Data-driven control based on marine predators algorithm for optimal tuning of the wind plant

Abstract

The main challenge in controlling the wind plant nowadays is a highly arduous effort in discovering the best controller parameters of the turbines due to the wake interaction effect. The aim of this paper is to develop the data-driven control based on marine predators algorithm (MPA) for fine-tuning the controller parameters of a single row of ten turbines in improving the wind plant power production according to the reference power. The real wind plant model from Denmark named Horns Rev is considered in this study. Effectiveness of the proposed method was particularly assessed according to the convergence curve and statistical analysis of the fitness function, and Wilcoxon's rank test. Comparative results alongside other existing metaheuristic-based algorithms further confirmed excellence of the proposed method through its superior performance against the slime mould algorithm (SMA), multi-verse optimizer (MVO), sine-cosine algorithm (SCA), grey wolf optimizer (GWO), and safe experimentation dynamics (SED) algorithm.