Abstract-The success of Hadoop, an open-source framework for massively parallel and distributed computing, is expected to drive energy consumption of cloud data centers to new highs as service providers continue to add new infrastructure, services and capabilities to meet the market demands. While current research on data center airflow management, HVAC (Heating, Ventilation and Air Conditioning) system design, workload distribution and optimization, and energy efficient computing hardware and software are all contributing to improved energy efficiency, energy forecast in cloud computing remains a challenge. This paper reports an evolutionary computation based modeling and forecasting approach to this problem. In particular, an evolutionary neural network is developed and structurally optimized to forecast the energy load of a cloud data center. The results, both in terms of forecasting speed and accuracy, suggest that the evolutionary neural network approach to energy consumption forecasting for cloud computing is highly promising.

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.