Data Center Management Research Articles

A generalized petri net-based modeling framework for service reliability evaluation and management of cloud data centers

A cloud data center is a critical infrastructure whose service reliability is relevant for service delivery. Constituting the carrier of service for cloud computing, the IT architecture of a cloud data center plays an important role, since it directly relates to service reliability. However, most existing research focuses only on the connectivity of the IT architecture and on service considering only the processing procedure. In order to bridge the gap between the existing works and reality, a hierarchical colored generalized stochastic petri net is proposed to evaluate the service reliability by Monte Carlo simulation, which comprehensively considers the connectivity and performance of the IT architecture and the dynamic of service delivery. The modeling and simulation framework is applied to the cloud data center of an insurance company and cost-effective strategies are found to support the configuration, operation and maintenance of the cloud data center.

Thermal Prediction for Efficient Energy Management of Clouds Using Machine Learning

Thermal management in the hyper-scale cloud data centers is a critical problem. Increased host temperature creates hotspots which significantly increases cooling cost and affects reliability. Accurate prediction of host temperature is crucial for managing the resources effectively. Temperature estimation is a non-trivial problem due to thermal variations in the data center. Existing solutions for temperature estimation are inefficient due to their computational complexity and lack of accurate prediction. However, data-driven machine learning methods for temperature prediction is a promising approach. In this regard, we collect and study data from a private cloud and show the presence of thermal variations. We investigate several machine learning models to accurately predict the host temperature. Specifically, we propose a gradient boosting machine learning model for temperature prediction. The experiment results show that our model accurately predicts the temperature with the average RMSE value of 0.05 or an average prediction error of 2.38 °C, which is 6 °C less as compared to an existing theoretical model. In addition, we propose a dynamic scheduling algorithm to minimize the peak temperature of hosts. The results show that our algorithm reduces the peak temperature by 6.5 °C and consumes 34.5 percent less energy as compared to the baseline algorithm.

Time-constrained and network-aware containers scheduling in GPU era

The recent advances on data center management and applications development are reflected by lightweight containers technology and critical Quality-of-Service (QoS) requirements. Tenants encapsulate applications in containers abstracting away details on the infrastructure, and entrust its management framework with the provisioning of network and time QOS requirements. In this paper, we addressed this NP-hard scheduling problem proposing a GPU Accelerated Containers Scheduler (GPUACS). We model the joint allocation of network and containers with QoS requirements as a graph embedding problem. GPUACS innovates by refactoring two Multicriteria Decision Makings (MCDMs) to GPU model, as well as by defining an efficient data structure to speed up the comparison of time-evolving QoS requirements. GPUACS follows a modular and configurable architecture, and the scheduling objective function can be adjusted by selecting the MCDM method and setting the appropriated weights to guide the comparisons. An experimental analysis demonstrated the sensitivity that GPU-tailored MCDM methods have to schedule container requests considering critical time, network, and processing criteria, as well as multiple queueing policies.

Data Centers Optimized Integration with Multi-Energy Grids: Test Cases and Results in Operational Environment

In this paper, we address the management of Data Centers (DCs) by considering their optimal integration with the electrical, thermal, and IT (Information Technology) networks helping them to meet sustainability objectives and gain primary energy savings. Innovative scenarios are defined for exploiting the DCs electrical, thermal, and workload flexibility as a commodity and Information and Communication Technologies (ICT) are proposed and used as enablers for the scenarios’ implementation. The technology and scenarios were evaluated in the context of two operational DCs: a micro DC in Poznan which has on-site renewable sources and a DC in Point Saint Martin. The test cases’ results validate the possibility of using renewable energy sources (RES) for exploiting DCs’ energy flexibility and the potential of combining IT load migration with the availability of RES to increase the amount of energy flexibility by finding a trade-off between the flexibility level, IT load Quality of Service (QoS), and the RES production level. Moreover, the experiments conducted show that the DCs can successfully adapt their thermal energy profile for heat re-use as well as the combined electrical and thermal energy profiles to match specific flexibility requests.

