Estimation of Wind Speed Probability Distribution Parameters by Using Four Different Metaheuristic Algorithms

Authors : Okan ORAL, Murat İNCE, Batin Latif AYLAK, Mehmet Hakan ÖZDEMİR

Pages : 1342-1362

Doi:10.31202/ecjse.1135209

View : 23 | Download : 9

Publication Date : 2022-12-31

Article Type : Research Paper

Abstract :The inclusion of energy produced from renewable energy sources insert ignore into journalissuearticles values(RES); such as solar and wind energy into existing energy systems is important to reduce carbon emissions, air pollution and climate change, and to ensure sustainable development. However, the integration of RES into the energy system is quite difficult due to their highly uncertain and intermittent nature. In this study, considering three different probability density functions insert ignore into journalissuearticles values(PDFs); in total, the scale and shape parameters of the Weibull PDF, the scale parameter of the Rayleigh PDF, and the scale and shape parameters of the Gamma PDF were estimated for the wind speed data obtained from urban stations located in Istanbul by using the four different metaheuristic algorithms, namely Genetic Algorithm insert ignore into journalissuearticles values(GA);, Differential Evolution insert ignore into journalissuearticles values(DE);, Particle Swarm Optimization insert ignore into journalissuearticles values(PSO); and Grey Wolf Optimization insert ignore into journalissuearticles values(GWO); algorithms. Calculating the mean absolute error insert ignore into journalissuearticles values(MAE);, root mean squared error insert ignore into journalissuearticles values(RMSE);, and R2 values for each PDF at each station, the PDF that characterizes the wind speed probability distribution the best was identified.
Keywords : Rüzgâr hızı, yenilenebilir enerji, olasılık yoğunluk fonksiyonu, parametre tahmini, metasezgisel algoritma