Energy Efficiency Of Data Centers Research Articles

Sustainability Analysis of Green Data Centers With CCHP and Waste Heat Reuse Systems

Data centers worldwide consume a large amount of energy and pose serious threats to the environment. Combined cooling, heating, and power (CCHP) and waste heat reuse (WHR) systems are two effective approaches to improve the data center energy efficiency. However, whether and to what extent the combination of them can bring further performance improvement have not been explored yet. Moreover, it is unclear how to manage the energy flow in such a hybrid system. In this article, we try to answer these questions by proposing a data center energy architecture that includes both CCHP and WHR technologies. We formulate the energy management problem as two optimization problems with different objectives. By analytically solving the optimization problems, two energy management strategies, namely, Following the electrical load with waste heat reuse (FEL-WHR) and operating cost-aware energy management with waste heat reuse (OCM-WHR), are developed. We evaluate the performance of proposed solutions by extensive simulations using a real-world workload trace from a production data center. Numerical results suggest that the CCHP and WHR technologies generally reduce the operating cost and are more environmental friendly. If the power generation efficiency of CCHP system is high, the impact of WHR will be more conspicuous (up to 8 percent improvement) and FEL-WHR is recommended because it achieves better sustainability at an operating cost comparable to OCM-WHR. Otherwise, WHR only improves the sustainability trivially, and the energy management policy should be carefully chosen according to the data center operator's objective.

Energy efficiency in cloud data centres using parallel hybrid Jaya algorithm

PurposeData centres evolve constantly in size, complexity and power consumption. Energy-efficient scheduling in a cloud data centre is a critical and challenging research problem. It becomes essential to minimize the overall operational costs as well as environmental impact and to guarantee the service-level agreements for the services provided by the cloud data centres. Resource scheduling in cloud data centres is NP-hard and often requires substantial computational resources.Design/methodology/approachTo overcome these problems, the authors propose a novel model that leads to nominal operational cost and energy consumption in cloud data centres. The authors propose an effective approach, parallel hybrid Jaya algorithm, that performs parallel processing of Jaya algorithm and genetic algorithm using multi-threading and shared memory for interchanging the information to enhance convergence premature rate and global exploration.FindingsExperimental results reveal that the proposed approach reduces the power consumption in cloud data centres up to 38% and premature convergence rate up to 60% compared to other algorithms.Originality/valueExperimental results reveals that our proposed approach reduces the power consumption in cloud data centres up to 38% and premature convergence rate up to 60% compared to other algorithms.

Energy saving analysis of evaporative cooling composite air conditioning system for data centers

An evaporative cooling composite air conditioning system aimed at enhancing energy efficiency of data centers was proposed. Furthermore, the mathematical models on the base of the operation characteristics of the system were established. After verification by experiment, the energy saving performance of the system under different climatic conditions was investigated. The simulation results showed that the annual performance factor (APF) values are 5.31, 5.02, 4.75 and 4.50, respectively in severe cold zone-Shenyang (123.38E, 41.8N), cold zone-Beijing (116.30E, 39.9N), hot summer & cold winter zone-Nanjing (118.78E, 32.0N) and mild zone-Kunming (102.72E, 25.1N). The power usage effectiveness (PUE) values are below 1.40, the system has good energy saving advantages in different locations. After a water-cooled heat exchanger is used in the evaporative condenser, the APF values improve in all the four cities. The use of water-cooled heat exchanger is beneficial to further enhance energy saving of the system. A case study based on the system elaborates that it is feasible for energy saving of data centers in various climatic zones.

60 GHz wireless data center networks: A survey

Data centers (DCs) became an important part of computing today. A lot of services in Internet are run on DCs. Meanwhile a lot of research is done to tackle the challenges of high-performance and energy-efficient data center networking (DCN). Hot node congestion, cabling complexity/cost, and cooling cost are some of the important issues about data centers that need further investigation. Static and rigid topology in wired DCNs is an other issue that hinders flexibility. Use of wireless links for DCNs to eliminate these disadvantages is proposed and is an important research topic. In this paper, we review research studies in literature about the design of radio frequency (RF) based wireless data center networks. RF wireless DCNs can be grouped into two as hybrid (wireless and wired) and completely wireless data centers. We investigate both. We also compare wireless DCN solutions in the literature with respect to various aspects. Open areas and research ideas are also discussed.

