A Sensor Predictive Model for Power Consumption using Machine Learning
Nalveer Moocheet, Brigitte Jaumard, Pierre Thibault, Lackis Eleftheriadis · 2023
Reducing the power consumption of computing devices remains a challenge for the data center industry. In 2022, it represents approximately 2% of global electricity consumption and 1% of global greenhouse gas emissions. In addition, data centers must integrate the 5G and B5G challenges into their strategies, by increasing the computing resources available to face higher-quality service constraints. Indeed, 5G and B5G future networks are increasingly software-oriented and therefore, rely heavily on cloud computing to process large amounts of data from multiple sources in real-time.Several research works on energy management have been proposed to ensure a reduction of the energy consumed by the various components of a data center (e.g., software, computing devices, or cooling systems). However, to optimize the energy consumption of computing devices (e.g., virtual machines/container operations), it is essential to have an accurate model for predicting power consumption. Thus, we propose in this study a new sensor predictive model to predict the dynamic power consumption of cloud computing devices with high accuracy.Our proposal takes advantage of the various sensors that are now embedded in physical machines, or more generally in cloud server machines, as well as Performance Monitoring Counters to implement a Machine Learning power prediction model.The performance evaluation results confirm that our power consumption prediction models outperform previous literature models in terms of accuracy. Indeed, our best model achieves a R2score of 93.6% which is higher than the compared baseline model by 21.1%.