Aggregating data center measurements for availability analysis

SummaryA data center infrastructure is composed of heterogeneous resources divided into three main subsystems: IT (processor, memory, disk, network, etc.), power (generators, power transformers, uninterruptible power supplies, distribution units, among others), and cooling (water chillers, pipes, and cooling tower). This heterogeneity brings challenges for collecting and gathering data from several devices in the infrastructure. In addition, extracting relevant information is another challenge for data center managers. While seeking to improve the cloud availability, monitoring the entire infrastructure using a variety of (open source and/or commercial) advanced monitoring tools, such as Zabbix, Nagios, Prometheus, CloudWatch, AzureWatch, and others is required. It is often common to use many monitoring systems to collect real‐time data for data center components from different subsystems. Such an environment brings an inherent challenge stemming from the need to aggregate and organize the whole collected infrastructure data and measurements. This first step is necessary prior to obtaining any valuable insights for decision‐making. In this paper, we present the Data Center Availability (DCA) System, a software system that is able to aggregate and analyze data center measurements aimed toward the study of DCA. We also discuss the DCA implementation and illustrate its operation, monitoring a small University research laboratory data center. The DCA System is able to monitor different types of devices using the Zabbix tool, such as servers, switches, and power devices. The DCA System is able to automatically identify the failure time seasonality and trend present in the collected data from different devices of the data center.

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.

Information and Memory in Dynamic Resource Allocation

We propose a general framework, dubbed stochastic processing under imperfect information (SPII), to study the impact of information constraints and memories on dynamic resource allocation. The framework involves a stochastic processing network (SPN) scheduling problem in which the scheduler may access the system state only through a noisy channel, and resource allocation decisions must be carried out through the interaction between an encoding policy (that observes the state) and an allocation policy (that chooses the allocation). Applications in the management of large-scale data centers and human-in-the-loop service systems are among our chief motivations. We quantify the degree to which information constraints reduce the size of the capacity region in general SPNs and how such reduction depends on the amount of memories available to the encoding and allocation policies. Using a novel metric, capacity factor, our main theorem characterizes the reduction in capacity region (under “optimal” policies) for all nondegenerate channels and across almost all combinations of memory sizes. Notably, the theorem demonstrates, in substantial generality, that (1) the presence of a noisy channel always reduces capacity, (2) more memory for the allocation policy always improves capacity, and (3) more memory for the encoding policy has little to no effect on capacity. Finally, all of our positive (achievability) results are established through constructive, implementable policies.

Blockchain-based decentralized workload and energy management of geo-distributed data centers

Minimizing the costs of cloud services is important for cloud service providers to grow their business. In cost calculation of cloud services, power consumption cost is a major factor. The variability present in renewable power generation, electricity price, and power demand variates the power utilization expenditures. Due to high computational requests, datacenters consume enormous energy every day, thereby necessitating the need for energy efficient designs. Therefore, an energy consumption cost reduction mechanism is required to optimize the data center’s power consumption cost locally and to have the option to redistribute the workload on geo-distributed data centers in peak hours for further reduction in power consumption cost. In this paper, the authors investigate the energy consumption cost optimization problem in cloud datacenters and propose a blockchain-based decentralized workload distribution and management model. Moreover, we minimize request scheduler time for transferring any job from one data center to another and secure the energy cost optimization process due to shut down/ communication failure. The proposed work is the primitive to present the energy cost optimization problem in geo-distributed data centers by introducing blockchain-based secure workload scheduling method considering both the temporal and spatial disparities associated with electricity tariffs and workload arrival process. The simulations are evaluated on real-world workload of the Google data center and associated electricity tariffs. The blockchain-based decentralized workload management framework is evaluate based on privacy and security analysis, update overhead, latency, and throughput. Moreover, the results show blockchain model migrate workload in minimum 46 % reduced time compared to conventional model.

