Machine Learning-Based Energy Aware Placement of Container Over Virtual Machines

Abstract

    The advent of 5G and the imminent arrival of Beyond 5G (B5G) have significantly increased demands on service providers. This exponential growth poses a challenge for 5G networks, since clients are currently offloading data to edge cloud servers to meet the connectivity and latency requirements. These servers must continually scale to meet increasing demands for CPU, memory, and storage, leading to significant energy consumption. Data centers account for 1.5% of global energy consumption and produce equally high greenhouse gas emissions. This trend will grow unless we find ways to improve efficiency.

Our work proposes a solution to these problems with an efficient placement algorithm backed by an accurate energy predictive model. This model helps by pre-emptively detecting the energy each machine will consume when future tasks are deployed. These predictive capabilities help the placement and reduce overall energy consumption. Our model uses Performance Monitoring Counters and various sensors, such as heat and fan speed, commonly found on Data Center machines, to increase its feature space and accuracy. Our work includes creating the model and integrating it with the energy-aware placement algorithm. Additionally, our method increased the performance and overall Quality of Service.

Our results show that our machine learning model, particularly using XGBoost, can

reduce energy consumption and improve task completion times in realistic scenarios. Our

experiments, tested on real servers with realistic loads, achieved good results without using stresses like stress-ng that generate unrealistic loads. Our model achieved an R² score of 91.2%, helping reduce energy consumption by 6% without changes to the cluster or the need for consolidation.