Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Datacenters”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

A Transformational Natural Gas Fueled Dynamic SOFC for Data Center in-Rack Power (Final Technical Report)

Data centers consume 250TWh or 1% of global electricity use in 2019. This electricity demand is expected to grow exponentially in the future. The current data center power supply relies on electric grids with diesel engines and batteries as backup; the latter is critically important because a sudden loss of power could erase crucial data, causing catastrophic economic loss. However, such a double protection architecture is costly, inefficient and polluting. In search for better in-rack power system, fuel-cell based generators have recently emerged as a promising alternative to diesel engines and batteries because of its potential to be more cost-effective, more efficient and less polluting. Among many types of fuel cells, solid oxide fuel cells stand out to be a front runner because of their ability to directly operate on natural gas that has an existing infrastructure. However, there are several critical challenges facing SOFC generators to meet the rigorous power requirements of data centers: high cost, poor reliability and more importantly, slow response to the datacenters’ dynamic load change. The unexpected overload conditions in data centers can cause fuel starvation; the latter can initiate microcracks in the anode structure, thus jeopardizing the lifetime of the SOFC generator. The current efforts to increase transient power capabilities of traditional SOFCs and therefore protect SOFC stacks from internal damage during transient loading, rely primarily upon mathematical algorithms. One of the challenges to these control methodologies is the physical limitations of the fuel delivery system such as slow response of mass flow controllers to fast power demand.

30 DIRECT ENERGY CONVERSION↗

Extreme Efficiency 240 Vac to Load Data Center Power Delivery Topologies and Control

The research explored innovative new circuit topologies and power converter architectures for data center power delivery, from the 240 V ac voltage at the input of a server rack, down to the less than 1 V dc power supply of the latest microprocessors. The research pursued three parallel tracks to increase the power conversion efficiency and to reduce the overall size of the servers: 1) An innovative new ac-dc power converter topology which enables improved efficiency through use of a novel direct step-down topology, well suited for the popular 48V dc power distribution. 2) A new series-stacked power delivery approach for servers comprising a large number of similar loads, such as hard drives in storage servers. The approach greatly reduces the power conversion losses, and achieves efficiency well over 99%. 3) A new family of hybrid switched-capacitor power converters that enable improved efficiency and reduced size through the use of dense ceramic capacitors and new circuit topologies that leverage GaN and low-voltage Si transistor technology. Together, the accomplished research achieved the goal of reducing the power conversion losses in datacenters, thereby reducing greenhouse gas emissions, operating costs, and overall electricity consumption.

24 POWER TRANSMISSION AND DISTRIBUTION↗

PV Inverter Systems Enabled by Monolithically Integrated SiC based Four Quadrant Power Switch (4-QPS) [BiDFET]

The purpose of this project was to develop a new breed of Power Conversion Systems (PCS) for PV integration that is enabled by the newly developed 4-Quadrant Single Die SiC Power Semiconductor Switches (4-QPS) or also referred to as “Bidirectional FET (BIDFET)”. This work includes semiconductor die development, advanced packaging, converter design, development, and testing of 4-QPS enabled hardware prototypes at 1 kW (for single phase residential application) and 10 kW (for three phase commercial application). The BiDirectional Field-Effect Transistor (BiDFET) can enable circuit topologies requiring four-quadrant switches, that were earlier designed using discrete combinations of MOSFETs, IGBTs, GaN HEMTs, and PiN diodes. The monolithic nature of the BiDFET allows lower device count, smaller switch volume, lower inductance, and simpler packaging, and hence more reliable and commercially viable implementation in power electronics converters. The matrix converter topologies, now feasible using BiDFETs, can eliminate the bulky and unreliable dc link capacitors or inductors required for conventional voltage-source or current-source converters in ac–ac and ac–dc applications. The 1.2 kV BiDFET has the potential to disrupt all the applications utilizing 1.2 kV switches, including electric vehicle (EV) drivetrain, bidirectional EV chargers, industrial motor drives, solid-state transformers, datacenter power supplies, elevator drives, dc microgrids, energy storage grid integration, solid-state breakers, etc.

