IT Server Research Articles

Innovative server simulator for data centers and critical indices of performance evaluation

Server simulators, also known as dummy loads, are used to simulate real IT equipment for performance examining of data centers. Without these tests, potential failures could result in significant losses. Due to oversimplified designs and lack of evaluation methods, commercial dummy loads often fail to reflect accurately the true conditions of the real servers in data centers. In this study, a novel dummy-chip server simulator (DCSS) is developed, which can well reproduce the working mechanism of real servers. In this paper, three indices are proposed for the first time to evaluate the performance from different perspectives, i.e. Coefficient of Heat Removal (CHR) for heat removal capability, Coefficient of Temperature Deviation (α) for temperature rating, and Power Usage per Computing (PUC) for energy and computation efficiency. Experimental tests are conducted in this study, and results show that the good performance of the DCSS approaching the real server, and the values of CHR, α, and PUC indicate significant improvements compared to the commercial dummy load. The findings of this study present straightforward guidance for IT server simulator design, and demonstrate the advancement of DCSS and proposed index for data center performance evaluation.

Sustainability of Data Center Digital Twins with Reinforcement Learning

The rapid growth of machine learning (ML) has led to an increased demand for computational power, resulting in larger data centers (DCs) and higher energy consumption. To address this issue and reduce carbon emissions, intelligent design and control of DC components such as IT servers, cabinets, HVAC cooling, flexible load shifting, and battery energy storage are essential. However, the complexity of designing and controlling them in tandem presents a significant challenge. While some individual components like CFD-based design and Reinforcement Learning (RL) based HVAC control have been researched, there's a gap in the holistic design and optimization covering all elements simultaneously. To tackle this, we've developed DCRL-Green, a multi-agent RL environment that empowers the ML community to design data centers and research, develop, and refine RL controllers for carbon footprint reduction in DCs. It is a flexible, modular, scalable, and configurable platform that can handle large High Performance Computing (HPC) clusters. Furthermore, in its default setup, DCRL-Green provides a benchmark for evaluating single as well as multi-agent RL algorithms. It easily allows users to subclass the default implementations and design their own control approaches, encouraging community development for sustainable data centers. Open Source Link: https://github.com/HewlettPackard/dc-rl

What Caused the EHR to Crash? Lessons Learned

After a power disruption in a medical office building led to a catastrophic shutdown of the IT servers and ultimately to a loss of the use of EHR and administrative IT systems, a root cause analysis was applied to identify the security threats to the IT systems of a multispecialty group and ways to mitigate this threat in the future.

Inquisitive Genetic-Based Wolf Optimization for Load Balancing in Cloud Computing

Abstract Cloud remains an active and dominant player in the field of information technology. Hence, to meet the rapidly growing requirement of computational processes and storage resources, the cloud provider deploys efficient data centres globally that comprise thousands of IT servers. Because of tremendous energy and resource utilization, a reliable cloud platform has to be necessarily optimized. Effective load balancing is a great option to overcome these issues. However, loading balancing difficulties, such as increased computational complexity, the chance of losing the client data during task rescheduling, and consuming huge memory of the host, and new VM (Virtual Machine), need appropriate optimization. Hence, the study aims to create a newly developed IG-WA (Inquisitive Genetic–Wolf Optimization) framework that meritoriously detects the optimized virtual machine in an environment. For this purpose, the system utilises the GWO (Grey Wolf Optimization) method with an evolutionary mechanism for achieving a proper compromise between exploitation and exploration, thereby accelerating the convergence and achieving optimized accuracy. Furthermore, the fitness function evaluated with an inquisitive genetic algorithm adds value to the overall efficacy. Performance evaluation brings forward the outperformance of the proposed IGWO system in terms of energy consumption, execution time and cost, makespan, CPU utilization, and memory utilization. Further, the system attains more comprehensive and better results when compared to the state of art methods.

