Data Center Efficiency Research Articles

Energy efficiency of data center operating practices: Server clustering, powering on/off, and bang–bang control

Data centers today account for up to 3% of all global electricity consumption and produce 200 million metric tons of . Hence, improving energy efficiency is an important operational concern. This article examines common operating practices such as server clustering, powering on/off, and bang–bang control in terms of energy efficiency. Extending the mixed integer programming (MIP) formulation in a previous research study, we introduce new constraints reflecting the operating practices adopted for operational convenience. We develop an algorithmic strategy for constructing energy efficient clusters of servers using two upper bounds on the cluster size. Numerical experiments show that server clustering and bang–bang control do not diminish energy efficiency, and that powering on/off by itself is insufficient. Our results produce a conclusion that differs from the published literature on data center design and operations. © 2017 Wiley Periodicals, Inc. NETWORKS, Vol. 71(2), 107–119 2018

Study and Analysis of Energy Efficient Data center for Sustainable Development of ICT

:Data canters are the foundation, of contemporary information Technology. The Cloud services and web applications requires data centres having huge storage, network and computation capacity, has driven increase of extensive complex data centres running many of today’s Internet, financial, commercial and business applications. With continuous increase in the demands of clouds services and web application the need for remote storage and computation will certainly grow. Data centres are large group of servers and consume huge quantity of computation power to drive and run these server farms bringing about numerous difficulties like enormous energy consumption, emanation of greenhouse gasses, security , backup and recovery ; This paper study and analyse the methods to achieve energy efficiency in datacenter for sustainable development of ICT and low carbon green IT structures for these large and complex data centres to save consumption of electricity and reduce the emission of greenhouse gases to lower the effects of global warming. The structure utilizes most recent energy saving techniques like virtualization, cloud computing and green metrics to achieve green data canters. It also explores five stage to legitimately actualize green IT structure strategies to accomplish green data centres

Achieving energy efficiency in data centers with a performance-guaranteed power aware routing

Nowadays, data centers are designed to offer the highest performance in case of high traffic load and peak utilisation of the network. However, in a realistic data center environment, the peak capacity of the network is rarely reached and the average utilisation of devices varies between 5% and 25% which results into a huge loss of energy since most of the time links and servers are idle or under-utilized. The high impact of this wasted power on environmental effects, energy needs and electricity costs raised the concerns to seek for an efficient solution to make data centers more power effective while keeping the desired quality of service. In this paper, we propose a power-aware routing algorithm that saves a considerable amount of energy with a negligible trade-off on the performance of the network and a guaranteed reliability of the system. The key idea is to keep active only the vital and critical nodes participating in the communication traffic and ensuring the reliability while the unneeded devices are turned-off. Vital nodes between clusters (parts of the network) are calculated only once during the initialization of the system and consequently used with a constant time complexity. Besides its short computation time, our routing algorithm guarantees over 50% of energy saving by maintaining the minimum number of needed devices and over 20% when adding backup routes. This power efficiency is accompanied by a guaranteed performance and reliability against failures.

NUTS scheduling approach for cloud data centers to optimize energy consumption

The cloud data center is accommodated with many servers for cloud-based services which cause more consumption of energy and menace cost factors in computing tasks. Many existing scheduling techniques hinge on allocating task where scheduling algorithm is not based on assigning tasks through urgent and non-urgent task scheduling using dynamic voltage frequency scaling (DVFS) controller. In demand to reduce energy consumption and to maintain the quality of services, this paper proposes non-urgent and urgent task scheduling (NUTS) algorithm using DVFS, to restraint and scheduling of task in the more efficient way for minimizing the power consumption of the IT equipment. To increase the energy efficiency, we proposed scheduling queue and non-completed task queue for scheduling urgent, non-urgent and non-completed tasks to ally utilization of resources efficiently and to decrease the consumption of energy in the data center. In this paper, we compared proposed algorithm with two existing standard scheduling algorithms. The experimental results boast that NUTS algorithm performs better than the existing algorithms and can centrist energy efficiency in cloud data center.