24 POWER TRANSMISSION AND DISTRIBUTION↗

New Energy Infrastructure Outlook [Slides]

This report provides a perspective on energy infrastructure under development in the continental U.S. as of the end of 2025, focusing on those making significant progress toward achieving commercial operation. Infrastructures covered in this report include power plants, electric transmission, natural gas pipelines, liquefied natural gas terminals, and datacenters. Additionally, this report includes a section on stockpiled volumes of coal, natural gas, and petroleum.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Congestion Management Solutions for Enhanced Distribution System Operations with Aggregated Distribution Grid Resources Providing Grid Services and Market Participation

Microgrids and other aggregations of distribution grid resources (DGRs) are poised to actively participate in electricity markets and provide essential grid services in the coming years. In fact, DGRs already play such a role through behind-the-meter (BTM) demand response programs and small-scale BTM dispatchable generation initiatives. At the same time, the rapid growth of artificial intelligence (AI) and cryptocurrency datacenters imposes significant, often unpredictable, demands on the power distribution system. Aggregated DGRs can serve as flexible resources that help mitigate these pressures by using available transmission and distribution capacity more efficiently, supporting resource adequacy and other reliability services, and providing bridge strategies while long-term transmission infrastructure is being developed. The impacts this activity will have on distribution networks are not fully understood and could present significant challenges for distribution utilities due to capacity constraints and the need for congestion management. Technical issues include reverse power flow, variability and possible degradation of equipment integrity, voltage violations, and customer power quality concerns. These issues will likely intensify as electricity market operators across the United States implement Federal Energy Regulatory Commission Order 2222 over the next few years.

24 POWER TRANSMISSION AND DISTRIBUTION↗

A Multi-Objective Approach for Optimizing Edge-Based Resource Allocation Using TOPSIS

Existing approaches for allocating resources on edge environments are inefficient and lack the support of heterogeneous edge devices, which in turn fail to optimize the dependency on cloud infrastructures or datacenters. To this extent, we propose in this paper OpERA, a multi-layered edge-based resource allocation optimization framework that supports heterogeneous and seamless execution of offloadable tasks across edge, fog, and cloud computing layers and architectures. By capturing offloadable task requirements, OpERA is capable of identifying suitable resources within nearby edge or fog layers, thus optimizing the execution process. Throughout the paper, we present results which show the effectiveness of our proposed optimization strategy in terms of reducing costs, minimizing energy consumption, and promoting other residual gains in terms of processing computations, network bandwidth, and task execution time. We also demonstrate that by optimizing resource allocation in computation offloading, it is then possible to increase the likelihood of successful task offloading, particularly for computationally intensive tasks that are becoming integral as part of many IoT applications such robotic surgery, autonomous driving, smart city monitoring device grids, and deep learning tasks. The evaluation of our OpERA optimization algorithm reveals that the TOPSIS MCDM technique effectively identifies optimal compute resources for processing offloadable tasks, with a 96% success rate. Moreover, the results from our experiments with a diverse range of use cases show that our OpERA optimization strategy can effectively reduce energy consumption by up to 88%, and operational costs by 76%, by identifying relevant compute resources.

97 MATHEMATICS AND COMPUTING↗

Energy Proportionality and Performance in Data Parallel Computing Clusters

Energy consumption in datacenters has recently become a major concern due to the rising operational costs andscalability issues. Recent solutions to this problem propose the principle of energy proportionality, i.e., the amount of energy consumedby the server nodes must be proportional to the amount of work performed. For data parallelism and fault tolerancepurposes, most common file systems used in MapReduce-type clusters maintain a set of replicas for each data block. A coveringset is a group of nodes that together contain at least one replica of the data blocks needed for performing computing tasks. In thiswork, we develop and analyze algorithms to maintain energy proportionality by discovering a covering set that minimizesenergy consumption while placing the remaining nodes in lowpower standby mode. Our algorithms can also discover coveringsets in heterogeneous computing environments. In order to allow more data parallelism, we generalize our algorithms so that itcan discover k-covering sets, i.e., a set of nodes that contain at least k replicas of the data blocks. Our experimental results showthat we can achieve substantial energy saving without significant performance loss in diverse cluster configurations and workingenvironments.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

"Hot" for Warm Water Cooling

Liquid cooling is key to reducing energy consumption for this generation of supercomputers and remains on the roadmap for the foreseeable future. This is because the heat capacity of liquids is orders of magnitude larger than that of air and once heat has been transferred to a liquid, it can be removed from the datacenter efficiently. The transition from air to liquid cooling is an inflection point providing an opportunity to work collectively to set guidelines for facilitating the energy efficiency of liquid-cooled High Performance Computing (HPC) facilities and systems. The vision is to use non-compressor-based cooling, to facilitate heat re-use, and thereby build solutions that are more energy-efficient, less carbon intensive and more cost effective than their air-cooled predecessors. The Energy Efficient HPC Working Group is developing guidelines for warmer liquid-cooling temperatures in order to standardize facility and HPC equipment, and provide more opportunity for reuse of waste heat. This report describes the development of those guidelines.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