The Perioperative and Anesthetic Adverse Events in Thailand (PAAd Thai) Study of Endobronchial Intubation: An Analysis of 2,000 Incident Reports

Background: The Royal College of Anesthesiologists of Thailand hosted a multicentered project, namely the Perioperative and Anesthetic Adverse Events in Thailand (PAAd Thai) Study. Objective: The aims of the present study were to investigate incidences, contributing factors and suggested preventive strategies of anesthesia-related complications particularly the endobronchial intubation (EBI). Materials and Methods: The PAAd Thai study was a collaborative incident report among 22 hospitals across Thailand. After approval by the Institutional Ethical Committee, the structured incident report together with open ended data record form of anesthesia-related complications such as cardiac arrest, death within 24 hours, and respiratory complications including EBI were requested to be sent to the data management center together with monthly statistics of anesthesia service in each hospital for 12 months (between January 2015 and December 2015) on an anonymous and voluntary basis. The EBI reports were reviewed by three anesthesiologists. Any discretion was discussed to achieve a consensus. Descriptive statistics were used. Results: Among the first 2,000 incident reports, there were 23 EBIs, at the rate of 1.06:10,000 (95% CI 0.62 to 1.49) or 1.15% of all reports. Two-thirds of the incidents occurred in patients with age less than 5 years old and more than 60 years old, and in elective cases. The common sites of surgery were trunk, head and neck, and laparoscopic procedures. EBIs were diagnosed by pulse oximeter (13 cases, 54.0%), increased airway pressure (four cases, 17.2%) and clinical monitoring (four cases 17.2%). Common phases of detection were pre-induction (one case, 4.3%), induction (nine cases, 39.2%), maintenance (12 cases, 52.2%), and emergence (one case, 4.3%). Contributing factors were lack of knowledge, inexperience, and haste, while factors minimizing the incidents were having experience and vigilance. Suggested preventive strategies were additional training, including simulation, practice guidelines, improvement of supervision, and communication. Conclusion: The authors have found that EBI was uncommon, but it is one of the serious anesthesia-related adverse events. It can happen anytime during the entire course of anesthesia. Under these circumstances, careful monitoring and vigilance of the anesthesiologists is essential. Keywords: Anesthesia, Complication, Endobronchial intubation, Intubation, Hypoxia

Low-Cost Datacenter Load Balancing With Multipath Transport and Top-of-Rack Switches

Load balancing in datacenter networks (DCNs) is an important and challenging task for datacenter managers. A number of sophisticated technologies have been proposed to improve load balancing performance in a complicated circumstance, i.e., with various traffic characteristics. Many approaches need a high cost to implement, such as changing switch hardware. The efficiency problem has not been well addressed. MPTCP was proposed as a low-cost approach to improve data transmission in DCNs, which uses subflows to balance workloads across multiple paths. However, current MPTCP is not satisfying, especially when there are rack-local flows or many-to-one short flows. In this article, we propose DCMPTCP to improve the efficacy of MPTCP. We gradually develop three mechanisms. First, DCMPTCP identifies rack-local traffic and eliminates unnecessary subflows to reduce the overhead. Second, DCMPTCP estimates flow length and establishes subflows in a smarter way. Third, DCMPTCP strengthens explicit congestion notification to improve the congestion control performance on inter-rack many-to-one short flows. We have implemented DCMPTCP in both the Linux kernel and ns-3 simulator. Our comprehensive testbed experiments and simulations show that DCMPTCP outperforms MPTCP in both 1 Gbps testbed, and 10 Gbps large-scale simulation network.

