A Comparative Analysis of Genetic Algorithm and Moth Flame Optimization Algorithm for Multi-Criteria Design Optimization of Wind Turbine Generator Bearing

As global climate change is affecting the meteorological conditions and instigating massive social suffering, the emanation of greenhouse gases is necessitated to be restricted through effective usage of renewable sources of energy as per the directions of the Paris treaty of 2015. Wind energy, a renowned renewable energy resource, is enabling countries to generate power in a relatively cost-effective way and causes a remarkably nominal carbon trail. A considerable extent of the functioning lifespan of wind turbines remains unexploited every year all over the globe because of mechanical malfunctions. The existing research strives to evaluate the relative competency of the Genetic Algorithm (GA) and the Moth Flame Optimization Algorithm (MFOA) for optimizing the wind turbine generator bearing design through enhancement of its static and dynamic load-bearing capacities. The design solutions attained by both of the algorithms validate a noteworthy growth of the optimization objectives when contrasted with the technical catalog standards. Moreover, the relative evaluation demonstrates the superior aptness of multi-criteria GA on multi-criteria MFOA for finding improved design resolutions