Experimental investigation of a data-centre cooling system using a new single-phase immersion/liquid technique

This paper presents an experimental investigation conducted on a new single-phase immersion/liquid-cooling technique developed at the OVHcloud laboratory, combining a direct-to-chip water-cooling system with passive single-immersion cooling technology. The experimental setup tested the impact of three dielectric fluids (S5X, SmartCoolant and ThermaSafe R), the effect of the water circuit configuration, and the server power/profile. Results suggest that the system cooling demand depends on the fluid's viscosity. As the viscosity increased from 4.6 to 9.8 mPa s, the cooling performance decreased by approximately 6%. Moreover, all the IT server profiles were validated at various water inlet temperatures and flow rates. The energy performance of the proposed technique and the liquid-cooling system previously used by OVHcloud was compared at a 600 kW data centre (DC). The proposed technique showed a reduction in the DC electrical power consumption by at least 20.7% compared to the liquid-cooling system. Finally, the cooling performance of the air- and liquid-cooled systems and the proposed solution was compared computationally at the server level. When using the proposed solution, the energy consumed per server was reduced by at least 20% compared with the air-cooling system and 7% compared with liquid-cooling system.

Fan-noise reduction of data centre telecommunications’ server racks, with an acoustic metamaterial broadband, low-frequency sound-absorbing liner

An acoustic metamaterial is evaluated successfully as a means to reduce axial fan noise in an IT server rack application. The continuing growth in demand for cloud-based memory storage is outpacing sustainable energy management which still requires the axial fan as a fundamental component in temperature control technologies. As chip temperatures increase, additional numbers of more powerful fans are required to run faster with the result that data centres have become unsafe working environments due to the acoustic output exceeding prescribed occupational noise level limits. Noise isolation using soundproof cabinets is expensive and impractical in data centres which seek to reduce floor space and communication losses. Instead, in this work, a 15 mm deep acoustic liner solution is proposed being the approach taken in the aeronautics sector to reduce aeroengine noise which, similarly, is a flow duct problem. The acoustic metamaterial adopted here is the recently developed Segmented Membrane Sound Absorber (SeMSA) which can be tailored for low frequency, broadband and tonal noise in a thin form-factor and which can be used in a grazing flow configuration. An equivalent circuit model developed for the SeMSA allows its design to be optimised to attenuate a typical server fan’s frequency spectrum. An array of manufactured rectangular SeMSA cells was embedded in a “deflector plate”, which is an existing component in a server rack. The deflector plate was implemented in a custom-built fan sound power rig, tested in an hemi-anechoic chamber and compared to a hardwall case and to PU foam. A relative overall decrease of 2.5 dBA was achieved for the SeMSA deflector plate liner which corresponds to a 43.9% decrease in overall sound emissions, which using a material thickness of only 15 mm, signifies an almost twofold increase in the time required for hearing damage to occur. A 3 dBA drop was achieved at the blade passing frequency of 620 Hz, while relative drops of 1–2.5 dBA were achieved from 2000–8000 Hz.

Foundations for New Media Nodes

According to the European Broadcasting Union (EBU), broadcasting “should strive to reuse, as much as possible, existing IT and Internet Standards to leverage the research and development investments of this much wider industry. [Broadcast workflows] should be implementable in software running on standard IT servers, so enabling flexible, agile and scalable infrastructures.” We outline three foundational layers of Accelerated Server Hardware, Virtualization, and Software Composability that together facilitate this goal. We explain how the technologies in these layers can be applied to build unlimited Media Nodes that can run anywhere and be managed with standard IT and data center tools.

Finite time thermodynamic analysis and optimization of water cooled multi-spilit heat pipe system (MSHPS)

• Energy saving in data centers is increasingly with the developing IT industry. • An accurate performance and evaluation model based on time cycle is proposed. • An periodic integral energy efficiency model is proposed. • The refrigerant flow distribution characteristic of MSHPS was built and tested. • The proposed method is fit for analysis of MSHPS and the real pipe-net systems. This study focuses on the heat transfer characteristics of the evaporation terminal, the cool distribute unit (CDU) and refrigerant flow distribution of a water cooled multi-spilit heat pipe system (MSHPS) used in data center. The finite time thermodynamic analysis, the exergy method and the software SIMULINK was employed to build the simulation model of the combined system. The results show that the IT servers should concentrate on arranging at the location below 1.3 m. The CDU has a heat transfer of about 74 J in a period of 6 s. And the optimum flow rate of the CDU is 0.82 kg/s. The flow distribution characteristic of a CDU which connect 2 heat pipe evaporator terminals of 6 kW was calculated, and the working fluid is R22. Then the free cooling time,part time free cooling and energy saving potential in major cities of China were analysised. The energy saving potential is from 61% to 25%. The results are of great significance for the operational control and practical application of a MSHPS and other pipe-net systems.