Efficacy and safety of fire needle therapy for blood stasis syndrome of plaque psoriasis: protocol for a randomized, single-blind, multicenter clinical trial

BackgroundFire needle therapy is a characteristic treatment in traditional Chinese medicine (TCM). An increasing number of studies have indicated that fire needle treatment for psoriasis provides satisfactory results with few side effects and a low recurrence rate. We herein describe the protocol for a multicenter, randomized, single-blind, placebo-controlled trial that will provide high-quality evidence on the efficacy and safety of fire needle therapy for plaque psoriasis.MethodsNinety-two patients with blood stasis syndrome (BSS) of plaque psoriasis will be enrolled and randomly assigned to receive fire needle therapy (intervention group) or fire needle control therapy (control group) once a week for 4 weeks. The Psoriasis Area and Severity Index (PASI) score will serve as the major efficacy index, while the body surface area (BSA), Physician Global Assessment (PGA) score, Dermatology Life Quality Index (DLQI) score, patient-reported quality of life (PRQoL), visual analog scale (VAS) score for itching, TCM symptom score, and relapse rate will be assessed as secondary outcomes. The PASI score, BSA, PGA score, and VAS score for itching will be evaluated at baseline and during the 4-week treatment and follow-up periods. DLQI score, PRQoL, and TCM symptom score will be assessed at baseline and during the treatment period. Recurrence will be evaluated during the follow-up period. Safety assessments include vital sign monitoring, routine blood tests, blood biochemistry, routine urine tests, pregnancy tests, physical examinations, and adverse-event recording. SAS software will be used for data analysis. The data network platform will be designed by the data management center of Nanjing Ningqi Medical Technology Co., Ltd.DiscussionIt is believed that fire needle therapy can activate the meridians, promote blood circulation, and regulate skin immunity. BSS of plaque psoriasis is related to not only immune dysfunction but also poor or stagnant blood flow. We anticipate that the results of the trial described in this protocol will provide strong evidence for the safety and efficacy of fire needle therapy for BSS of plaque psoriasis.Trial registrationClinicaltrials.govNCT03953885. Registered on May 15, 2019. Name: Fire Needle Therapy on Plaque Psoriasis with Blood Stasis Syndrome

Horizontal-to-Vertical Spectral Ratio (HVSR) IRIS Station Toolbox

AbstractThe horizontal-to-vertical spectral ratio (HVSR) for seismic ambient noise is a popular method that can be used to estimate the predominant frequency at a given site. In this article, we introduce the Incorporated Research Institutions for Seismology (IRIS) Data Management Center’s (DMC’s) openly available HVSR station toolbox. These tools offer a variety of ways to compute the spectral ratio by providing different averaging routines. The options range from the simple average of spectral ratios to the ratio of spectral averages. Computations take advantage of the available power spectral density estimates of ambient noise for the seismic stations, and they can be used to estimate the predominant frequency of the many three-component seismic stations available from the IRIS DMC. Furthermore, to facilitate the identification of the peaks in HVSR profiles for the assessment of the predominant frequency of station sites, the toolbox can also process the results of HVSR analysis to detect and rank HVSR peaks. To highlight the toolbox capabilities, three different examples of possible use of this toolbox for routine site-effect analysis are discussed: (1) site effects related to thawing in Arctic regions, (2) ground-motion amplification in urban area, and (3) estimation of station VS30.

A scalable ledger-assisted architecture for secure query processing over distributed IoT data

Massive amount of IoT data poses unique challenges in centralized data management systems. Specifically, IoT data can originate from heterogeneous and distributed sources, and commonly regulations forbid data from different IoT stakeholders to be managed via central governance. To serve for IoT applications, recent proposals leverage distributed ledgers (e.g., blockchains) to function on top of distributed data storage with improved data interoperability. Unfortunately, most of them do not consider data security and privacy in the first place. Along with this transformative paradigm, in this paper, we propose a ledger-assisted architecture for secure distributed IoT data management. This architecture adapts searchable encryption to decentralized storage network to enable encrypted query processing. Meanwhile, it is designed to leverage the distributed ledger to harden both data and query integrity. To deal with continuously generated IoT data, we further devise an efficient secure data insertion protocol, and employ a recent variant of blockchain for users to validate updated query results in a scalable manner. Evaluations on Azure blockchain service confirm the practicality of our proposed architecture.