A stable matching based elephant flow scheduling algorithm in data center networks

With the development of cloud computing in recent years, data center networks have become a hot topic in both industrial and academic communities. Previous studies have shown that elephant flows, which usually carry large amount of data, are critical to the efficiency of data centers. How to schedule elephant flows efficiently becomes an important issue for maintaining high performance and avoiding network congestion. In this paper, we study the efficient flow scheduling problem in data centers with a focus on elephant flows. By applying stable matching theory, the scheduling problem is modeled and proven to be NP-Hard. Then, we propose Fincher, an efficient scheme leveraging Software-Defined Networking (SDN) to reduce latency and avoid congestions in data centers. We have implemented Fincher with POX controller and Mininet. Extensive evaluation results demonstrate that Fincher can improve bisection bandwidth by 30% and reduce flow completion time by 28% on average compared to ECMP and Hedera.

Improving Datacenter Efficiency

Internet companies can improve datacenter efficiency and reduce costs, by minimizing resource waste while avoiding (or limiting) performance degradation. In this talk, I will first overview a few of the efficiency-related efforts we are undertaking at Microsoft, including leveraging workload history to improve resource management. I will then discuss some lessons from deploying these efforts in production and how they relate to academic research.

Improving Datacenter Efficiency

Internet companies can improve datacenter efficiency and reduce costs, by minimizing resource waste while avoiding (or limiting) performance degradation. In this talk, I will first overview a few of the efficiency-related efforts we are undertaking at Microsoft, including leveraging workload history to improve resource management. I will then discuss some lessons from deploying these efforts in production and how they relate to academic research.

Application Scheduling, Placement, and Routing for Power Efficiency in Cloud Data Centers

Increased power usage and network performance degradation due to best-effort bandwidth sharing significantly affect tenancy cost, cloud adoption, and data center efficiencies. In this article, we propose a novel Sliding-Scheduled Tenant request model which enables tenants to specify the required duration of their application within a certain window, in addition to its resource requirement graph. We investigate the sliding-scheduled application placement and routing problem, which selects the start-time of requests within their specified time-window to reserve both server and network resources for their required duration, and therefore provide resource guarantees with predictable performance. Using the multi-component utilization-based power model, we formulate the problem as an optimization problem that maximizes the acceptance rate while consuming as low power as possible. We develop fast online heuristics that adopt power, acceptance and adaptive spread-based scheduling policies while allocating the resources with the consideration of request duration and current shutdown-time of the devices. We demonstrate the effectiveness of the proposed algorithms in terms of power saving and acceptance rate, 1) for small data centers, by comparing their performance with the numerical results obtained from solving the optimization problem using CPLEX and 2) for large data centers using comprehensive simulation results.

Guest Editors’ Introduction: Special Issue on Green and Energy-Efficient Cloud Computing Part II

The papers in this special section focus on green and energy efficient cloud computing. Cloud computing has had a huge commercial impact and has attracted the interest of the research community. Public clouds allow their customers to outsource the management of physical resources, and rent a variable amount of resources in accordance to their specific needs. Private clouds allow companies to manage on-premises resources, exploiting the capabilities offered by the cloud technologies, such as using virtualization to improve resource utilization and cloud software for resource management automation. Hybrid clouds, where private infrastructures are integrated and complemented by external resources, are becoming a common scenario as well, for example to manage load peaks. Cloud applications are hosted by data centers whose size ranges from tens to tens of thousands of servers, which raises significant challenges related to energy and cost management. It has been estimated that the Information and Communication Technology (ICT) industry alone is responsible for 2-3 percent of the global greenhouse gas emissions. Therefore, we must find innovative methods and tools to manage the energy efficiency and carbon footprint of data centers, so that they can operate and scale in a cost-effective and environmentally sustainable manner. These methods and tools are often categorized as Data Center Infrastructure Management (DCIM) to monitor, control, and optimize data centers with extensive automation. DCIM must also effectively manage the quality of service provided by the data center, since cloud customers require high reliability, availability, usability, and low response times.

