Assefa, AbebayehuZerfie, Dereje2018-07-312023-11-182018-07-312023-11-182016-04http://etd.aau.edu.et/handle/12345678/10613Presently there is a growing energy demand usually covered by energy sources such as fossil fuel, coal and natural gas, which have been the basis for growth and development of the people since the beginning of 20th century. Wind is an intermittent generation resource and weather changes can cause large and rapid changes in output, system operators will need accurate and robust wind energy forecasting systems in the future. Main defects in wind turbine are the emergence of an unanticipated outcome which are not considered during the design of the blade. The turbine is generally described by wind speed inputs and power output which represent the internal state of the wind turbine. Turbine disturbances can always exist in small or large scale depending on the environment of the system. The disturbances may be results of wrong measurement (unnecessary input insertion), or it can be the result of unnecessary (not optimal) power output, instrumental defect. Using a mathematical model of non-linear systems such as model to analyze different possible disturbances by wind speed on the wind turbine power output with one interval for each parent in a given time. In each generation, the fitness of every individual in the power output is evaluated, multiple individuals are stochastically selected from the current power output (based on their fitness), and modified (recombined and possibly randomly mutated) to form a new power output. The new power output is then used in the next iteration of the algorithm. The aim of this paper is to design a genetic algorithm based system state approximation mechanism for the wind turbine for which disturbances are assumed to be random defects, whose values are in a known limited intervals. Genetic algorithm approach is a proficient approach for modeling the power systems that inspired their design and proposes to find out best solutions of the problems with any mathematical equations.enStream ThermalThesis