An Analysis Framework for Investigating the Trade-offs Between System Performance and Energy Consumption in a Heterogeneous Computing Environment

Rising costs of energy consumption and an ongoing effort for increases in computing performance are leading to a significant need for energy-efficient computing. Before systems such as supercomputers, servers, and datacenters can begin operating in an energy-efficient manner, the energy consumption and performance characteristics of the system must be analyzed. In this paper, we provide an analysis framework that will allow a system administrator to investigate the tradeoffs between system energy consumption and utility earned by a system (as a measure of system performance). We model these trade-offs as a bi-objective resource allocation problem. We use a popular multi-objective genetic algorithm to construct Pareto fronts to illustrate how different resource allocations can cause a system to consume significantly different amounts of energy and earn different amounts of utility. We demonstrate our analysis framework using real data collected from online benchmarks, and further provide a method to create larger data sets that exhibit similar heterogeneity characteristics to real data sets. This analysis framework can provide system administrators with insight to make intelligent scheduling decisions based on the energy and utility needs of their systems.

Friese, Ryan↗

DOE Hanford Network Upgrades and Disaster Recovery Exercise Support the Cleanup Mission Now and into the Future

In 2013, the U.S. Department of Energy's (DOE) Hanford Site, located in Washington State, funded an update to the critical network infrastructure supporting the Hanford Federal Cloud (HFC). The project, called ET-50, was the final step in a plan that was initiated five years ago called "Hanford's IT Vision, 2015 and Beyond." The ET-50 project upgraded Hanford's core data center switches and routers along with a majority of the distribution layer switches. The upgrades allowed HFC the network intelligence to provide Hanford with a more reliable and resilient network architecture. The culmination of the five year plan improved network intelligence and high performance computing as well as helped to provide 10 Gbps capable links between core backbone devices (10 times the previous bandwidth). These improvements allow Hanford the ability to further support bandwidth intense applications, such as video teleconferencing. The ET-50 switch upgrade, along with other upgrades implemented from the five year plan, have prepared Hanford's network for the next evolution of technology in voice, video, and data. Hand-in-hand with ET-50's major data center outage, Mission Support Alliance's (MSA) Information Management (IM) organization executed a disaster recovery (DR) exercise to perform a true integration test and capability study. The DR scope was planned within the constraints of ET-50's 14 hour datacenter outage window. This DR exercise tested Hanford's Continuity of Operations (COOP) capability and failover plans for safety and business critical Hanford Federal Cloud applications. The planned suite of services to be tested was identified prior to the outage and plans were prepared to test the services ability to failover from the primary Hanford data center to the backup data center. The services tested were: Core Network (backbone, firewall, load balancers); Voicemail; Voice over IP (VoIP); Emergency Notification; Virtual desktops; and, Select set of production applications and data. The primary objective of the exercise was to test COOP around the emergency operations at Hanford to provide information on capabilities and dependencies of the current system to insure improved focus of emergency, safety and security capacity in a disaster situation. The integration of the DR test into the ET-50 project allowed the testing of COOP at Hanford and allowed the lessons learned to be defined. These lessons learned have helped improve the understanding of Hanford's COOP capabilities and will be critical for future planning. With the completion of the Hanford Federal Cloud network upgrades and the disaster recovery exercise, the MSA has a clearer path forward for future technology implementations as well as network improvements to help shape the usability and reliability of the Hanford network in support of the cleanup mission.

