Wind Farm Layout Optimization: Genetic Algorithms, Machine Learning, and Bibliometric Insights
Asfour,, Rawan
Asfour,, Rawan
Type
Supervisor
Subject
Date
2026-03-01
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
The optimization of wind farm layouts (WFLO) is pivotal in maximizing energy production while reducing operational costs and environmental impact. This chapter presents a comprehensive framework that investigates genetic algorithms (GA) and machine learning (ML) techniques for WFLO. A parametric GA-based simulation explores the influence of key parameters population size, hub height, surface roughness, and cost models on layout efficiency and power output. To enrich this computational foundation, a bibliometric analysiscovering 2015–2024 was conducted using cleaned and merged data from Scopus and Web of Science, involving 483 unique documents. The analysis classifies WFLO research into major optimization categories such as GA, ML, PSO, and hybrid techniques, and reveals an increasing reliance on data-driven models and hybrid frameworks. A keyword heatmap confirms the growing prominence of ML algorithms like ANN, SVM, and Random Forest in WFLO. The results highlight the evolution of optimization strategies, the synergy between GA and ML, and the emergence of intelligent layout designs that combine predictive accuracy with computational efficiency.
Department
Publisher
Sponsor
None