Dynamic performance of an in-rack proton exchange membrane fuel cell battery system to power servers

To improve the reliability and the energy efficiency of data centers, as well as to reduce infrastructure costs and environmental impacts, we experimentally evaluated in-rack powering of servers with a hybrid 12 kW Proton Exchange Membrane Fuel Cell (PEMFC) and battery system. The steady state and the transient performance of the PEMFC and battery in response to dynamic AC loads and real server loads have been evaluated and characterized. The PEMFC system responds quickly and reproducibly to load changes directly from the server rack. Peak efficiency of 55.2% in a single server rack can be achieved. The effect of fuel cell coolant temperature on the hybrid system transient behavior is also captured and evaluated. The observed PEMFC transient responses obtained from the experiments were used to design the size of the energy storage component for the hybrid system. Simulations and analysis of various types of energy storage devices for the hybrid system were carried out. To provide power to meet the most significant transient demand, energy storage capacity greater than 0.3 kWh is required for all battery types, while only 0.053 kWh capacity is required for the ultracapacitor. During charging, the ultracapacitor uses the shortest amount of time to recover to the original SOC, while the charging duration for the lead acid battery is twice as long as that of the ultracapacitor.

An evergreen cloud: Optimizing energy efficiency in heterogeneous cloud computing architectures

In a heterogeneous Cloud network scenario where a Cloud computing data center serves mobile Cloud computing requests, Cloud providers are expected to implement more innovative and effective solutions for a list of long standing challenges. Energy efficiency in the Cloud data center is one of the more pressing issues near the top of that list. Cloud providers are in constant pursuit of a system that satisfies client demands for resources, maximizes availability and other service level agreement metrics while minimizing energy consumption and, in turn, minimizing Cloud providers' cost.In this work, we introduce a novel mathematical optimization model to solve the problem of energy efficiency in a cloud data center. Next, we offer a solution based on VM migration that tackles this problem and minimizes energy efficiency in comparison to other common solutions. This solution includes a novel proposed technique to be integrated in any consolidation-based energy efficiency solution. This technique depends on dynamic idleness prediction (DIP) using machine learning classifiers. Moreover, we offer a robust energy efficiency scheduling solution that does not depend on live migration. This technique, termed Smart VM Over Provision (SVOP), offers a major advantage to cloud providers in the cases when live migration of VMs is not preferred due to its effects on performance. We evaluate the aforementioned solutions in terms of a number of critical metrics, namely, energy used per server, energy used per served request, acceptance rate, and the number of migrations performed.

Virtual machine consolidation enhancement using hybrid regression algorithms

Cloud computing data centers are growing rapidly in both number and capacity to meet the increasing demands for highly-responsive computing and massive storage. Such data centers consume enormous amounts of electrical energy resulting in high operating costs and carbon dioxide emissions. The reason for this extremely high energy consumption is not just the quantity of computing resources and the power inefficiency of hardware, but rather lies in the inefficient usage of these resources. VM consolidation involves live migration of VMs hence the capability of transferring a VM between physical servers with a close to zero down time. It is an effective way to improve the utilization of resources and increase energy efficiency in cloud data centers. VM consolidation consists of host overload/underload detection, VM selection and VM placement. Most of the current VM consolidation approaches apply either heuristic-based techniques, such as static utilization thresholds, decision-making based on statistical analysis of historical data; or simply periodic adaptation of the VM allocation. Most of those algorithms rely on CPU utilization only for host overload detection. In this paper we propose using hybrid factors to enhance VM consolidation. Specifically we developed a multiple regression algorithm that uses CPU utilization, memory utilization and bandwidth utilization for host overload detection. The proposed algorithm, Multiple Regression Host Overload Detection (MRHOD), significantly reduces energy consumption while ensuring a high level of adherence to Service Level Agreements (SLA) since it gives a real indication of host utilization based on three parameters (CPU, Memory, Bandwidth) utilizations instead of one parameter only (CPU utilization). Through simulations we show that our approach reduces power consumption by 6 times compared to single factor algorithms using random workload. Also using PlanetLab workload traces we show that MRHOD improves the ESV metric by about 24% better than other single factor regression algorithms (LR and LRR). Also we developed Hybrid Local Regression Host Overload Detection algorithm (HLRHOD) that is based on local regression using hybrid factors. It outperforms the single factor algorithms.

Numerical Simulation and Comparative Analysis of Different Airflow Distributions in Data Centers

Airflow pattern in a data center impacts the cooling effectiveness of the air-conditioning systems significantly, and hence impacts the energy efficiency of the whole data center. This paper presented investigation of 3 airflow patterns for a typical data center by CFD simulation. An under-floor air supplying system, row-level cooling system and rack level cooling system was used in the targeted data center. Cooling performance was simulated by CFD software. The cooling performance was compared by indices like Index of Mixing (IOM), Return Temperature Index (RTI), Temperature Inequality Index KT, Mean Temperature Difference Index of Rack Intake and Exhaust Air, Energy Utilization Coefficient. The results indicated that rack level airflow pattern shows the best performance in data center cooling. Compared with under-floor air supplying system, the IOM index is only 0.0011, and the KT index is 0.0082. In the end an optimization method was proposed for the deficiencies in rack level cooling system.

A 10 W On-Chip Switched Capacitor Voltage Regulator With Feedforward Regulation Capability for Granular Microprocessor Power Delivery

Granular power delivery with per-core regulation for microprocessor power delivery has the potential to significantly improve the energy efficiency of future data centers. On-chip switched capacitor converters can enable such granular power delivery with per-core regulation given a high efficiency, high power density, fast response time, and high output power converter design. This paper details the implementation of an on-chip switched capacitor voltage regulator in a $32\,\mathrm{n}\mathrm{m}$ SOI CMOS technology with deep trench capacitors. A novel feedforward control for reconfigurable switched capacitor converters is presented. The feedforward control reduces the output voltage droop following a transient load step. This leads to a reduced minimum microprocessor supply voltage, thereby reducing the overall power consumption of the microprocessor. The implemented on-chip switched capacitor voltage regulator provides a $0.7-1.1$ V output voltage from $1.8$ V input. It achieves a $85.1\%$ maximum efficiency at $3.2\,\mathrm{W}\mathrm{/}\mathrm{m}\mathrm{m}^2$ power density, a subnanosecond response time with improved minimum supply voltage capability, and a maximum output power of $10\,\mathrm{W}$ . For an output voltage of $850\,\mathrm{m}\mathrm{V}$ , the feedforward control reduces the required voltage overhead by $60\,\mathrm{m}\mathrm{V}$ for a transient load step from $10\%$ to $100\%$ of the nominal load. This can reduce the overall power consumption of the microprocessor by $7\%$ .

The Application of a Modular Air Conditioning System in Data Center

With the rapid development of Internet communication business, the issues related to the space, efficiency and energy consumption of data center are increasingly attracting more attentions. Because the modular air conditioning system has the advantages of quick construction, easy replication, rapid deployment, flexible scalability, high cooling efficiently, it has become a way to solve the bottleneck problem of traditional data center. In this paper, a data center being equipped with modular air conditioning system in Tianjin is taken as an example to analyze the energy and electricity saving and the characteristics of deployment by steps. The practice of this example shows the feasibility and prospects of applying modular air conditioning system in data center.

Enclosed aisle effect on cooling efficiency in small scale data center

Taking actual computer room of small scale data center in project as an example, airflow distribution of computer room in different aisle types were simulated, and temperature and velocity field were analyzed. An experiment was also carried out for the newly used computer room. The study shows that cold and hot air mix at two sides and top of free open cold and hot aisles, which reduces the utilization of cold air. Cooling effect of free open, semi-enclosed and full enclosed cold aisle turns better; and the effect of semi-enclosed cold aisle is obvious, which is recommended to use. Computer room’s temperatures of full enclosed hot aisle are lower than that of full enclosed cold aisle. So the former has a slight advantage, but requires more aisle partitions and higher cost. When the heat quantity of computer room is small, the natural cooling capacity of outdoor air in winter can meet the cooling requirement. Test data also show that enclosed cold aisle can improve the cooling efficiency.

Heat Sink Sunk

This article explores various innovative ways that technology companies are working upon to deal with the large amount of heat of their big data centers. Microsoft’s research and development team is working on designing and building of an underwater data center. Researchers believe that underwater data centers might have power, construction, and performance advantages as well. Berkeley’s National Energy Research Scientific Computing Center (NERSC) recycles its chilled water. NERSC uses air to chill the data center and cooler-running components, such as disk drives, routers, and network servers. With the growing efficiency of data centers, better cooling might not be enough to make underwater operations worthwhile. But cooling is only one of the advantages that Microsoft sees in submerging its data centers. Submersibles also simplify deployment. Microsoft used an underwater cable connected to the electrical grid to power Leona Philpot, a submersible data center. In the future, it may reduce costs through renewable energy, combined with on-site energy storage and backup power from the grid.

