Wind Speed Clustering Using Linkage-Ward Method: A Case Study of Khaaf, Iran

Abstract

The use of renewable energy for providing electricity is growing rapidly. Among others, windpower is one of the most appealing energy sources. The wind speed has direct impact on thegenerated wind power and this causes the necessity of wind speed forecasting. For better powersystem planning and operation, we need to forecast the available wind power. Wind power isvolatile and intermittent over the year. For getting better insight and a tractable optimizationproblem for different decision making problems in presence of wind power generation, it isrequired to cluster the possible wind power generation scenarios. This article presentsprobabilistic wind speed clustering prototype for wind speed data of Khaaf, Iran. This region isknown as one of the high potential wind sites in Iran and several wind farm projects is plannedin this area. The average speed of wind for a ten-minute period measured at height of 40m overa year (2008) is used for clustering. From the result of this research, the most appropriateprobabilistic model for the wind speed can be obtained.