Probing the Structure of the Crust and Mantle Lithosphere beneath the Southern New England Appalachians via the SEISConn Deployment

AbstractThe eastern margin of North America has been affected by a range of fundamental tectonic processes in the geologic past. Major events include the Paleozoic Appalachian orogeny, which culminated in the formation of the supercontinent Pangea, and the breakup of Pangea during the Mesozoic. The southern New England Appalachians exhibit a particularly rich set of geologic and tectonic structures that reflect multiple episodes of subduction and terrane accretion, as well as subsequent continental breakup. It remains poorly known, however, to what extent structures at depth in the crust and lithospheric mantle reflect these processes, and how they relate to the geological architecture at the surface. The Seismic Experiment for Imaging Structure beneath Connecticut (SEISConn) was a deployment of 15 broadband seismometers in a dense linear array across northern Connecticut. The array traversed a number of major tectonic boundaries, sampling across the Laurentian margin in its western portion to the Avalonian terrane at its eastern end. It also crossed the Hartford rift basin in the central portion of the state. The SEISConn stations operated between 2015 and 2019; data from the experiment are archived at the Incorporated Research Institutions for Seismology Data Management Center and will be publicly available beginning in 2021. A suite of imaging techniques is being applied to SEISConn data, with the goal of providing a detailed view of the crust and mantle lithosphere (including discontinuities, seismic velocities, and seismic anisotropy) beneath the southern New England Appalachians. Results from these analyses will inform a host of fundamental scientific questions about the structural evolution of orogens, the processes involved in continental rifting, and the nature of crustal and mantle lithospheric deformation during subduction, terrane accretion, and continental breakup.

The MAGIC Experiment: A Combined Seismic and Magnetotelluric Deployment to Investigate the Structure, Dynamics, and Evolution of the Central Appalachians

Abstract The eastern margin of North America has undergone multiple episodes of orogenesis and rifting, yielding the surface geology and topography visible today. It is poorly known how the crust and mantle lithosphere have responded to these tectonic forces, and how geologic units preserved at the surface related to deeper structures. The eastern North American margin has undergone significant postrift evolution since the breakup of Pangea, as evidenced by the presence of young (Eocene) volcanic rocks in western Virginia and eastern West Virginia and by the apparently recent rejuvenation of Appalachian topography. The drivers of this postrift evolution, and the precise mechanisms through which relatively recent processes have modified the structure of the margin, remain poorly understood. The Mid-Atlantic Geophysical Integrative Collaboration (MAGIC) experiment, part of the EarthScope USArray Flexible Array, consisted of collocated, dense, linear arrays of broadband seismic and magnetotelluric (MT) stations (25–28 instruments of each type) across the central Appalachian Mountains, through the U.S. states of Virginia, West Virginia, and Ohio. The goals of the MAGIC deployment were to characterize the seismic and electrical conductivity structure of the crust and upper mantle beneath the central Appalachians using natural-source seismic and MT imaging methods. The MAGIC stations operated between 2013 and 2016, and the data are publicly available via the Incorporated Research Institutions for Seismology Data Management Center.

A Peer-to-Peer Data Sharing Framework for Web Browsers

Concerns over data ownership and misuse of personal data over the Web have become increasingly widespread in recent years; especially, as most web service providers are moving towards closed silo-based platforms, making the web more and more centralized. This is concerning, because, as service providers move towards centralized data storage and management, end-users become more susceptible to loss of data ownership and misuse of personal data. While in recent years, quite a few solutions have been proposed to solve these issues, the issues themselves still prevail, primarily due to lack of acceptance. That said, in this paper, we build on our previously proposed browser-based Peer-to-Peer Data Sharing Framework. We first explain the requirements and design choices which we had to keep in mind while designing the framework. And then, we provide insights into how we evaluated the functionalities and security features of the framework, through lab experiments. Finally, we elucidate the direction in which we would like to develop the framework in the near future.