PINE: Photonic Integrated Networked Energy efficient datacenters (ENLITENED Program) [Invited

We review the motivation, goals, and achievements of the Photonic Integrated Networked Energy efficient datacenter (PINE) project, which is part of the Advanced Research Projects Agency–Energy (ARPA-E) ENergy-efficient Light-wave Integrated Technology Enabling Networks that Enhance Dataprocessing (ENLITENED) program. The PINE program leverages the unique features of photonic technologies to enable alternative mega-datacenters and high-performance computing (HPC) system architectures that deliver more substantial energy efficiency improvements than can be achieved through link energy efficiency alone. In phase 1 of the program, the PINE system architecture demonstrated an average factor of 2.2 × improvement in transactions/joule across a diverse set of HPC and datacenter applications. In phase 2, PINE will demonstrate an aggressive 1.0 pJ/bit total link budget with high-bandwidth-density dense wavelength-division multiplexing (DWDM) links to enable additional 2.5 × or more efficiency gains through deep resource disaggregation.

A gray-box model for real-time transient temperature predictions in data centers

In response to the need to improve the energy efficiency of data centers (DCs), system designers now incorporate solutions such as continuous performance monitoring, automated diagnostics, and optimal control. While these solutions must ideally be able to predict transient conditions, in particular real time DC temperatures, existing forecasting methods are inadequate because they (1) make restrictive assumptions about system configurations, (2) are extremely time-consuming for real time applications, (3) are accurate only over limited time horizons, (4) fail to accurately model the effects of operating conditions, such as cooling unit operation conditions and server workloads, or (5) ignore important facets of the flow physics and heat transfer that can lead to large prediction errors in extrapolative predictions. To address these deficiencies, we develop a gray-box model that combines machine learning with the thermofluid transport equations relevant for a row-based cooled DC to predict transient temperatures in server CPUs and cold air inlet to the servers. An artificial neural network (ANN) embedded in the gray-box model predicts pressures, which provide inputs for the thermofluid transport equations that predict the spatio-temporal temperature distributions. The model is validated with experimental measurements for different (1) server workload distributions, (2) cooling unit set-point temperatures and (3) the airflow of the cooling units. This gray-box model exhibits superior performance compared to a conventional zonal temperature prediction model and an advanced black-box model that is based on a nonlinear autoregressive exogenous model. An application of the gray-box model involves a case study to detect cooling unit fan failure in a row-based DC cooling system.

A discrete chaotic multi-objective SCA-ALO optimization algorithm for an optimal virtual machine placement in cloud data center

Cloud computing, with its immense potentials in low cost and on-demand services, is a promising computing platform for both commercial and non-commercial computation applications. It focuses on the sharing of information and computation in a large network that are quite likely to be owned by geographically disbursed different venders. Power efficiency in cloud data centers (DCs) has become an important topic in recent years as more and larger DCs have been established and the electricity cost has become a major expense for operating them. Server consolidation using virtualization technology has become an important technology to improve the energy efficiency of DCs. Virtual machine (VM) assignment is the key in server consolidation. In the past few years, many methods to VM assignment have been proposed, but existing VM assignment approaches to the VM assignment problem consider the energy consumption by physical machines (PM). In current paper a new approach is proposed that using a combination of the sine cosine algorithm (SCA) and ant lion optimizer (ALO) as discrete multi-objective and chaotic functions for optimal VM assignment. First objective of our proposed model is minimizing the power consumption in cloud DCs by balancing the number of active PMs. Second objective is reducing the resources wastage by using optimal VM assignment on PMs in cloud DCs. Reducing SLA levels was another purpose of this research. By using the method, the number of increase of migration of VMs to PMs is prevented. In this paper, several performance metrics such as resource wastage, power consumption, overall memory utilization, overall CPU utilization, overall storage space, and overall bandwidth, a number of active PMs, a number of shutdowns, a number of migrations, and SLA are used. Ultimately, the results obtained from the proposed algorithm were compared with those of the algorithms used in this regard, including First Fit (FF), VMPACS and MGGA.