Experimental investigation of a novel micro-channel flat loop heat pipe (MC-FLHP) for data center cooling and heat recovery

ABSTRACT In this paper, a novel micro-channel flat loop heat pipe (MC-FLHP) for data center cooling and heat recovery is proposed, which has the following novelties and distinguished advantages, i.e., a tightly attached flat heat pipes array with IT server thus reaching a ‘server level’ cooling for data center, several pre-set micro-grooves which increases the convective heat transfer coefficient, and a separated evaporator-condenser which greatly improves the flexibility of the system’s installation. The proposed system with R134a (filling ratio of 30%) as the working fluid is designed, constructed and tested, and the testing results are used to evaluate its thermal recovery efficiency and its impact factors, i.e., simulated heat load, cooling water inlet temperature and height difference between the evaporator and condenser. Under the range of test conditions (e.g., simulated heat load from 500 W to 3000 W, cooling water inlet temperature from 15°C to 24°C, height difference from 0.6 m to 1.0 m), the overall thermal recovery efficiency is in the range 57.34% to 84.52%. It is found that under the specific operational conditions with the simulated heat load of 500 W, cooling water inlet temperature of 15°C, and height difference between the evaporator and the condenser of 0.8 m, a peak thermal recovery efficiency of 84.52% is achieved. This study can help achieve the global goals of green and sustainable data center, and also save data center energy consumption and thus operational costs.

Economic analysis of hydrogen-powered data center

The data center needs more and more electricity due to the explosive growth of IT servers and it could cause electricity power shortage and huge carbon emission. It is an attractive and promising solution to power the data center with hydrogen energy source. The present work aims to conduct an economic analysis on the hydrogen-powered data center. Configurations of hydrogen-powered and traditional data centers are compared and the differences focus on backup power system, converter/inverter, fuel cell subsystem, carbon emission, hydrogen and electricity consumptions. Economic analysis is conducted to evaluate the feasibility to power the data center with hydrogen energy source. Results show that electricity price increasing rate and hydrogen cost are the main factors to influence economic feasibility of hydrogen-powered data center. When the electricity price keeps constant in the coming two decades, the critical hydrogen price is about 2.8 U.S. dollar per kilogram. If the electricity price could increase 5% annually due to explosive growth of electric vehicles and economy, critical hydrogen price will become 6.4 U.S. dollar per kilogram. Hydrogen sources and transportation determine the hydrogen price together. Hydrogen production cost varies greatly with hydrogen sources and production technologies. Hydrogen transport cost is greatly influenced by distances and H2 consumptions to consumers. It could be summarized that the hydrogen-powered data center is economic if hydrogen could be produced from natural gas or H2-rich industrial waste streams in chemical plant and data center could not be built too far away from hydrogen sources. In addition, large-scale hydrogen-powered data center is more likely to be economic. Solar hydrogen powered data center has entered into a critical stage in the economic feasibility. Solar hydrogen production cost has restrained the H2 utilization in data center power systems now, since it could be competitive only when more strict carbon emission regulation is employed, hydrogen production cost reduces greatly and electricity price is increasing greatly in the future. However, it could be expected solar hydrogen-powered system will be adopted as the power source of data centers in the next few years.

Don't Let Electronic Monitoring of Employees Hand an Issue to Unions

Most union campaigns begin with morale problems. Issues concerning fair treatment, most union organizers agree, are what initially motivate most workers to seek out a union. One practice that has been known to create impressions of unfairness is electronic monitoring of production and employee work tasks. Surveillance cameras can be easily acquired through any online retailer and installed simply. IT servers can easily be scoured for e‐mails and internet activity. Computerized time‐keeping systems track to the minute “on” and “off” time. Automatic toll records and GPS devices continuously record where employees are. Our world makes it easy for an employer to be “big brother.” Not surprisingly, many employees resent their employer's perceived mistrust or intrusions into their privacy.

