Power Consumption Of Virtual Machines Research Articles

PM2VE: Power Metering Model for Virtualization Environments in Cloud Data Centers

Virtualization technologies provide solutions for cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many practical models for estimating the power consumption of virtual machines (VMs) have been proposed, few power estimation models of containers have been put forth. In this paper, we propose a fast-training piecewise regression model based on a decision tree for VM power metering and estimate the power of containers configured on the VM by treating the container as a group of processes on the VM. We select appropriate features from the collected metrics of VMs/containers to help our model fit the nonlinear relationship between power and features well. Besides, we optimize the leaf nodes of the regression tree, realizing the effective power metering of virtualization environments. We evaluate the proposed model on 13 tasks in PARSEC and compare it with several commonly used models in data centers. The experimental results prove the effectiveness of the proposed model, and the estimated power of containers is in line with expectations.

Integrated Energy Security Defense Monitoring Software Based on Cloud Computing

In order to solve the problem of outlier detection of integrated energy security defense monitoring software, an automatic detection algorithm of virtual machine power anomaly in a cloud computing environment is proposed. The method is implemented through three main steps: data preprocessing, pattern recognition, and prediction of virtual machine power anomaly detection model. It is found through experiments that with the increase of node number, the convergent iterations of the model are less and RMSE is lower, but the increase of node number of the hidden layer will lead to a longer model running time. When the number of nodes reaches 100, the test results of the validation set are significantly improved, and the loss function of the validation set is minimal when the number of nodes is less than 30 iterations. Finally, the hidden layer of the model consists of 100 LSTM units, followed by a dense output layer with 1 neuron, and 0.2 loss, retrospection, and foresight equal to 1. Adam optimizer was used to train LSTM and stop it in advance after 50 iteration steps. Its parameters remained default, with a learning rate of 0.001 and attenuation of 0.9. It can be seen that this model can well predict the virtual machine power consumption data and effectively solve the problem of outlier detection of integrated energy security defense monitoring software.

Power consumption prediction in cloud data center using machine learning

The flourishing development of the cloud computing paradigm provides several services in the industrial business world. Power consumption by cloud data centers is one of the crucial issues for service providers in the domain of cloud computing. Pursuant to the rapid technology enhancements in cloud environments and data centers augmentations, power utilization in data centers is expected to grow unabated. A diverse set of numerous connected devices, engaged with the ubiquitous cloud, results in unprecedented power utilization by the data centers, accompanied by increased carbon footprints. Nearly a million physical machines (PM) are running all over the data centers, along with (5 – 6) million virtual machines (VM). In the next five years, the power needs of this domain are expected to spiral up to 5% of global power production. The virtual machine power consumption reduction impacts the diminishing of the PM’s power, however further changing in power consumption of data center year by year, to aid the cloud vendors using prediction methods. The sudden fluctuation in power utilization will cause power outage in the cloud data centers. This paper aims to forecast the VM power consumption with the help of regressive predictive analysis, one of the Machine Learning (ML) techniques. The potency of this approach to make better predictions of future value, using Multi-layer Perceptron (MLP) regressor which provides 91% of accuracy during the prediction process.

PMC-based power measuring technique in virtualisation environments

Recently, resource virtualisation technology has been widely applied in many high-performance datacentres. However, measuring the power of individual virtual machine is still a challenging issue. In this work, we proposed a novel technique which uses performance monitor counters PMC for power metering on per-VM basis. Unlike the classical utilisation-based techniques which can only provide coarse-grained power metering with unbounded error, our approach can increase the accuracy when metering virtual machine power consumption by bounded error range. The experiments conducted by various benchmarks on different platforms show that the proposed approach outperforms existing approaches in terms of accuracy and power-efficiency.