97 MATHEMATICS AND COMPUTING↗

Data Movement Dominates: Final Report

Over the past three years in this project, what we have observed is that the primary reason for data movement in large-scale systems is that the per-node capacity is not large enough—i.e., one of the solutions to the data-movement problem (certainly not the only solution that is required, but a significant one nonetheless) is to increase per-node capacity so that inter-node traffic is reduced. This unfortunately is not as simple as it sounds. Today’s main memory systems for datacenters, enterprise computing systems, and supercomputers, fail to provide high per-socket capacity [Dirik & Jacob 2009; Cooper-Balis et al. 2012], except at extremely high price points (factors of 10–100x the cost/bit of consumer main-memory systems) [Stokes 2008]. The reason is that our choice of technology for today’s main memory systems—i.e., DRAM, which we have used as a main-memory technology since the 1970s [Jacob et al. 2007]—can no longer keep up with our needs for density and price per bit. Main memory systems have always been built from the cheapest, densest, lowest-power memory technology available, and DRAM is no longer the cheapest, the densest, nor the lowest-power storage technology out there. It is now time for DRAM to go the way that SRAM went: move out of the way for a cheaper, slower, denser storage technology, and become a cache instead. This inflection point has happened before, in the context of SRAM yielding to DRAM. There was once a time that SRAM was the storage technology of choice for all main memories [Tomasulo 1967; Thornton 1970; Kidder 1981]. However, once DRAM hit volume production in the 1970s and 80s, it supplanted SRAM as a main memory technology because it was cheaper, and it was denser. It also happened to be lower power, but that was not the primary consideration of the day. At the time, it was recognized that DRAM was much slower than SRAM, but it was only at the supercomputer level (For instance the Cray X-MP in the 1980s and its follow-on, the Cray Y-MP, in the 1990s) that could one afford to build ever- larger main memories out of SRAM—the reasoning for moving to DRAM was that an appropriately designed memory hierarchy, built of DRAM as main memory and SRAM as a cache, would approach the performance of SRAM, at the price-per-bit of DRAM [Mashey 1999]. Today it is quite clear that, were one to build an entire multi-gigabyte main memory out of SRAM instead of DRAM, one could improve the performance of almost any computer system by up to an order of magnitude—but this option is not even considered, because to build that system would be prohibitively expensive. It is now time to revisit the same design choice in the context of modern technologies and modern systems. For reasons both technical and economic, we can no longer afford to build ever-larger main memory systems out of DRAM. Flash memory, on the other hand, is significantly cheaper and denser than DRAM and therefore should take its place. While it is true that flash is significantly slower than DRAM, one can afford to build much larger main memories out of flash than out of DRAM, and we show that an appropriately designed memory hierarchy, built of flash as main memory and DRAM as a cache, will approach the performance of DRAM, at the price-per-bit of flash. In our studies as part of this project, we have investigated Non-Volatile Main Memory (NVMM), a new main-memory architecture for large-scale computing systems, one that is specifically designed to address the weaknesses described previously. In particular, it provides the following features: non-volatility: The bulk of the storage is comprised of NAND flash, and in this organization DRAM is used only as a cache, not as main memory. Furthermore, the flash is journaled, which means that operations such as checkpoint/restore are already built into the system. 1+ terabytes of storage per socket: SSDs and DRAM DIMMs have roughly the same form factor (several square inches of PCB surface area), and terabyte SSDs are now commonplace. performance approaching that of DRAM: DRAM is used as a cache to the flash system. price-per-bit approaching that of NAND: Flash is currently well under $0.50 per gigabyte; DDR3 SDRAM is currently just over $10 per gigabyte [Newegg 2014]. Even today, one can build an easily affordable main memory system with a terabyte or more of NAND storage per CPU socket (which would be extremely expensive were one to use DRAM), and our cycle- accurate, full-system experiments show that this can be done at a performance point that lies within a factor of two of DRAM.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

Tour Robot Dance

This program exercises the robotic elements in Oracle Storage Tek tape libraries. This is useful for two known cases: 1.) shaking out marginal or new hardware by ensuring hardware robustness under high-duty usage. 2.) ensuring tape libraries are visually interesting during datacenter tours

Cleary, Geoff↗

ArrayBridge: Interweaving declarative array processing with high-performance computing

Scientists are increasingly turning to datacenter-scale computers to produce and analyze massive arrays. Despite decades of database research that extols the virtues of declarative query processing, scientists still write, debug and parallelize imperative HPC kernels even for the most mundane queries. This impedance mismatch has been partly attributed to the cumbersome data loading process; in response, the database community has proposed in situ mechanisms to access data in scientific file formats. Scientists, however, desire more than a passive access method that reads arrays from files. This paper describes ArrayBridge, a bi-directional array view mechanism for scientific file formats, that aims to make declarative array manipulations interoperable with imperative file-centric analyses. Our prototype implementation of ArrayBridge uses HDF5 as the underlying array storage library and seamlessly integrates into the SciDB open-source array database system. In addition to fast querying over external array objects, ArrayBridge produces arrays in the HDF5 file format just as easily as it can read from it. ArrayBridge also supports time travel queries from imperative kernels through the unmodified HDF5 API, and automatically deduplicates between array versions for space efficiency. Our extensive performance evaluation in NERSC, a large-scale scientific computing facility, shows that ArrayBridge exhibits statistically indistinguishable performance and I/O scalability to the native SciDB storage engine.