WITHDRAWN: An energy efficient load balancing on cloud computing using adaptive cat swarm optimization

Cloud has been a dominant player in information technology in recent years. To meet the growing demands for computing and storage resources, cloud providers deploy data centers (DC) across the globe that includes hundreds of thousands of IT servers. Due to massive energy use, every DC leave a huge carbon footprint and thus, have bad effects on the environment. Because of this, efficient computing resource utilization and minimization of energy usage are critical issues to create cloud computing more booming. Efficient load balancing is the primary means of solving these problems. In order to overcome optimization problems, this study has developed a load balancing system using adaptive cat swarm optimization (ACSO) algorithm. The efficiency of the proposed technique is analyzed by using different value metrics and performance differentiated with other methods.

Virtual CPU Scaling for Efficient Server Power Consumption in Cloud Data Center

Cloud computing is a fast-growing technology used by major corporations these days because of the flexibility framework it provides to consumers. Cloud technology requires large data centers consisting of multiple IT equipment and servers. One main problem with these data centers is the vast amount of power consumed during servers operation. This reduces financial benefit and increases the need to produce more energy to cover the needs of operating the cloud infrastructure. This paper proposes an approach for managing the virtual central processing unit (vCPU) of a virtual machine to improve server power efficiency. A framework is used to study the proposed approach while processing different types of workloads widely found in most general-purpose cloud computing applications. Results indicate an improvement in server power saving.

Finite time thermodynamic analysis of water cooled multi-spilit heat pipe system

Energy saving in data centers is increasingly important along with the rapidly developing IT industry. A integrated heat pipe air conditioning (AC) system which used chilled water unit and heat pipe heat exchanger (HPHE) was proposed.With the meteorological parameter of Changde city (31°53′N and 117°15′E) as the reference. The thermodynamic simulation software SIMULINK was employed in build the simulation model of the combined system. And it is compared with the traditional air-conditional system. The system include heat pipe evaporator cooling deliver unit (CDU) and the cold source. A time integral model for heat transfer of heat pipe evaporator is proposed. A heat pipe evaporator of a 12KW in the company was taking as an example. The results show that the time period of working fluid passing through the heat exchanger is about 6 seconds. When the dry degree is greater than 0.72, the heat transfer efficiency is low. When arranging the IT server, we should concentrate on the location below 1.3 meters. The CDU was treated as a condenser. Then, the cooling source is vapor compressor. The finite time thermodynamic and the exergy method were employed to analysis the heat exchanger and the compress processes.The results show that the former one has saved 26% of the energy. Then the using time and energy saving potential in major cities of China were investigated and studied.

Abstract P2-13-16: A multidisciplinary approach to implement personalized multifaceted care plans in standard breast cancer care: A quality improvement project

