A power generation accumulation-based adaptive chaotic differential evolution algorithm for wind turbine placement problems

The focus on clean energy has significantly increased in recent years, emphasizing eco-friendly sources like solar, wind, hydropower, geothermal, and biomass energy. Among these, wind energy, utilizing the kinetic energy from the wind, is distinguished by its economic competitiveness and environmental benefits, offering scalability and minimal operational emissions. It requires strategic turbine placement within wind farms to maximize energy conversion efficiency, a complex task involving the analysis of wind patterns, turbine spacing, and technology. This task has traditionally been tackled by meta-heuristic algorithms, which face challenges in balancing local exploitation with global exploration and integrating problem-specific knowledge into the search mechanism. To address these challenges, an innovative power generation accumulation-based adaptive chaotic differential evolution algorithm (ACDE) is proposed, enhancing the conventional differential evolution approach with an adaptive chaotic local search and a wind turbine adjustment strategy based on tournament selection. This strategy aimed to prioritize energy-efficient turbine positions and improve population diversity, thereby overcoming the limitations of existing meta-heuristic algorithms. Comprehensive experiments with varying wind rose configurations demonstrated ACDE's superior performance in energy conversion efficiency, showcasing its potential in optimizing wind turbine placement for enhanced clean energy production. The wind farm layout optimization competition hosted by the Genetic and Evolutionary Computation Conference provided a comprehensive set of complex wind farm layouts. This dataset was utilized to further validate the performance of the algorithms. The results unequivocally demonstrate the superiority of ACDE when tackling complex optimization problems.