Please wait a minute...
Front. Inform. Technol. Electron. Eng.  2013, Vol. 14 Issue (11): 845-858    DOI: 10.1631/jzus.C1300109
    
A mixture of HMM, GA, and Elman network for load prediction in cloud-oriented data centers
Da-yu Xu, Shan-lin Yang, Ren-ping Liu
MOE Key Laboratory of Process Optimization and Intelligent Decision-Making, Hefei University of Technology, Hefei 230009, China; Information and Communication Technologies Centre, CSIRO, Sydney 2122, Australia
Download:   PDF(0KB)
Export: BibTeX | EndNote (RIS)      

Abstract  The rapid growth of computational power demand from scientific, business, and Web applications has led to the emergence of cloud-oriented data centers. These centers use pay-as-you-go execution environments that scale transparently to the user. Load prediction is a significant cost-optimal resource allocation and energy saving approach for a cloud computing environment. Traditional linear or nonlinear prediction models that forecast future load directly from historical information appear less effective. Load classification before prediction is necessary to improve prediction accuracy. In this paper, a novel approach is proposed to forecast the future load for cloud-oriented data centers. First, a hidden Markov model (HMM) based data clustering method is adopted to classify the cloud load. The Bayesian information criterion and Akaike information criterion are employed to automatically determine the optimal HMM model size and cluster numbers. Trained HMMs are then used to identify the most appropriate cluster that possesses the maximum likelihood for current load. With the data from this cluster, a genetic algorithm optimized Elman network is used to forecast future load. Experimental results show that our algorithm outperforms other approaches reported in previous works.

Key wordsCloud computing      Load prediction      Hidden Markov model      Genetic algorithm      Elman network     
Received: 25 April 2013      Published: 06 November 2013
CLC:  TP391  
Cite this article:

Da-yu Xu, Shan-lin Yang, Ren-ping Liu. A mixture of HMM, GA, and Elman network for load prediction in cloud-oriented data centers. Front. Inform. Technol. Electron. Eng., 2013, 14(11): 845-858.

URL:

http://www.zjujournals.com/xueshu/fitee/10.1631/jzus.C1300109     OR     http://www.zjujournals.com/xueshu/fitee/Y2013/V14/I11/845


A mixture of HMM, GA, and Elman network for load prediction in cloud-oriented data centers

The rapid growth of computational power demand from scientific, business, and Web applications has led to the emergence of cloud-oriented data centers. These centers use pay-as-you-go execution environments that scale transparently to the user. Load prediction is a significant cost-optimal resource allocation and energy saving approach for a cloud computing environment. Traditional linear or nonlinear prediction models that forecast future load directly from historical information appear less effective. Load classification before prediction is necessary to improve prediction accuracy. In this paper, a novel approach is proposed to forecast the future load for cloud-oriented data centers. First, a hidden Markov model (HMM) based data clustering method is adopted to classify the cloud load. The Bayesian information criterion and Akaike information criterion are employed to automatically determine the optimal HMM model size and cluster numbers. Trained HMMs are then used to identify the most appropriate cluster that possesses the maximum likelihood for current load. With the data from this cluster, a genetic algorithm optimized Elman network is used to forecast future load. Experimental results show that our algorithm outperforms other approaches reported in previous works.

关键词: Cloud computing,  Load prediction,  Hidden Markov model,  Genetic algorithm,  Elman network 
[1] Muhammad Asif Zahoor Raja, Iftikhar Ahmad, Imtiaz Khan, Muhammed Ibrahem Syam, Abdul Majid Wazwaz. Neuro-heuristic computational intelligence for solving nonlinear pantograph systems[J]. Front. Inform. Technol. Electron. Eng., 2017, 18(4): 464-484.
[2] Gang Xiong, Yu-xiang Hu, Le Tian, Ju-long Lan, Jun-fei Li, Qiao Zhou. A virtual service placement approach based on improved quantum genetic algorithm[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(7): 661-671.
[3] Aftab Ahmed Chandio, Nikos Tziritas, Fan Zhang, Ling Yin, Cheng-Zhong Xu. Towards adaptable and tunable cloud-based map-matching strategy for GPS trajectories[J]. Front. Inform. Technol. Electron. Eng., 2016, 17(12): 1305-1319.
[4] Hong-wu Lv, Jun-yu Lin, Hui-qiang Wang, Guang-sheng Feng, Mo Zhou. Analyzing the service availability of mobile cloud computing systems by fluid-flow approximation[J]. Front. Inform. Technol. Electron. Eng., 2015, 16(7): 553-567.
[5] Han Qi, Muhammad Shiraz, Jie-yao Liu, Abdullah Gani, Zulkanain ABDUL Rahman, Torki A. Altameem. Data center network architecture in cloud computing: review, taxonomy, and open research issues[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(9): 776-793.
[6] Ya-tao Zhang, Cheng-yu Liu, Shou-shui Wei, Chang-zhi Wei, Fei-fei Liu. ECG quality assessment based on a kernel support vector machine and genetic algorithm with a feature matrix[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(7): 564-573.
[7] Hamid Tabatabaee, Mohammad Reza Akbarzadeh-T, Naser Pariz. Dynamic task scheduling modeling in unstructured heterogeneous multiprocessor systems[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(6): 423-434.
[8] Guangdong Tian, Hua Ke, Xiaowei Chen. Fuzzy cost-profit tradeoff model for locating a vehicle inspection station considering regional constraints[J]. Front. Inform. Technol. Electron. Eng., 2014, 15(12): 1138-1146.
[9] Ozoemena Anthony Ani, He Xu, Yi-ping Shen, Shao-gang Liu, Kai Xue. Modeling and multiobjective optimization of traction performance for autonomous wheeled mobile robot in rough terrain[J]. Front. Inform. Technol. Electron. Eng., 2013, 14(1): 11-29.
[10] Ommolbanin Yousefi, Mirbahadorgholi Aryanezhad, Seyed Jafar Sadjadi, Arash Shahin. Developing a multi-objective, multi-item inventory model and three algorithms for its solution[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(8): 601-612.
[11] Lei He, Chang-fu Zong, Chang Wang. Driving intention recognition and behaviour prediction based on a double-layer hidden Markov model[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(3): 208-217.
[12] Hossein Ghaffarian, Mohsen Soryani, Mahmood Fathy. Planning VANET infrastructures to improve safety awareness in curved roads[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(12): 918-928.
[13] Xiao-hong Tan, Rui-min Shen, Yan Wang. Personalized course generation and evolution based on genetic algorithms[J]. Front. Inform. Technol. Electron. Eng., 2012, 13(12): 909-917.
[14] Zheng-min Kong, Liang Zhong, Guang-xi Zhu, Li Ding. Differential multiuser detection using a novel genetic algorithm for ultra-wideband systems in lognormal fading channel[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(9): 754-765.
[15] Yuan-hong Shen, Xiao-hu Yang. A self-optimizing QoS-aware service composition approach in a context sensitive environment[J]. Front. Inform. Technol. Electron. Eng., 2011, 12(3): 221-238.