layout optimization using adaptive equilibrium optimizer

The layout optimization of wind turbines seeks to improve wind power conversion efficiency by minimizing the wake effect in wind farm. However, the existing optimization methods cannot provide a layout with high output power due to their inability to weaken the energy losses caused by the wake effec...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2024, Vol.80 (11), p.15245-15291
Main Authors: Zhong, Keyu, Xiao, Fen, Gao, Xieping
Format: Article
Language:English
Subjects:
Compilers
Computer Science
Energy conversion efficiency
Equilibrium
Heuristic methods
Interpreters
Layouts
Optimization
Perturbation
Processor Architectures
Programming Languages
Turbines
Wind effects
Wind farms
Wind power
Wind speed
Wind turbines
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The layout optimization of wind turbines seeks to improve wind power conversion efficiency by minimizing the wake effect in wind farm. However, the existing optimization methods cannot provide a layout with high output power due to their inability to weaken the energy losses caused by the wake effect between turbines. In this paper, an equilibrium optimizer with local perturbation and adaptive escape strategies, termed adaptive equilibrium optimizer (AEO), is proposed to tackle the wind farm layout optimization problem (WFLOP). To be specific, the worst turbines in the layout are re-located to better locations to reduce wind losses by enhancing the exploitation capacity of AEO with a local perturbation strategy. Then, an adaptive escape strategy supports the particles to get out of the local optimum and to search toward more promising areas, which facilitates the adjustment of the layout to reduce the wake effect. Besides, an adaptive repair operator adaptively reconfigures infeasible layouts to augment the proportion of feasible solutions in the population; thus, AEO can sufficiently explore the layout space to optimize the output power of wind farms. Twelve prohibited area constraints, three turbine scales, and three wind farm sizes are utilized to evaluate the performance of AEO in two cases with various wind speeds and directions. The experimental results demonstrate that the AEO performs excellently in terms of efficiency, robustness, and generalization for the layout optimization of turbines with different constraints, scales, and wind farm sizes in comparison with the state-of-the-art metaheuristics and other methods reported in the literature.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-024-05986-1