Evolutionary neural network modeling for energy prediction of cloud data centers

Accurate forecasts of data center energy consumptions can help eliminate risks caused by underprovisioning or waste caused by over-provisioning. However, due to nonlinearity and complexity, energy prediction remains a challenge. An added layer of complexity further comes from dynamically changing workloads. There is a lack of physical principle based clear-box models, and existing black-box based methods such neural networks are restrictive. In this paper, we develop an evolutionary neural network as a structurally optimal black-box model to forecast the energy consumption of a dynamic cloud data center. In particular, the approach to evolving an optimal network is developed from several novel mechanisms of a genetic algorithm, such as a structurally-inclusive matrix encoding and species parallelism that help maintain an overall increasing fitness to overcome slow convergence whilst preventing premature dominance. The model is trained using part of the data obtained from a set of MapReduce jobs on a 120-core Hadoop cluster and is then validated against unseen data. The results, both in terms of prediction speed and accuracy, suggest that this evolutionary neural network approach to cloud data center forecast is highly promising.

[1]  Zhihang Song,et al.  Multi-objective optimization of temperature distributions using Artificial Neural Networks , 2012, 13th InterSociety Conference on Thermal and Thermomechanical Phenomena in Electronic Systems.

[2]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.

[3]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[4]  Jun Zhang,et al.  Cloud Computing Resource Scheduling and a Survey of Its Evolutionary Approaches , 2015, ACM Comput. Surv..

[5]  Jim Gao,et al.  Machine Learning Applications for Data Center Optimization , 2014 .

[6]  Kevin N. Gurney,et al.  An introduction to neural networks , 2018 .

[7]  Depei Qian,et al.  Energy Prediction for MapReduce Workloads , 2011, 2011 IEEE Ninth International Conference on Dependable, Autonomic and Secure Computing.

[8]  Xiaodong Li,et al.  Species based evolutionary algorithms for multimodal optimization: A brief review , 2010, IEEE Congress on Evolutionary Computation.

[9]  Kranthimanoj Nagothu,et al.  Prediction of cloud data center networks loads using stochastic and neural models , 2011, 2011 6th International Conference on System of Systems Engineering.

[10]  Pascal Bouvry,et al.  Computational intelligence for cloud management current trends and opportunities , 2013, 2013 IEEE Congress on Evolutionary Computation.

[11]  Yun Li,et al.  Heuristically enhanced dynamic neural networks for structurally improving photovoltaic power forecasting , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[12]  Lakhmi C. Jain,et al.  Computational Intelligence: A Compendium , 2008, Computational Intelligence: A Compendium.

[13]  Jie Xu,et al.  Neural Network-Based Overallocation for Improved Energy-Efficiency in Real-Time Cloud Environments , 2012, 2012 IEEE 15th International Symposium on Object/Component/Service-Oriented Real-Time Distributed Computing.

[14]  Jeff Heaton,et al.  Introduction to Neural Networks for C#, 2nd Edition , 2008 .

[15]  John Fulcher,et al.  Computational Intelligence: An Introduction , 2008, Computational Intelligence: A Compendium.