A deep learning approach for VM workload prediction in the cloud

In order to manage the resources in cloud efficiently, ensure the performance of cloud services and reduce the power consumption, it is critical to predict the workload of virtual machines (VM) accurately. In this paper, a new approach for VM workload prediction based on deep learning was proposed. A deep learning prediction model was designed with a deep belief network (DBN) composed of multiple-layered restricted Boltzmann machines (RBMs) and a regression layer. The DBN is used to extract the high level features from all VMs workload data and the regression layer is used to predict the workload of the VMs in the future. With little prior knowledge, DBN could learn the features efficiently for the VM workload prediction in an unsupervised fashion. Experimental results show that the proposed approach improves the workload prediction performance compared with other widely used workload prediction approaches.

[1]  Bingsheng He,et al.  A Survey of Resource Management in Multi-Tier Web Applications , 2014, IEEE Communications Surveys & Tutorials.

[2]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[3]  Rajkumar Buyya,et al.  CloudSim: a toolkit for modeling and simulation of cloud computing environments and evaluation of resource provisioning algorithms , 2011, Softw. Pract. Exp..

[4]  Dimosthenis Kyriazis,et al.  Parametric Design and Performance Analysis of a Decoupled Service-Oriented Prediction Framework Based on Embedded Numerical Software , 2013, IEEE Transactions on Services Computing.

[5]  Zhen Xiao,et al.  Dynamic Resource Allocation Using Virtual Machines for Cloud Computing Environment , 2013, IEEE Transactions on Parallel and Distributed Systems.

[6]  Geoffrey E. Hinton,et al.  Exponential Family Harmoniums with an Application to Information Retrieval , 2004, NIPS.

[7]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[8]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[9]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[11]  Xifeng Yan,et al.  Workload characterization and prediction in the cloud: A multiple time series approach , 2012, 2012 IEEE Network Operations and Management Symposium.

[12]  Kevin Lee,et al.  Empirical prediction models for adaptive resource provisioning in the cloud , 2012, Future Gener. Comput. Syst..

[13]  Geoffrey E. Hinton,et al.  Application of Deep Belief Networks for Natural Language Understanding , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[14]  Rajkumar Buyya,et al.  Workload Prediction Using ARIMA Model and Its Impact on Cloud Applications’ QoS , 2015, IEEE Transactions on Cloud Computing.

[15]  Kunikazu Kobayashi,et al.  Time series forecasting using a deep belief network with restricted Boltzmann machines , 2014, Neurocomputing.

[16]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[17]  Albert Y. Zomaya,et al.  Trends and challenges in cloud datacenters , 2014, IEEE Cloud Computing.

[18]  Jie Xu,et al.  Analysis, Modeling and Simulation of Workload Patterns in a Large-Scale Utility Cloud , 2014, IEEE Transactions on Cloud Computing.

[19]  Yu Zhou,et al.  Multi-step-ahead host load prediction using autoencoder and echo state networks in cloud computing , 2015, The Journal of Supercomputing.