National Institutes of Health StrokeNet During the Time of COVID-19 and Beyond.

National Institutes of Health StrokeNet During the Time of COVID-19 and Beyond.

Installation and Performance of the Albuquerque Seismological Laboratory Small-Aperture Posthole Array

AbstractThe Global Seismographic Network (GSN) has been used extensively by seismologists to characterize large earthquakes and image deep earth structure. Although the network’s original design goals have been met, the seismological community has suggested that the incorporation of small-aperture seismic arrays at select sites may improve performance of the network and enable new observations. As a pilot study for this concept, we have created a 500 m aperture, nine-element broadband seismic array around the GSN station ANMO (Albuquerque, New Mexico) at the U.S. Geological Survey Albuquerque Seismological Laboratory (ASL). The array was formed by supplementing the secondary borehole seismometer (90 m depth) at ANMO with eight additional 2.6 m posthole sites. Each station’s seismometer was oriented using a fiber optic gyroscope to within 2.0° of north. Data quality, particularly on the vertical components, is excellent with median power levels closely tracking the secondary sensor at ANMO at frequencies lower than 1 Hz. Horizontal component data are more variable at low frequencies (<0.02 Hz), with the type of installation and local geography appearing to strongly influence the amount of tilt-induced noise. Throughout the article, we pose several fundamental questions related to the variability and precision of seismic wavefield measurements that we seek to address with data from this array. In addition, we calculate the array response and show a few examples of using the array to obtain back azimuths of a local event and a continuous narrowband noise source. The apparent velocity of the event across the array is then used to infer the local P-wave velocity at the ASL. Near-real-time data collected from the array along with collocated meteorological, magnetic, and infrasound data are freely available in near-real time from the Incorporated Research Institutions for Seismology Data Management Center.

Design of Intelligent Operation and Inspection Management System for Power Grid Equipment Based on Full Business Data Center

There are some problems in the existing operation and inspection systems of State Grid Corporation of China, such as low level of system data integration, poor degree of functional application practicality. In order to solve these problems, the intelligent operation and inspection management system for power grid equipment has been designed based on full business data center. This system complies with the overall deployment requirements of the Internet of Things, including sensing layer, network layer, platform layer, and application layer. Based on the unified storage and management of the full business data center, the integration and service call of data information from 14 sets of operation and inspection systems could be realized. As a result, holographic perception of equipment status, active fault warning and prediction, and intelligent generation of operation and inspection decision could be realized by the designed system, which can promote the transformation of operation and inspection mode from business process driven to equipment status driven.

Online traffic-aware linked VM placement in cloud data centers

In cloud computing, virtual machine (VM) placement plays a crucial role in data center (DC) management, as different ways of VM placement may require different system resources.As Cisco research reveals that virtualization of DC increases traffic within the DC and causes network bandwidth to become scarce resource, recent researches have been focusing on traffic-aware VM placement. However, previous traffic-aware VM placement schemes treat the VM placement as a static process in that they do not take into account the impact of the current placement decision on the subsequent placement. In this paper, we thus propose a novel online traffic-aware VM placement scheme. Our scheme views VM placement as a context-sensitive dynamic process in that the decision of every step of the placement is made aiming at helping the subsequent steps of placement to reduce the required network bandwidth in the long run. In our scheme, we consider not only inter-VM traffic but also the bandwidth constraint of a physical machine (PM) when making a VM placement decision. To realize our objective, we put those VMs with close end time in the same or close proximity PMs so that when the VMs are terminated, one can make enough room for the future arrivals so as to not only minimize the number of active PMs but also reduce networking costs. We conduct extensive simulations to verify the superiority of our scheme in terms of networking costs and energy consumption.Simulation results show that our scheme outperforms improved-best-fit-decreasing (IBFD) scheme, a revised best-fit version thattakes inter-VM traffic into account, by 30%–40% on network cost under various scenarios. Our scheme also promises 10%–25% power savingscompared with IBFD.