Evolutionary Neural Network Modeling for Energy Prediction of Cloud Data Centers

Abstract

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.

Intelligent swarm firefly algorithm for the prediction of China's national electricity consumption

“…This study could provide practical policy indication in terms of energy investment and governmental energy policy. As an ANN is a black-box data-fitting model whose parameters would not bear a physical interpretation as many other modelling methods do, especially in extrapolation or prediction [31], we proposed this EC model and the FAVP approach to perform the prediction. In our future work, we plan however to compare with an EC-based ANN and the Bayesian method [32] for this application in our future work.…”

EWM: An entropy‐based framework for estimating energy consumption of edge servers

“…Yu et al 23 proposed a CMP power model, which has the main drawback of utilizing too few selected parameters. Foo et al [24][25][26] developed a power model based on evolutionary neural networks, but the main drawback is its high training complexity.…”

“…Foo et al 24‐26 developed a power model based on evolutionary neural networks, but the main drawback is its high training complexity.…”

Power consumption model based on feature selection and deep learning in cloud computing scenarios

“…Foo et al [32–34] develop an EC prediction model based on an evolutionary NN combining with several novel mechanisms of a genetic algorithm. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary NN approach to EC forecasting for cloud computing is highly promising.…”