The probability distribution of wind speeds is a mathematical function describing the range and relative frequency of wind speeds at a particular location . In other word , the behavior of wind velocity at a given site can be specified as a probability distribution function. The accuracy of design wind estimation depends on the choice of an appropriate probability distribution model (PDM) and parameter estimation techniques. Generally, parameters for PDMs are estimated with the method of moments(MOM), probability weighted moments(PWM), and maximum likelihood (ML). In this work , we tried to estimate the parameters of PDMs for wind speed data using a recently developed meta-heuristic approach known as a harmony search (HS) that is a phenomenon-mimicking algorithm. The performance of the HS is compared to the genetic algorithm (GA) and conventional method (i.e.,ML) via simulation and case study.

• Nima Ghazijahani(Dept. of Civil Engr., ERI, Gyeongsang National University)
• Sukmin Yoon(Dept. of Civil Engr., ERI, Gyeongsang National University)
• Taesam Lee(Dept. of Civil Engr., ERI, Gyeongsang National University) Corresponding author