Prototype energy models for data centers

Data centers in the United States consume about twopercent of the nation’s electricity. Because heat gains from IT equipment drive cooling demand, data centers offer unique opportunities for energy savings. However, no prototype energy model for data centers is available in the suite of existing U.S. Department of Energy’s Commercial Prototype Building Models. This study presented the development of two new data center prototype models and their implementation in OpenStudio and EnergyPlus. The small-size data center model represents a computer room in a building served by computer room air conditioners (CRACs); while the large-sized model represents stand-alone data centers served by computer room air handlers (CRAHs) with a central chiller plant. For each data center model, two levels of IT equipment (ITE) load density were considered, to cover the wide range of IT power density of data centers: 40 and 100 W/ft2 (430 and 1076 W/m2) for the computer room, and 100 and 500 W/ft2 (1076 and 5382 W/m2) for the stand-alone data center. All other assumptions, such as building envelope, lighting, HVAC efficiencies and schedules, were based on the minimal requirements of ASHRAE Standard 90.1 at various vintages. We introduced a novel concept of supply and return air approach temperatures to capture the essential effects of non-uniform airflow and temperature distribution in data centers. The approach temperatures were pre-computed by computational fluid dynamics (CFD) simulations for various configurations of ITE loads and airflow containment management in data centers. A new feature was developed in EnergyPlus to implement the approach temperature method. A case study was conducted to demonstrate the use of the data center models. The two data center models cover all U.S. climate zones and can be used to evaluate energy saving measures for data centers, as well as to support development of data center energy efficiency codes and standards.

Improving energy efficiency in colocation data centers for demand response

Colocation data centers (colocations, for short) are developing rapidly and have become ideal participants for emergency demand response (EDR) programs. However, even colocation operators wish to save energy, they cannot achieve energy reduction without coordination from the tenants, because the servers in the colocations are owned and operated by the tenants. To solve the “uncoordinated relationship” issue between operators and tenants, some works have been done by way of incentivizing the tenants to reduce the energy consumption of their servers. However, apart from servers, the power consumption of the cooling system also accounts for a large portion in a colocation, which should be optimized as well. Unfortunately, the servers and the cooling system are controlled by tenants and operators separately in colocations, and thus “uncoordinated relationship” issue also exists between IT and cooling systems. In this paper, coarse-grained and fine-grained incentive mechanisms are proposed to solve these problems. Approximation algorithms are developed to optimize the energy-saving problems. Furthermore, Vickrey–Clarke–Groves (VCG) theory is introduced into our incentive mechanism design to guarantee the feasibility and truthfulness of the two mechanisms. Trace-driven simulations are performed to validate the effectiveness of the two incentive mechanisms. The results show that compared with the existing incentive mechanisms, up to 20.50% of the energy-saving cost can be reduced in the coarse-grained mechanism and 28.34% of the cost reduction can be achieved in the fine-grained mechanism.

