A Resource Demand Prediction Method Based on EEMD in Cloud Computing

Abstract A large number of resources are integrated into a data center to provide various resource services in cloud computing. A major challenge is how to provide resources timely and accurately to satisfy users’ demands. However, users’ resource demands change constantly and sometimes fluctuate very strong. The resource provision may be not performed in time. And even, sometimes the active physical resources may be too insufficient to satisfy users’ demands because some of them are shut down in order to reduce energy. So it is important to provide a proactive resource provision to guarantee good users’ experiences in cloud computing. The key is to predict the future resource demands accurately to support resource provision in advance. In this paper, we propose a resource demand prediction method EEMD-ARIMA based on ensemble empirical mode decomposition (EEMD) in cloud computing. This method decomposes the non-stationary users’ resource demands into a plurality of intrinsic mode function components (IMFs) and residual component (RES) through EEMD method to improve the prediction accuracy. The experimental results show that our method has a higher prediction accuracy compared with the existing ARIMA prediction model in the short-term prediction of cloud resource demands.

[1]  Bernd Freisleben,et al.  Cross-Correlation Prediction of Resource Demand for Virtual Machine Resource Allocation in Clouds , 2014, 2014 Sixth International Conference on Computational Intelligence, Communication Systems and Networks.

[2]  Zhijia Chen,et al.  Self-Adaptive Prediction of Cloud Resource Demands Using Ensemble Model and Subtractive-Fuzzy Clustering Based Fuzzy Neural Network , 2015, Comput. Intell. Neurosci..

[3]  Aniruddha S. Gokhale,et al.  Efficient Autoscaling in the Cloud Using Predictive Models for Workload Forecasting , 2011, 2011 IEEE 4th International Conference on Cloud Computing.

[4]  Nanjangud C. Narendra,et al.  Resource Demand Prediction in Multi-Tenant Service Clouds , 2013, 2013 IEEE International Conference on Cloud Computing in Emerging Markets (CCEM).

[5]  N. Huang,et al.  The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis , 1998, Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences.

[6]  Xi Chen,et al.  APU Degradation Prediction Based on EEMD and Gaussian Process Regression , 2017, 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC).

[7]  Carlos A. Varela,et al.  Accurate Resource Prediction for Hybrid IaaS Clouds Using Workload-Tailored Elastic Compute Units , 2013, 2013 IEEE/ACM 6th International Conference on Utility and Cloud Computing.

[8]  Christoph Hochreiner,et al.  Predicting Cloud Resource Utilization , 2016, 2016 IEEE/ACM 9th International Conference on Utility and Cloud Computing (UCC).

[9]  Kanchana Rajaram,et al.  Utilization based prediction model for resource provisioning , 2017, 2017 International Conference on Computer, Communication and Signal Processing (ICCCSP).

[10]  Mi Hai.  Resource On-Demand Reconfiguration Method for Virtualized Data Centers , 2011 .

[11]  Gang Yin,et al.  Resource On-Demand Reconfiguration Method for Virtualized Data Centers: Resource On-Demand Reconfiguration Method for Virtualized Data Centers , 2011 .

[12]  Norden E. Huang,et al.  Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method , 2009, Adv. Data Sci. Adapt. Anal..

[13]  Tao Li,et al.  ASAP: A Self-Adaptive Prediction System for Instant Cloud Resource Demand Provisioning , 2011, 2011 IEEE 11th International Conference on Data Mining.

[14]  Samuel Ajila,et al.  Predicting cloud resource provisioning using machine learning techniques , 2013, 2013 26th IEEE Canadian Conference on Electrical and Computer Engineering (CCECE).

[15]  Feng Xia,et al.  Resource requests prediction in the cloud computing environment with a deep belief network , 2017, Softw. Pract. Exp..

[16]  Haiying Shen,et al.  Towards resource-efficient cloud systems: Avoiding over-provisioning in demand-prediction based resource provisioning , 2016, 2016 IEEE International Conference on Big Data (Big Data).

[17]  Li Zhang,et al.  Short-Term Wind Power Interval Forecasting Based on an EEMD-RT-RVM Model , 2016 .

[18]  Markus Ullrich,et al.  Current Challenges and Approaches for Resource Demand Estimation in the Cloud , 2013, 2013 International Conference on Cloud Computing and Big Data.

[19]  Zhinong Wei,et al.  Short-term wind speed forecasting based on an EEMD-CAPSO-RVM model , 2016, 2016 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC).