主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

Chinese Journal of Management Science ›› 2015, Vol. 23 ›› Issue (5): 56-64.doi: 10.16381/j.cnki.issn1003-207x.2015.05.008

• Articles • Previous Articles     Next Articles

Research on Generalized Fuzzy Soft Sets Theory based Combined Model for Demanded Cloud Computing Resource Prediction

XU Da-yu1,2, YANG Shan-lin2, LUO He2   

  1. 1. Zhejiang A&F University, Zhejiang Provincial Key Laboratory of Forestry Intelligent Monitoring and Information Technology Research, Hangzhou 311300, China;
    2. HeFei University of Technology, Key Laboratory of Process Optimization and Intelligent Decision-making, Ministry of Education, HeFei 230009, China
  • Received:2012-11-20 Revised:2013-06-17 Online:2015-05-20 Published:2015-05-20

Abstract: In order to realize high scalability, flexibility and cost-effectiveness, cloud computing platforms need to be able to quickly plan and provision resources. To this end, it calls for mechanisms to predict demanded resource effectively. Therefore, resource prediction is a crucial issue for efficient resource utilization in dynamic cloud computing environment. In this paper, the basic concept of generalized fuzzy soft sets is introduced, and a novel angle cosine is proposed based similarity measurement of generalized fuzzy soft sets. Then the similarity measurement result and the prediction accuracy from Adaptive Neuro-Fuzzy Inference System and Seasonal ARIMA model are adopted to obtain the weights of combined prediction model. On this basis,the generalized fuzzy soft sets theory based on the combination of forecasting model GFSS-ANFIS/SARIMA is constrncted. Finally, this model is explorted to predict the demanded resource in cloud computing. The experimental results show that the proposed model can significantly improve the prediction accuracy with high prediction performance. Efficient decision support for resource scheduling and allocation in cloud computing can be provided by the proposed method.

Key words: cloud computing, generalized fuzzy soft sets, combined prediction, similarity measurement, adaptive neuro-fuzzy inference system

CLC Number: