Data Center Load Research Articles

A Novel Load Adaptive ZVS Auxiliary Circuit for PWM Three-Level DC–DC Converters

Three-level PWM dc–dc converters convert high dc voltage (>500 V) generally at the output of a three-phase ac–dc PWM rectifier in ac–dc converters to an isolated dc output voltage which can be used to power data center loads. Strict efficiency requirements at loads from 20% to 50% of full load of ac–dc converters for telecom applications have been introduced by energy star enforcing industries to improve efficiency of the dc–dc converter in an ac–dc converter powering data-center loads at those loads. High-efficiency requirements at low and mid loads in high switching frequency PWM dc–dc three-level converters implemented with MOSFETs can be achieved by reducing switching losses through optimized load adaptive ZVS for the entire load range. In this paper, a simple yet novel load adaptive ZVS auxiliary circuit for three-level converter is proposed for so that the resulting three-phase ac–dc converter can meet energy star platinum efficiency standard. The operation of the proposed dc–dc converter is described, analyzed, and validated by experimental results from an industrial prototype of a three-phase ac–dc converter comprising of a front-end three-phase boost PWM rectifier followed by the proposed converter.

An Optimal Resource Allocation Algorithm in Cloud Computing Environment

Resource allocation is a key technology of cloud computing. At present, the most of studies on resource allocation mainly focus on improving the overall performance by balancing the load of data center. This paper will design the experimental platform of resource allocation algorithm, energy optimization and performance analysis, obtain original achievements in scientific research ,for the resource allocation method based on immune algorithm and energy optimization in cloud computing to provide innovative ideas and scientific basis. This research has important significance for further study on resource allocation and energy optimization in cloud computing environment.

Analyzing the Cooling Efficiency of the Thermal Environment in Data Centers

Given the explosive growth of data, scalability and fault tolerance have become a fundamental challenge for data center network structures. Temperature in data centers significantly affects the failure ratio of high-speed network devices. Various types of air distribution schemes influence the temperature of network equipment differently, and the cooling cost in data centers dominates the overall energy cost. On the basis of the energy efficiency of cooling systems, this study analyzes and compares the thermal load distribution in the enclosure of standard and non-standard data centers by considering the effects of the external environment. Analysis results demonstrate that the external environment significantly affects the thermal load of non-standard data centers. By leveraging on the air temperature outside data centers and on the inlet/outlet of IT equipment, the air temperature and return air temperature of air conditioning are calculated when performing hot and cold aisle containment. The calculations indicate that sealing an appropriate aisle (hot or cold aisle) can significantly reduce the energy consumption of cooling systems in terms of the external air temperature outside data centers. Furthermore, if the air temperature outside data centers is higher than the temperature at the inlet of IT equipment, sealing the cold aisle outperforms sealing the hot aisle. By contrast, the aisle to be sealed depends on the energy efficiency ratio of the air conditioning.

Exploring smart grid and data center interactions for electric power load balancing

The operation of a data center consumes a tremendous amount of electricity, and the energy cost accounts for a large portion of the data center's operation cost. This leads to a growing interest towards reducing the energy cost of data centers. One approach advocated in recent studies is to distribute the computation workload among multiple geographically dispersed data centers by exploiting the electricity price differences. However, the impact of load redistributions on the power grid is not well understood yet. This paper takes the first step towards tackling this important issue, by studying how the power grid can take advantage of the data center's load distribution proactively for the purpose of power load balancing. We model the interactions between power grid and data centers as a two-stage problem, where the power grid operator aims to balance the electric power load in the first stage, and the data centers seek to minimize their total energy cost in the second stage. We show that this two-stage problem is a bilevel program with an indefinite quadratic objective function, which cannot be solved efficiently using standard convex optimization algorithms. Therefore, we reformulate this bilevel optimization problem as a linear program with additional finite complementarity slackness conditions, and propose a branch and bound algorithm to attain the globally optimal solution. The simulation results demonstrate that our proposed scheme can improve the load balancing performance by around 12% in terms of the electric load index and reduce the energy cost of data centers by 46% on average.

Green Scheduling of Bag-of-tasks Applications in Cloud Data Center Using GreenCloud Simulator

The cloud provider provisions the resources of the data center to the user so as to satisfy the Quality of Service (QoS) negotiated between them and specified in the Service Level Agreements (SLA). To attain maximum profit, the cloud provider has to schedule the tasks in the data center efficiently in accordance to the users QoS requirements and also minimize the energy consumption thus reducing the operational expense (OPEX) of the data center. The energy efficient scheduling of cloud applications has to consider the QoS parameter specified as job deadline and assign them to minimum number of servers possible without affecting the performance so that the idle servers can be shutdown to reduce the energy consumed. This paper analyses this green scheduling for various workloads of the cloud users and provide information about the task completion and rejection at various data center load, the SLA violations and the degradation of system performance. It presents the server utilization specifying the number of busy and idle servers with their computational load and the energy consumed by them for different workloads. The paper also provides the insights on the utilization of the servers for the workloads and analyses the reasons for the underutilization of servers and how the scheduling can be improved without sacrificing the performance of the data center. The paper analyses the above observations of the green scheduling of the data center using GreenCloud.

Expanded Assessment of a Practical Thermally Aware Energy-Optimized Load Placement Strategy for Open-Aisle, Air-Cooled Data Centers

This paper expands on the work presented by Demetriou and Khalifa (Demetriou and Khalifa, 2013, “Thermally Aware, Energy-Based Load Placement in Open-Aisle, Air-Cooled Data Centers,” ASME J. Electron. Packag., 135(3), p. 030906) that investigated practical IT load placement options in open-aisle, air-cooled data centers. The study found that a robust approach was to use real-time temperature measurements at the inlet of the racks to remove IT load from the servers with the warmest inlet temperature. By considering the holistic optimization of the data center load placement strategy and the cooling infrastructure optimization, for a range of data center IT utilization levels, this study investigated the effect of ambient temperatures on the data center operation, the consolidation of servers by completely shutting them off, a complementary strategy to those presented by Demetriou and Khalifa (Demetriou and Khalifa, 2013, “Thermally Aware, Energy-Based Load Placement in Open-Aisle, Air-Cooled Data Centers,” ASME J. Electron. Packag., 135(3), p. 030906) for increasing the IT load beginning with servers that have the coldest inlet temperature and finally the development of load placement rules via either static (i.e., during data center benchmarking) or dynamic (using real-time data from the current thermal environment) allocation. In all of these case studies, by using a holistic optimization of the data center and associated cooling infrastructure, a key finding has been that a significant amount of savings in the cooling infrastructure's power consumption is seen by reducing the CRAH's airflow rate. In many cases, these savings can be larger than providing higher temperature chilled water from the refrigeration units. Therefore, the path to realizing the industry's goal of higher IT equipment inlet temperatures to improve energy efficiency should be through both a reduction in air flow rate and increasing supply air temperatures and not necessarily through only higher CRAH supply air temperatures.

ACE

Peak power management of datacenters has tremendous cost implications. While numerous mechanisms have been proposed to cap power consumption, real datacenter power consumption data is scarce. To address this gap, we collect power demands at multiple spatial and fine-grained temporal resolutions from the load of geo-distributed datacenters of Microsoft over 6 months. We conduct aggregate analysis of this data, to study its statistical properties. With workload characterization a key ingredient for systems design and evaluation, we note the importance of better abstractions for capturing power demands, in the form of peaks and valleys. We identify and characterize attributes for peaks and valleys, and important correlations across these attributes that can influence the choice and effectiveness of different power capping techniques. With the wide scope of exploitability of such characteristics for power provisioning and optimizations, we illustrate its benefits with two specific case studies.

B3: Fuzzy-Based Data Center Load Optimization in Cloud Computing

Cloud computing started a new era in getting variety of information puddles through various internet connections by any connective devices. It provides pay and use method for grasping the services by the clients. Data center is a sophisticated high definition server, which runs applications virtually in cloud computing. It moves the application, services, and data to a large data center. Data center provides more service level, which covers maximum of users. In order to find the overall load efficiency, the utilization service in data center is a definite task. Hence, we propose a novel method to find the efficiency of the data center in cloud computing. The goal is to optimize date center utilization in terms of three big factors—Bandwidth, Memory, and Central Processing Unit (CPU) cycle. We constructed a fuzzy expert system model to obtain maximum Data Center Load Efficiency (DCLE) in cloud computing environments. The advantage of the proposed system lies in DCLE computing. While computing, it allows regular evaluation of services to any number of clients. This approach indicates that the current cloud needs an order of magnitude in data center management to be used in next generation computing.

Minimizing the thermal impact of computing equipment upgrades in data centers

Upgrading of today's air-cooled data centers (DCs) with high-performance computing, networking, and storage equipment is a challenging task due to typically higher power needs and more adverse cooling requirements of new equipment. To cope with the increase of the power and heat load in DCs, load spreading is commonly applied. This technique distributes the thermal load of new equipment over multiple racks if the power requirement and heat generation of new equipment exceeds the rack's capacity. We present a novel load spreading technique that allows upgrading of the computing equipment with minimal thermal impact on the existing optimized DC cooling environment. Our approach is based on an abstract heat-flow model of the DC, whose parameters are determined by performing a measurement campaign in the DC and with support of computational fluid dynamics simulations. The optimum placement of the new equipment in the racks of the DC is found by applying a particle swarm optimization technique to this model. The effectiveness of our method was assessed based on experiments performed in a production DC. The results show that our holistic approach for optimizing the placement of the upgraded computing equipment in the DC outperforms the conventional load spreading technique.

Data center selection based on neuro-fuzzy inference systems in cloud computing environments

A high-quality service for applications in cloud computing environments is guaranteed by making efficient use of resources in data centers. Applications should be allocated to resources suitable for the load of data centers to achieve this. The complex and dynamic nature of the load prevents the proper selection of one of multiple data centers and fails to meet the demands of resources in applications. An incorrect data center selection seriously lowers resource utilization in the data center and accordingly deteriorates the quality of services for applications. This paper proposes a neuro-fuzzy inference-based prediction scheme to select one of multiple data centers in accordance with application workloads. This scheme is used to aggressively capture the time-varying load of data centers by learning and predicting the availability of resources therein. Therefore, it predicts not only the present load but also the future load of data centers in the process of determining a suitable data center. By an autonomic control for data center selection, our scheme can also provide load balancing between data centers. Moreover, we present performance evaluations with experiments based on Xen testbeds to demonstrate the effectiveness of our scheme. The experimental results show that our scheme is superior to other selection schemes with regard to the entire and changed loads of data centers.