Abstract Background: IOM, ASCO and Commission on Cancer have emphasized the provision of survivorship care plans (SCPs) to cancer patients. Cancer Care Ontario (CCO) aims to ensure that SCPs are developed and shared with healthcare providers (HCPs) to facilitate integrated cancer care. In 2016, a randomized mixed-methods study at St. Michael’s Hospital (SMH) provided a paper based Personalized Multifaceted Care Plan (PMCPs) to breast cancer (BC) patients, which included an upfront treatment plan. The PMCP was generated by entering non-repetitive patient data into a care plan database software developed by the team. The study results showed that patients and primary care providers (PCPs) found PMCP to be useful. Despite the benefits, implementation of SCPs as standard of care remained a challenge due to lack of designated personnel for developing SCP and limited resources causing poor provider buy-in. In 2017, we initiated a quality improvement (QI) project to implement the PMCP by integrating it into existing workflow by involving the care team. Methods: This REB approved QI project was done in two phases. Phase 1 was to identify key members to create the PMCP and to secure the software to the SMH IT server. In phase 2, the PMCPs were delivered to newly diagnosed invasive BC patients, receiving chemotherapy. The PMCPs were also shared with respective PCPs. At SMH, new patients diagnosed with BC are seen initially at the Multidisciplinary Clinic (MDC) by a medical and radiation oncologist, and a patient navigator (PN) to plan treatment. In phase 1, the PN who coordinated the MDC was identified as the most appropriate care team member to initiate the PMCP. To incorporate the PMCP into the PN’s existing workflow, a Transfer of Accountability (TOA) document was designed using the care plan software to replace a patient summary that was created in silos. The TOA was electronically shared with the team and had most of the information provided in the PMCP. The primary outcome measures were proportion of information completed to generate the PMCP and care plans delivered by patients’ care team. Secondary Outcome measures were patient and provider satisfaction with PMCP assessed using surveys at three time points and single time point respectively. Data were summarized using median and IQR as well as frequency and percentages. Data was also shared at QI team meetings, practice patterns were observed for changes and incorporated into subsequent PDSA cycles. Results: From 2017 to 2019, 90% (120/134) of eligible BC patients were provided with the PMCP. At the first 2 PDSA cycles 100% PMCP preparation and delivery was done by research staff. We have achieved 80% compliance in Phase 1 by involving the PN in data entry for PMCP while preparing the TOA document. TOA had been incorporated into standard of care at MDC and a recent nursing project found that HCPs surveyed perceived TOA to be a useful tool in information exchange and care coordination. Patient satisfaction surveys for PMCP found their responses were consistent over all time points with high levels of agreement. Surveys also showed that 73% (86/117) patients agreed that the PMCP helped with communication with their PCPs and 81% (95/117) agreed it helped with communication with the team. Of the 25 PCPs and 5 oncology HCPs surveyed, 91% (22/25) PCPs and 100% (5/5) oncology HCPs agreed that the PMCP should be incorporated into BC care. Conclusions: Implementation of SCPs with a multidisciplinary approach is feasible in BC care. Integration of SCPs within the existing work flow and involvement of members of the care team can lead to increased SCP uptake, better care coordination, sustainability and provider buy-in. With the high patient and provider satisfaction with PMCP, and recommendation by CCO, we are in the process of integrating PMCPs for BC patients as standard of care in the oncology clinic. Citation Format: Rashida Haq, Amy Kong, Ronita Lee, Geetha Mukherji, Christine Brezden-Maesley, Pauline Gulasingam. A multidisciplinary approach to implement personalized multifaceted care plans in standard breast cancer care: A quality improvement project [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P2-13-16.

Development and experimental study of an independent row-based cooling system for improving thermal performance of a data center

As the power density of IT equipment increases, the requirements for data center facilities are also becoming more rigorous. In addition to higher IT power density, cooling has become a key issue in data centers where cooling accounts for about 40% of total energy usage. An improved independent row-based data center cooling system has been suggested, and is found to be the better efficient in removing heat output of IT equipment based on the observations and experimental results from two cooling strategies. This study, that is practice-based learning in a legacy data center remodeling project, has evaluated the energy and thermal performance of two data center cooling approaches: an improved independent row-based cooling and a conventional room-based cooling. The air temperature, humidity and air distribution efficiency of an IT environment were examined by using field measurements and six performance indices. The differences and technical features of this experimental study is that two different forms of cooling systems were evaluated based on the same IT environment conditions; location of the IT equipment and the cooling load in same IT server room. The results show that data center cooling systems utilizing the “the fully containment of cold and hot aisles” technique are very effective at removing heat load of IT servers. The advantage of row-based cooling is that it is located close to hot spots and does not experience the heat losses generated in the air delivery path of the room typical of room-based cooling systems. SHI and RHI were improved by 37.1% and 20.0%, and RTI and β were improved by 73.2% and 44.3% respectively. According to the observations and index evaluation results, we suggest that a new independent row-based cooling strategy is more efficient for server cooling. Air management helps to reduce cooling energy by enhancing optimal operation and improving cooling system efficiency. Furthermore, metrics play a significant role in providing performance indices for air management systems.