Prediction Model for Virtual Machine Power Consumption in Cloud Environments

Power consumption has become a crucial issue in cloud computing environments because of environmental and financial concerns. It is necessary to estimate individual virtual machine power consumption to enforce efficient power aware policies in cloud. Existing solutions are built on linear power models to infer power consumption through VM resource utilization. However, linear models do not capture dependencies among multiple parameters and hence they do not ensure prediction accuracy across multiple workloads. In this paper, a non-linear support vector regression based power model using performance monitor counters is proposed to predict individual virtual machine power consumption. Experimental results with various standard benchmark workloads demonstrate that the prediction accuracy of proposed approach is better than the existing linear regression based power model.

A Tree Regression-Based Approach for VM Power Metering

Cloud computing is developing so fast that more and more data centers have been built every year. This naturally leads to high-power consumption. Virtual machine (VM) consolidation is the most popular solution based on resource utilization. In fact, much more power can be saved if we know the power consumption of each VM. Therefore, it is significant to measure the power consumption of each VM for green cloud data centers. Since there is no device that can directly measure the power consumption of each VM, modeling methods have been proposed. However, current models are not accurate enough when multi-VMs are competing for resources on the same server. One of the main reasons is that the resource features for modeling are correlated with each other, such as CPU and cache. In this paper, we propose a tree regression-based method to accurately measure the power consumption of VMs on the same host. The merits of this method are that the tree structure will split the data set into partitions, and each is an easy-modeling subset. Experiments show that the average accuracy of our method is about 98% for different types of applications running in VMs.

Power-Aware Cloud Metering

The cost of electricity contributes significantly to the operating expense incurred in hosting cloud services. It is necessary to consider this cost while charging the consumers for their service utilization. In this work, we arrive at a metering mechanism for cloud services, in which the price of a cloud service tracks the variable input cost of electricity from a smart grid. The power-aware cloud metering developed here is a dynamic pricing and billing model where tariff for a cloud service is varied in accordance with the input electricity cost. We arrive at a model for power consumption of virtual machines hosted on the cloud infrastructure. This power consumption model is used in calculating the cost of operation of the service. A cloud instance leased by a consumer is billed based on the cost of operation obtained, and its resource utilization. Experimental results validate the approach presented.

Power consumption estimation of CPU and peripheral components in virtual machines

Energy consumption of IT increased continuously during the last decades. Numerous works have been accomplished for improving energy efficiency of hardware whereas software energy efficiency has been ignored for a long time. This contribution presents a novel approach for estimating energy consumption of computer systems in dependency of software-caused workloads in different execution environments. The system is the basis for automatic optimization of software execution in an energy-efficient way by finding the best-suiting host computer (and best-suiting peripheral devices). Thus, it opens novel ways to further improve energy-efficiency of IT systems by migrating software-caused load to an energy-efficient target. Exemplary, the approach is tested in a virtualized data center environment, where virtual machines are the applications. The presented approach is a vehicle for automatically computing an energy-efficient virtual machine placement. The paper presents a new algorithm for estimating virtual machine power consumption, which consists of CPU power consumption estimation as well as power usage estimation of peripheral components like hard disk drive and network interface controller. The accuracy of the presented approach is proved by means of measurements.

Virtual machine power measuring technique with bounded error in cloud environments

In virtualized datacenters, accurately measuring the power consumption of virtual machines (VMs) is the prerequisite to achieve the goal of fine-grained power management. However, existing VM power models can only provide power measurements with empirical accuracy and unbounded error. In this paper, we firstly formulize the co-relation between utilization and accuracy of power model, and compare two classes of VM power models; then we propose a novel VM power model which is based on a conception named relative performance monitoring counter (PMC); finally, based on the relative PMC power model, we propose a novel VM scheduling algorithm which uses the information of relative PMC to compensate the recursive power consumption. Theoretical analysis indicates that the proposed algorithm can provide bounded error when measuring per-VM power consumption. Extensive experiments are conducted by using various benchmarks on different platforms, and the results show that the error of per-VM power measurement can be significantly reduced. In addition, the proposed algorithm is effective to improve the power efficiency of a server when its virtualization ratio is high.