Journal of Digital Information Management Dulyawit Prangchumpol, Peraphon Sophatsathit, ChidchanokLursinsap, PanjaiTantasanawong 13 5 2015 http://dline.info/fpaper/jdim/v13i5/v13i5_11.pdf This paper proposes a practical and effective predicting model for resource allocation and usage for server. The approach rests on virtualization technique to simulate a heterogeneous virtual machine environment. The study is confined to management of number of CPUs and memory units being allocated on three servers to serve user's requests. The objective is fast response time to attain as high user satisfaction as possible. The algorithm employs exponential smoothing technique to analyze trend of data and the relationship among them. Assessment was compared with association rules and ARIMA. The findings reveal that the proposed technique yields more accurate prediction results than other predicting models, having the least MSE and acceptable system response time.