HeporCloud: An energy and performance efficient resource orchestrator for hybrid heterogeneous cloud computing environments

In major Information Technology (IT) companies such as Google, Rackspace and Amazon Web Services (AWS), virtualisation and containerisation technologies are usually used to execute customers' workloads and applications. The computational resources are provided through large-scale datacenters, which consume substantial amount of energy and have, therefore, ecological impacts. Since long, Google runs users' applications in containers, Rackspace offers bare-metal hardware, whereas AWS runs them either in VMs (EC2), containers (ECS) and/or containers inside VMs (Lambda); therefore, making resource management a tedious activity. The role of a resource management system is of the greatest importance, principally, if IT companies practice various kinds of sand-boxing technologies, for instance, bare-metal, VMs, containers, and/or nested containers in their datacenters (hybrid platforms). The absence of centralised, workload-aware resource managers and consolidation policies produces questions on datacenters energy efficiency, workloads performance, and users' costs. In this paper, we demonstrate, through several experiments, using the Google workload data for 12,583 hosts and approximately one million tasks that belong to four different kinds of workload, the likelihood of: (i) using workload-aware resource managers in hybrid clouds; (ii) achieving energy and cost savings, in heterogeneous hybrid datacenters such that the workload performance is not affected, negatively; and (iii) how various allocation policies, combined with different migration approaches, will impact on datacenter's energy and performance efficiencies. Using plausible assumptions for hybrid datacenters set-up, our empirical evaluation suggests that, for no migration, a single scheduler is at most 16.86% more energy efficient than distributed schedulers. Moreover, when migrations are considered, our resource manager can save up to 45.61% energy and can improve up to 17.9% workload performance.

A detailed Study on Data Centre Energy Efficiency and Efficient Cooling Techniques

A detailed Study on Data Centre Energy Efficiency and Efficient Cooling Techniques

Optical networking within the Lightwave Energy-Efficient Datacenter project [Invited

The Lightwave Energy-Efficient Datacenter (LEED) project within the ARPA-e ENLITENED program is developing novel energy-efficient multichannel lightwave networks. These networks are enabled by a new optical “rotor” switch that can reconfigure the network topology in less than 20 µs and a field-programmable-gate-array-based network interface controller called Corundum that can provide precise network-wide synchronization of packets admitted into the lightwave network. Here we review the optical networking research within LEED and discuss future directions.

Adaptive Computing-Plus-Communication Optimization Framework for Multimedia Processing in Cloud Systems

A clear trend in the evolution of network-based services is the ever-increasing amount of multimedia data involved. This trend towards big-data multimedia processing finds its natural placement together with the adoption of the cloud computing paradigm, that seems the best solution to cope with the demands of a highly fluctuating workload that characterizes this type of services. However, as cloud data centers become more and more powerful, energy consumption becomes a major challenge both for environmental concerns and for economic reasons. An effective approach to improve energy efficiency in cloud data centers is to rely on traffic engineering techniques to dynamically adapt the number of active servers to the current workload. Towards this aim, we propose a joint computing-plus-communication optimization framework exploiting virtualization technologies, called MMGreen . Our proposal specifically addresses the typical scenario of multimedia data processing with computationally intensive tasks and exchange of a big volume of data. The proposed framework not only ensures users the Quality of Service (through Service Level Agreements), but also achieves maximum energy saving and attains green cloud computing goals in a fully distributed fashion by utilizing the DVFS-based CPU frequencies. To evaluate the actual effectiveness of the proposed framework, we conduct experiments with MMGreen under real-world and synthetic workload traces. The results of the experiments show that MMGreen may significantly reduce the energy cost for computing, communication and reconfiguration with respect to the previous resource provisioning strategies, respecting the SLA constraints.

A Taxonomy and Survey of Power Models and Power Modeling for Cloud Servers

Due to the increasing demand of cloud resources, the ever-increasing number and scale of cloud data centers make their massive power consumption a prominent issue today. Evidence reveals that the behaviors of cloud servers make the major impact on data centers’ power consumption. Although extensive research can be found in this context, a systematic review of the models and modeling methods for the entire hierarchy (from underlying hardware components to the upper-layer applications) of the cloud server is still missing, which is supposed to cover the relevant studies on physical and virtual cloud server instances, server components, and cloud applications. In this article, we summarize a broad range of relevant studies from three perspectives: power data acquisition, power models, and power modeling methods for cloud servers (including bare-metal, virtual machine (VM), and container instances). We present a comprehensive taxonomy on the collection methods of server-level power data, the existing mainstream power models at multiple levels from hardware to software and application, and commonly used methods for modeling power consumption including classical regression analysis and emerging methods like reinforcement learning. Throughout the work, we introduce a variety of models and methods, illustrating their implementation, usability, and applicability while discussing the limitations of existing approaches and possible ways of improvement. Apart from reviewing existing studies on server power models and modeling methods, we further figure out several open challenges and possible research directions, such as the study on modeling the power consumption of lightweight virtual units like unikernel and the necessity of further explorations toward empowering server power estimation/prediction with machine learning. As power monitoring is drawing increasing attention from cloud service providers (CSPs), this survey provides useful guidelines on server power modeling and can be inspiring for further research on energy-efficient data centers.

