A Review of Wind Clustering Methods Based on the Wind Speed and Trend in Malaysia

Abstract

Wind mapping has played a significant role in the selection of wind harvesting areas and engineering objectives. This research aims to find the best clustering method to cluster the wind speed of Malaysia. The wind speed trend of Malaysia is affected by two major monsoons: the southwest and the northeast monsoon. The research found multiple, worldwide studies using various methods to accomplish the clustering of wind speed in multiple wind conditions. The methods used are the k-means method, Ward’s method, hierarchical clustering, trend-based time series data clustering, and Anderberg hierarchical clustering. The clustering methods commonly used by the researchers are the k-means method and Ward’s method. The k-means method has been a popular choice in the clustering of wind speed. Each research study has its objectives and variables to deal with. Consequently, the variables play a significant role in deciding which method is to be used in the studies. The k-means method shortened the clustering time. However, the calculation’s relative error was higher than that of Ward’s method. Therefore, in terms of accuracy, Ward’s method was chosen because of its acceptance of multiple variables, its accuracy, and its acceptable calculation time. The method used in the research plays an important role in the result obtained. There are various aspects that the researcher needs to focus on to decide the best method to be used in predicting the result.