A modified grey wolf optimizer for improving wind plant energy production

Abstract

<span>The main problem of existing wind plant nowadays is that the optimum controller of single turbine degrades the total energy production of wind farm when it is located in a large wind plant. This is owing to its greedy control policy that can not cope with turbulence effect between turbines. This paper proposes a Modified Grey Wolf Optimizer (M-GWO) to improvise the controller parameter of an array of turbines such that the total energy production of wind plant is increased. The modification employed to the original GWO is in terms of the updated mechanism. This modification is expected to improve the variation of exploration and exploitation rates while avoiding the premature convergence condition. The effectiveness of the M-GWO is applied to maximize energy production of a row of ten turbines. The model of the wind plant is derived based on the real Horns Rev wind plant in Denmark. The statistical performance analysis shows that the M-GWO provides the highest total energy production as compared to the standard GWO, Particle Swarm Optimization (PSO) and Safe Experimentation Dynamics (SED) methods.</span>

Parameters estimation of solar photovoltaic module using camel behavior search algorithm

“…Various optimization approaches have been applied in the recent past. In these algorithms the estimation problem is converted into optimization problem, these including genetic algorithm [23,24], particle swarm optimization [25,26], wolf optimization [27], differential evolution [28] and artificial bee colony [29] as well as other types of optimization.…”

Optimal tuning of a wind plant energy production based on improved grey wolf optimizer

“…Alternatively, a grey wolf optimizer (GWO) [11], which is swarm-based inspired by social behavior of groups of animals (grey wolves), has been successfully solved numerous types of real applications. For instance, improving wind plant production [12], solving optimal reactive power dispatch problem [13], automatic generation control of interconnected power system [14], design for a photovoltaic (PV) [15,16], vehicle engine [17], unmanned aerial vehicle (UAV) [18], facial image [19], image segmentation [20], gridconnected permanent-magnet synchronous generator [21], satellite image segmentation [22], hybrid renewable energy system PV-diesel generator-battery [23], and liquid slosh system identification [24]. GWO algorithm is inspired by the social hierarchy of grey wolves that divided into four groups, which are alphas, beta, delta and omega.…”

“…The performance of the proposed method is analyzed statistically in terms of mean, best, worst and standard deviation of the wind plant total energy production. Furthermore, the results are compared with the previously published modified GWO [12] and the original GWO approaches.…”

Short-term wind speed forecasting system using deep learning for wind turbine applications

“…In addition, compared to machine learning, deep learning requires stronger processors and larger training data for its results. Compared to ANN, deep learning offers more layers working [31][32][33][34][35][36][37].…”