IBM z15: Improved data center density and energy efficiency, new system packaging, and modeling

The IBM z15 is designed to meet the requirements of a range of data centers, while reducing costs through increased density, configuration flexibility, and cooling efficiency. The z15 is a continuation and broadening of the physical transformation of the mainframe that began with the IBM z14 ZR1/LR1, which introduced the new “true 19-in” frame. A maximum configuration z15 delivers greater than 30% additional compute capacity per watt than z14, and maintains approximately the same maximum system footprint, while enabling significant floor space reduction for most configurations. The z15 introduces the choice of integrated 2N power using either intelligent power distribution units or bulk power, also supporting most data centers including hot/cold-aisle containment, raised-floor and nonraised-floor, and top and bottom-exit I/O and power. The z15 supports the ASHRAE A3 (fourth edition) environment, providing efficiency advantages by reducing humidification requirements. The z15 maintains the value of a system that is preconfigured/pretested before shipping. Innovations in packaging, I/O cabling, controls, and testing are put in the context of the latest data center trends. The capabilities of new tools to estimate power, weight, airflow, heat extracted to water for water-cooled systems as well as 3-D and computational fluid dynamics models to aid in the planning for the system are described.

A Machine Learning Solution for Data Center Thermal Characteristics Analysis

The energy efficiency of Data Center (DC) operations heavily relies on a DC ambient temperature as well as its IT and cooling systems performance. A reliable and efficient cooling system is necessary to produce a persistent flow of cold air to cool servers that are subjected to constantly increasing computational load due to the advent of smart cloud-based applications. Consequently, the increased demand for computing power will inadvertently increase server waste heat creation in data centers. To improve a DC thermal profile which could undeniably influence energy efficiency and reliability of IT equipment, it is imperative to explore the thermal characteristics analysis of an IT room. This work encompasses the employment of an unsupervised machine learning technique for uncovering weaknesses of a DC cooling system based on real DC monitoring thermal data. The findings of the analysis result in the identification of areas for thermal management and cooling improvement that further feeds into DC recommendations. With the aim to identify overheated zones in a DC IT room and corresponding servers, we applied analyzed thermal characteristics of the IT room. Experimental dataset includes measurements of ambient air temperature in the hot aisle of the IT room in ENEA Portici research center hosting the CRESCO6 computing cluster. We use machine learning clustering techniques to identify overheated locations and categorize computing nodes based on surrounding air temperature ranges abstracted from the data. This work employs the principles and approaches replicable for the analysis of thermal characteristics of any DC, thereby fostering transferability. This paper demonstrates how best practices and guidelines could be applied for thermal analysis and profiling of a commercial DC based on real thermal monitoring data.

Online parameter tuning of the flow classification method in the energy-efficient data center network “HOLST”

An online parameter-tuning method for the energy-efficient data center network (DCN) named HOLST (high-speed optical layer 1 switch system for time-slot-switching-based optical data center networks) is proposed. HOLST comprises an optical circuit switching network, optical slot switching network, and electrical packet switching network for the spine layer. It requires flows to be assigned to optimal switches to achieve high power savings. In this study, first we experimentally confirm that the change in the DCN characteristics in the short term of actual data center traffic downgrades the accuracy of flow classification. Subsequently, we propose a procedure for reconfiguring a flow classification function and a method for online parameter tuning for this function. Finally, the accuracy of the flow classification method using the proposed tuning and estimated switching energy consumption in the spine layer are evaluated. The proposed online parameter-tuning function increases the accuracy of flow classification and reduces switching energy consumption relative to the conventional flow classification function.