Modeling temperature distribution and power consumption in IT server enclosures with row-based cooling architectures

Traditional data center cooling methods cannot yet control cooling airflows and temperatures on demand, creating an intrinsic inefficiency. A recent solution places row-based cooling unit adjacent to servers and places the entire assembly within an enclosure, which improves airflow distribution and provides rapid real-time control. This is, in particular attractive for micro-data centers where traditional room-based cooling is less energy efficient. Spatiotemporal predictions of temperatures are required to control and optimize data center performance as the system configuration, and other parameters are varied. Current methods, such as proper orthogonal decomposition,machine learning, and heuristic models are inapplicable in practice because they require a prohibitively large number of a priori simulations or experiments to generate training datasets. We provide an alternative a computationally inexpensive training-free model for enclosedmicro-data centers that are integrated with in-row cooling units that requires no a priori training. The model determines the air flowrate within each zone based on a mechanical resistance circuit analysis. These flowrates are then introduced into a zonal energy balance to predict the temperature of each zone. The methodology is validated with experimental measurements and coupled with a power consumption calculation. Its applicability is demonstrated by evaluating the influence of various system factors, such as IT server configurations, cooling unit air, and water flowrates and the numbers of cooling units, on the temperature distributions, and total cooling power consumption. The method can improve micro-data centers control and help to optimize the design of any data center with a row-based cooling system.

Performance of a rack mountable cooling unit in an IT server enclosure

Almost thirty percent of the power consumption in a data center (DC) is attributable to the cooling of IT equipment (ITE). This offers opportunities to reduce a DC’s energy budget by considering alternatives to traditional cooling methods, such as perimeter or in-row air-conditioners, which suffer from inherent airflow deficiencies, e.g., hot air recirculation and cold air bypass. Due to these deficiencies, not enough cold air is supplied to the ITE, leading to hot spots that reduce equipment life significantly. Rack mountable cooling units (RMCUs), i.e., air-handlers mounted within the same enclosure containing the ITE, do not face this problem due to their proximity to servers. However, a proper understanding of airflow and temperature distribution inside an enclosure containing an RMCU has not yet been developed, preventing its widespread adoption. We investigate the temperature and airflow for various ITE configurations to determine the efficacy of an RMCU inside an enclosed rack. Experiments reveal that the principal factor influencing the temperature distribution is the leakage of warm air through passive servers, a hitherto unreported facet, which is dependent on the locations of these servers, IT load density and distribution, and cold chamber depth. This is also illustrated through a neural network model. The results help us to devise a design strategy to optimize ITE configurations with desirable temperature distributions, and to inform server workload assignments.

Thermal performance evaluation of a high-density data centre for cooling system under fault conditions

In this study, an actual 20 MW data centre project was analysed to evaluate the thermal performance of an IT server room during a cooling system outage under six fault conditions. In addition, a method of organizing and systematically managing operational stability and energy efficiency verification was identified for data centre construction in accordance with the commissioning process. It is essential to understand the operational characteristics of data centres and design optimal cooling systems to ensure the reliability of high-density data centres. In particular, it is necessary to consider these physical results and to perform an integrated review of the time required for emergency cooling equipment to operate as well as the back-up system availability time.

Real-time temperature predictions in IT server enclosures

Current data center (DC) cooling architectures are inefficient due to (1) inherent airflow efficiencies and (2) their inability to spatiotemporally control cooling airflow and DC temperatures on demand. Rack-based cooling is a promising recent alternative since it provides more effective airflow distribution and is more amenable to rapid real-time control. A control scheme should be able to predict spatiotemporal temperature changes as the system configuration and parameters change, but a suitable method is not yet available. Existing approaches, such as proper orthogonal decomposition or machine learning are unsuitable because they require an inordinately large number of a priori simulations or experiments to generate a training dataset. We provide an alternative real-time temperature prediction tool which requires no a priori training for DC server enclosures into which a rack mountable cooling unit (RMCU) has been integrated. This new model is validated with experimental measurements and its applicability is demonstrated by separately evaluating the influence of varying IT server configuration, RMCU flowrate, step changes in system conditions, and interactions between multiple RMCUs. The resulting tool will facilitate advanced control techniques and optimize design for any DC rack-based cooling architecture.