A hybrid wavelet decomposer and GMDH-ELM ensemble model for Network function virtualization workload forecasting in cloud computing

Abstract Nowadays Network function virtualization (NFV) has drawn immense attention from many cloud providers because of its benefits. NFV enables networks to virtualize node functions such as firewalls, load balancers, and WAN accelerators, conventionally running on dedicated hardware, and instead implements them as virtual software components on standard servers, switches, and storages. In order to provide NFV resources and meet Service Level Agreement (SLA) conditions, minimize energy consumption and utilize physical resources efficiently, resource allocation in the cloud is an essential task. Since network traffic is changing rapidly, an optimized resource allocation strategy should consider resource auto-scaling property for NFV services. In order to scale cloud resources, we should forecast the NFV workload. Existing forecasting methods are providing poor results for highly volatile and fluctuating time series such as cloud workloads. Therefore, we propose a novel hybrid wavelet time series decomposer and GMDH-ELM ensemble method named Wavelet-GMDH-ELM (WGE) for NFV workload forecasting which predicts and ensembles workload in different time-frequency scales. We evaluate the WGE model with three real cloud workload traces to verify its prediction accuracy and compare it with state of the art methods. The results show the proposed method provides better average prediction accuracy. Especially it improves Mean Absolute Percentage Error (MAPE) at least 8% compared to the rival forecasting methods such as support vector regression (SVR) and Long short term memory (LSTM).

[1]  Xiaobo Zhang,et al.  A novel decomposition‐ensemble model for forecasting short‐term load‐time series with multiple seasonal patterns , 2018, Appl. Soft Comput..

[2]  Qiumin Li,et al.  The k-nearest neighbour-based GMDH prediction model and its applications , 2014, Int. J. Syst. Sci..

[3]  Raj Jain,et al.  Network virtualization and software defined networking for cloud computing: a survey , 2013, IEEE Communications Magazine.

[4]  Yusuf Yaslan,et al.  Empirical mode decomposition based denoising method with support vector regression for time series prediction: A case study for electricity load forecasting , 2017 .

[5]  B. Eswara Reddy,et al.  A moving-average filter based hybrid ARIMA-ANN model for forecasting time series data , 2014, Appl. Soft Comput..

[6]  Filip De Turck,et al.  Network Function Virtualization: State-of-the-Art and Research Challenges , 2015, IEEE Communications Surveys & Tutorials.

[7]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[8]  Ramin Yahyapour,et al.  Parallel Computer Workload Modeling with Markov Chains , 2004, JSSPP.

[9]  Warren Smith,et al.  Using Run-Time Predictions to Estimate Queue Wait Times and Improve Scheduler Performance , 1999, JSSPP.

[10]  J. Adamowski,et al.  Application of wavelet-artificial intelligence hybrid models for water quality prediction: a case study in Aji-Chay River, Iran , 2016, Stochastic Environmental Research and Risk Assessment.

[11]  Valter Rogério Messias,et al.  Efficient Resource Allocation for Web Applications Hosted in the Cloud by means of Weighted Multi-objective Linear Programming , 2015, WebMedia.

[12]  K. Uma Rao,et al.  Development of statistical time series models for solar power prediction , 2015 .

[13]  Yaonan Wang,et al.  Bidirectional Extreme Learning Machine for Regression Problem and Its Learning Effectiveness , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[14]  Jitendra Kumar,et al.  Workload prediction in cloud using artificial neural network and adaptive differential evolution , 2018, Future Gener. Comput. Syst..

[15]  Fatma A. Omara,et al.  Prediction mechanisms for monitoring state of cloud resources using Markov chain model , 2016, J. Parallel Distributed Comput..

[16]  Weijun Chen,et al.  Who is answering whom? Finding “Reply-To” relations in group chats with deep bidirectional LSTM networks , 2018, Cluster Computing.

[17]  Dianhui Wang,et al.  Extreme learning machines: a survey , 2011, Int. J. Mach. Learn. Cybern..

[18]  Majid Ahmadi,et al.  An efficient illumination invariant face recognition framework via illumination enhancement and DD-DTCWT filtering , 2013, Pattern Recognit..

[19]  Wenhong Tian,et al.  Minimizing total busy time in offline parallel scheduling with application to energy efficiency in cloud computing , 2015, Concurr. Comput. Pract. Exp..

[20]  Meina Song,et al.  Host load prediction in cloud based on classification methods , 2014 .

