Abstract
Wind farm layout optimization (WFLO) has become a significant approach to enhancing the efficiency of wind energy utilization. However, load also represents a critical factor that must be considered during optimization. To enhance power generation while controlling loads within limitations, an innovative load-constrained layout optimization method that employs a surrogate model based on artificial neural networks and genetic algorithms was proposed. This paper verified the accuracy of the surrogate model and then conducted layout optimizations on a single and a full wind condition case to assess the proposed method. The results indicated that the mean absolute percentage errors of load channels can meet the precision requirements for WFLO. A comparison of layout optimization results between the method proposed in this paper and the traditional method showed that in the single-wind-condition case, the method proposed in this paper reduced the maximum load by 5.64 % compared to the traditional method, with nearly identical power output; in the full-wind-condition case, the reduction of maximum load was 1.70 %, while only sacrificing the annual power generation by 0.10 %. This study provides a load-constrained WFLO method, promising to effectively ensure the lifespan of wind turbines while increasing power generation and offering significant engineering value.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call