Review on Cooling System Energy Consumption in Internet Data Centers

Due to the advancement of the telecommunication and information technology (IT) industry, internet data centers (IDCs) have become widespread in the public and private sectors. As such, energy demand in the center has also become increasingly prominent. Several technologies on energy management have been studied to determine the options available to minimize the energy required to operate the data center as well as reduce greenhouse gas emissions. The cooling system is required to remove the high heat dissipated by the IT electronic components especially the servers in order to ensure safe and reliable working condition. However, it utilizes more than one-third of the total energy consumption in the data center. In this study, the energy efficiency technologies that are usually applied to cooling systems in data centers were reviewed. The aim is to find out the strategies that will reduce the energy consumption of the cooling system since the cooling demand in data center is all year round. Prior to that, the performance metric tool that is mostly used in analyzing data center efficiency was discussed. The conventional cooling system technologies that are utilized in data centers were also provided. Lastly, innovative cooling technologies for future solutions in data centers were discussed.

FuMAEVMS Novel VM Selection in Dynamic Consolidation of Virtual Machine

Background/Objective: Dynamic VM consolidation has been known as one from several ways to reduce energy consumption in cloud data center. The problem in reducing energy consumption with dynamic VM Consolidation has recognize as NP-Hard problem that divided into four subs, where VM selection is one of sub-problem. The objective VM selection is to choose the best VM that suitable to move from overload host and avoid oversubscription host. Methods: This research proposed novel VM selection model based on Fuzzy Logic, Markov Normal Algorithm (MA) and Existing VM Selection (FuMAEVMS) in dynamic VM consolidation. Moreover, RAM VM and max MIPS VM are consider as attribute to be used. The proposed VM selection model have been evaluated using Cloudsim with datasets from PlanetLabs in various condition of VM instance. The research measured the performance using several parameters such as Energy Consumption (EC), SLA Violation (SLAV), SLA Time per active host (SLATAH) and Performance Degradation Due Migration (PDM). FuMAEVMS were compared with existing VM selection such asconstant first selection (CFS), minimum migration time (MMT), random choice (RC) and maximum correlation (MC). Findings: FuMAEVMS as Novel VM selection capable to decide which VM that should be migrate from overload host in various condition VM instances that gives improvement of energy efficiency in cloud data center. We analyze the used of fuzzy logic in categorizing attribute VM capable to help in minimize rules production in Markov Normal Algorithm. This condition gives benefit to MA in deciding suitable existing VM selection such as CFS, MMT or MC to be used in migrating VM. Improvement: Results experiment has showed FuMAEVMS VM selection capable to reduced energy consumption in cloud data center significantly up to 4.45% when applied in dynamic VM consolidation compared with RC, MMT and MC.

Dynamic embedding of workflow requests for bandwidth efficiency in data centers

In this paper, we address the problem of embedding dynamically-arriving workflow requests in data centers. Workflows pose challenges due to data precedence and time disjointness among tasks, thus driving the need for intelligent methods to embed workflows in data centers while improving the bandwidth efficiency as well as guaranteeing the application performance. We first formulate an integer programming optimization model for the embedding problem that minimizes the amount of bandwidth required for workflow execution. We then develop two algorithms namely Critical Path Workflow Embedding (CPWE) and Edge Priority Workflow Embedding (EPWE) to solve this problem. We consider two data center network architectures: packet switching electrical networks and circuit switching optical wavelength division multiplexed (WDM) networks. While WDM-based optical networks have much larger bandwidth capacity to meet the ever-growing traffic demand in data centers, they pose challenges due to wavelength continuity constraint and the nature of circuit switching. We thus additionally propose methods for selecting appropriate Top-of-the-Rack (ToR) switches and wavelengths during the embedding process so as to increase the chance of accommodating many requests that span over multiple ToRs. We evaluate CPWE and EPWE through comprehensive simulations. The results show that CPWE and EPWE significantly reduce the bandwidth required for a workflow request by up to 66% for random workflows and 80% for realistic-application workflows compared to baseline algorithms. The results also show that the proposed methods for ToR selection and wavelength selection in optical data centers outperform other methods by reducing the rejection ratio by up to 47% with dynamic reconfiguration of lightpaths and 40% with incremental configuration of lightpaths.