[21]  Yu Zhou,et al.  Host load prediction with long short-term memory in cloud computing , 2017, The Journal of Supercomputing.

[22]  Sheng Di,et al.  Google hostload prediction based on Bayesian model with optimized feature combination , 2014, J. Parallel Distributed Comput..

[23]  Wang Yanhong,et al.  A prediction method based on wavelet transform and multiple models fusion for chaotic time series , 2017 .

[24]  Rajashree Dash,et al.  Performance analysis of a higher order neural network with an improved shuffled frog leaping algorithm for currency exchange rate prediction , 2018, Appl. Soft Comput..

[25]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[26]  Hojjat Adeli,et al.  A new music-empirical wavelet transform methodology for time-frequency analysis of noisy nonlinear and non-stationary signals , 2015, Digit. Signal Process..

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

[28]  Cheng Wu,et al.  Semi-Supervised and Unsupervised Extreme Learning Machines , 2014, IEEE Transactions on Cybernetics.

[29]  Xiaoyi Jiang,et al.  GMDH-based hybrid model for container throughput forecasting: Selective combination forecasting in nonlinear subseries , 2018, Appl. Soft Comput..

[30]  Abdallah Shami,et al.  NFV: state of the art, challenges, and implementation in next generation mobile networks (vEPC) , 2014, IEEE Network.

[31]  Farschad Torabi,et al.  Modeling and optimization of dew-point evaporative coolers based on a developed GMDH-type neural network , 2017 .

[32]  Narasimhan Sundararajan,et al.  Fully complex extreme learning machine , 2005, Neurocomputing.

[33]  B. Dabir,et al.  Modeling gas/vapor viscosity of hydrocarbon fluids using a hybrid GMDH-type neural network system , 2017 .

[34]  Dror G. Feitelson,et al.  Heuristics for Resource Matching in Intel's Compute Farm , 2013, JSSPP.

[35]  Xinying Xu,et al.  Similarity measurement based on cloud models for time series prediction , 2016, 2016 Chinese Control and Decision Conference (CCDC).

[36]  Maryam Amiri,et al.  Survey on prediction models of applications for resources provisioning in cloud , 2017, J. Netw. Comput. Appl..

[37]  Li-Der Chou,et al.  A novel VM workload prediction using Grey Forecasting model in cloud data center , 2014, The International Conference on Information Networking 2014 (ICOIN2014).

[38]  Marcos José Santana,et al.  Combining time series prediction models using genetic algorithm to autoscaling Web applications hosted in the cloud infrastructure , 2015, Neural Computing and Applications.

[39]  Bir Bhanu,et al.  Image super-resolution by extreme learning machine , 2012, 2012 19th IEEE International Conference on Image Processing.

[40]  Sunilkumar S. Manvi,et al.  Virtual resource prediction in cloud environment: A Bayesian approach , 2016, J. Netw. Comput. Appl..

[41]  G. N. Pillai,et al.  Prediction of landslide displacement with controlling factors using extreme learning adaptive neuro-fuzzy inference system (ELANFIS) , 2017, Appl. Soft Comput..

[42]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[43]  Dhiya Al-Jumeily,et al.  Regularized dynamic self-organized neural network inspired by the immune algorithm for financial time series prediction , 2016, Neurocomputing.

[44]  Paulo Cortez,et al.  Global and decomposition evolutionary support vector machine approaches for time series forecasting , 2014, Neural Computing and Applications.

[45]  A. Sohani,et al.  Modeling and multi-objective optimization of an M-cycle cross-flow indirect evaporative cooler using the GMDH type neural network , 2016 .

[46]  Jitendra Kumar,et al.  Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters , 2018 .

[47]  Saeed Sharifian,et al.  A hybrid heuristic-based tuned support vector regression model for cloud load prediction , 2015, The Journal of Supercomputing.

[48]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[49]  Xiaodong Li,et al.  Time series forecasting by evolving artificial neural networks with genetic algorithms, differential evolution and estimation of distribution algorithm , 2011, Neural Computing and Applications.

[50]  Taghi M. Khoshgoftaar,et al.  The improved grey model based on particle swarm optimization algorithm for time series prediction , 2016, Eng. Appl. Artif. Intell..

[51]  Kodjo Agbossou,et al.  Time series prediction using artificial wavelet neural network and multi-resolution analysis: Application to wind speed data , 2016 .