97 MATHEMATICS AND COMPUTING↗

Diolkos: Improving ethernet throughput through dynamic port selection

In large networked systems, a sudden increase in traffic could slowdown the network significantly, impacting network quality for multiple users. We present Diolkos, a system that leverages smart switches to dynamically re-reroute data flows in response to drops in performance. In contrast to other techniques, our tool predicts the future throughput at each port in a switch if a data flow were to be sent through it, and updates which port should be taken to maximize throughput. We use several techniques to predict network switch performance on a software defined network (SDN) mimicking topologies commonly found in datacenters. Experimentally, we demonstrate the effectiveness of choosing a port to send flows through based on predicted performance. We found that using a distributed predictive technique achieves a 24% improvement over using a traditional heuristic technique.

port selection, performance enhancement, Neural Ne↗

Job Scheduler-Driven Power Gateway for High Performance Computing

Power gateways in the form of a microgrid can incorporate multiple distributed energy resources (DER) in either grid forming or grid following mode and support high performance computing (HPC) power profiles including the large load-follow requirements observed in multi-user HPC systems. The microgrid’s flexibility to operate in either grid forming or grid following mode and to actively switch between these modes enables baseline power from multiple non-baseline DER while maintaining high power quality metrics for the HPC system. But this enormous flexibility in demand response and time of use shifting is generally programmed independently of any integration with an HPC job scheduler which can better inform the load shaping by the microgrid. While there are many existing approaches where the HPC job scheduler takes in information from the grid to make queue scheduling decisions, this work takes the opposite view and explores a scheduler where the jobs in the queue can directly impact the settings of the grid. Several HPC scheduler strategies are tested where the jobs in the queue directly impact the settings of a microgrid designed for HPC operation which is driving a datacenter with three classes of HPC architectures. The scheduler operation is shown using a microgrid with 64 kW of solar capacity and 320 kWh of battery over a period of 21 days operating with significant low-follow swings, a throttled grid, cloudy conditions, switching between grid following and grid forming modes, and a wide range of battery states-of-charge all while maintaining high quality power metrics. The scheduler provides a mechanism for the job queue to directly impact a power gateway like a microgrid and to improve HPC power outcomes such as maximizing renewable energy usage

microgrid↗

Microgrid Integration with High Performance Computing Systems for Microreactor Operation

Multiple nuclear microreactor concepts are currently being developed across several sizes and fuel types with high performance computing (HPC) systems anticipated to be end-users of the power. Nuclear microreactors are small in size, portable, produce less than 10 MW electric, operate autonomously, and have a refueling interval of as many as 10 years. However, their load-follow is also generally limited to 10%/minute or worse whereas the power variance in HPC systems easily exceeds this constraint under normal operations. This study explores an approach that requires no load-follow from the microreactor but integrates the HPC system with a microgrid built from commercial-off-the-shelf components. Three typical HPC architectures are explored in the context of microgrid operation in this study. Components of power quality and transient response are empirically measured for five different HPC load-follow response levels using a self-contained mobile datacenter connected to the microgrid capable of integration with a nuclear microreactor.

microgrids↗

Updated U.S. Low-Temperature Heating and Cooling Demand by County and Sector

This dataset includes U.S. low-temperature heating and cooling demand at the county level in major end-use sectors: residential, commercial, manufacturing, agricultural, and data centers. Census division-level end-use energy consumption, expenditure, and commissioned power database were dis-aggregated to the county level. The county-level database was incorporated with climate zone, numbers of housing units and farms, farm size, and coefficient of performance (COP) for heating and cooling demand analysis. This dataset also includes a paper containing a full explanation of the methodologies used and maps. Residential data were updated from the latest Residential Energy Consumption Survey (RECS) dataset (2015) using 2020 census data. Commercial data were baselined off the latest Commercial Building Energy Consumption Survey (CBECS) dataset (2012). Manufacturing data were baselined off the latest Manufacturing Energy Consumption Survey (MECS) dataset (2021).

15 GEOTHERMAL ENERGY↗

Recovery Act: Adaptive Environmentally Contained Power and Cooling IT Infrastructure for the Data Center (Final Technical Report)

The objectives of this program were to research and develop a fully enclosed Information Technology (IT) rack system for 100 kilowatts (KW) of IT load that provides its own internal power and cooling with High Voltage Alternating Current (HVAC defined as 480 volt) and chilled water as the primary inputs into the system and accepts alternative energy power sources such as wind and solar. For maximum efficiency, internal power to the IT equipment uses distributed High Voltage Direct Current power (HVDC defined as 360-380 volt) from the power source to the IT loads. The management scheme aggressively controls energy use to insure the best utilization of available power and cooling resources. The solution incorporates internal active management controls that not only optimizes the system environment for the given dynamic IT loads and changing system conditions, but also interfaces with data center Building Management Systems (BMS) to provide a complete end-to-end view of power and cooling chain. This technology achieves the goal of a Power Usage Effectiveness (PUE) of 1.25, resulting in a 38% reduction in the total amount of energy needed to support a 100KW IT load compared to current data center designs.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