Virtual Machine Consolidation with Minimization of Migration Thrashing for Cloud Data Centers

Cloud data centers consume huge amount of electrical energy bringing about in high operating costs and carbon dioxide emissions. Virtual machine (VM) consolidation utilizes live migration of virtual machines (VMs) to transfer a VM among physical servers in order to improve the utilization of resources and energy efficiency in cloud data centers. Most of the current VM consolidation approaches tend to aggressive-migrate for some types of applications such as large capacity application such as speech recognition, image processing, and decision support systems. These approaches generate a high migration thrashing because VMs are consolidated to servers according to VM’s instant resource usage without considering their overall and long-term utilization. The proposed approach, dynamic consolidation with minimization of migration thrashing (DCMMT) which prioritizes VM with high capacity, significantly reduces migration thrashing and the number of migrations to ensure service-level agreement (SLA) since it keeps VMs likely to suffer from migration thrashing in the same physical servers instead of migrating. We have performed experiments using real workload traces compared to existing aggressive-migration-based solutions; through simulations, we show that our approach improves migration thrashing metric by about 28%, number of migrations metric by about 21%, and SLAV metric by about 19%.

Ensuring renewable energy utilization with quality of service guarantee for energy-efficient data center operations

The reduction of greenhouse emissions is becoming a major goal of energy-intensive industries, such as data centers, and there have been significant efforts to achieve sustainable operations by meeting electricity consumption using renewable energy generations. Specifically, it has been a common practice for data centers to use renewable energy via on-site solar power generation to directly offset electricity consumption by renewable energy to contribute to environmental sustainability. However, the introduction of intermittent and non-dispatchable renewable energy generations for powering data centers that generally host time-varying workloads presents a significant challenge, and thus, this study mainly focuses on how to improve renewable energy utilization for data center operations considering the integration of co-located solar power generation and battery energy storage. The main objective is to develop a mathematical optimization model for energy-efficient and sustainable data center operations to minimize energy cost while ensuring the desired level of renewable energy utilization and the required quality of service guarantee. In particular, this study proposes a two-stage stochastic program integrated with an expected-value constraint and a chance constraint, and an integer programming and sampling-based approach are adopted to solve the problem to investigate optimal data center operations. The comprehensive numerical experiments are conducted to evaluate the proposed model compared with benchmark models for various parameter settings, and the results show that the proposed model can be successfully implemented to enable data centers to achieve the desired renewable energy utilization while improving energy efficiency.

Study on influence of operating parameters of data center air conditioning system based on the concept of on-demand cooling

Abstract To improve energy efficiency of data centers, an air conditioning system for the concept of demand-based on cooling was proposed. This system combines a heat pipe cooling cycle and a vapor compression cooling cycle. Besides, the evaporative condenser is used to further utilize the natural cooling source, and the evaporator is put into the rack to realize on-demand cooling. A mathematical model was established to perform simulations of the system. The results showed that the energy consumption of compressor and pump reduce with the rising of outdoor unit air flow and evaporator inlet temperature. The coefficient of performance (COP) was selected as a reference index. When the cooling capacity is 8000 W, 6400 W and 4800 W, the optimal outdoor unit air flow of the heat pipe mode is 2000 m3/h, 1400 m3/h and 800 m3/h, respectively, and that of the vapor compression mode is 4000 m3/h, 3600 m3/h and 2400 m3/h, respectively. With the rising of evaporator inlet temperature from 29 °C to 41 °C under rated conditions, the heat pipe mode COP increased by 30.11%, 13.52% and 6.30%, respectively, and the vapor compression mode COP increased by 74.65%, 82.12% and 90.97%, respectively.