Search results for "Data center"

showing 10 items of 30 documents

LaCoDa: Layered connected topology for massive data centers

2017

One of the fundamental challenges of existing data centers is to design a network that interconnects massive number of servers, and therefore providing an efficient and fault-tolerant routing service to upper-layer applications. Several solutions have been proposed (e.g. FatTree, DCell and BCube), however they either scale too fast (i.e., double exponentially) or too slow. This paper proposes a new data center topology, called LaCoDa, that combines the advantages of previous topologies while avoiding their limitations. LaCoDa uses a small node degree that matches physical restriction for servers, and it also interconnects a large number of servers while reducing the wiring complexity and wi…

Network achitecture[ INFO ] Computer Science [cs]Computer Networks and CommunicationsComputer scienceDistributed computing050801 communication & media studies02 engineering and technologyTopologyNetwork topology0508 media and communicationsServer0202 electrical engineering electronic engineering information engineering[INFO]Computer Science [cs]InterconnectionAverage path lengthNetwork topologybusiness.industryBisection bandwidth05 social sciences020206 networking & telecommunicationsData center networkAverage path lengthComputer Science ApplicationsHardware and ArchitectureData centerbusinessComputer network
researchProduct

Wireless versus Wired Network-on-Chip to Enable the Multi- Tenant Multi-FPGAs in Cloud

2021

The new era of computing is not CPU-centric but enriched with all the heterogeneous computing resources including the reconfigurable fabric. In multi-FPGA architecture, either deployed within a data center or as a standalone model, inter-FPGA communication is crucial. Network-on-chip exhibits a promising performance for the integration of one FPGA. A sustainable communication architecture requires stable performance as the number of applications or users grows. Wireless network-on-chip has the potential to be that communication architecture, as it boasts the same performance capability as wired solutions in addition to its multicast capacities. We conducted an exploratory study to investiga…

Network on a chipMulticastComputer architecturebusiness.industryComputer scienceWirelessSymmetric multiprocessor systemData centerCloud computingArchitecturebusinessField-programmable gate array2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS)
researchProduct

Green Data Centres integration in smart grids: New frontiers for ancillary service provision

2017

Abstract The paper presents a study, conceived within the GEYSER FP7 co-funded European research project, on the ancillary services that Green Data Centres (GDCs) can provide, focusing, in particular, on spinning reserve. More in detail, the main contribution of the paper is to show how GDCs can be involved in the secondary frequency regulation process of a smart distribution grid, for contrasting the disturbing effects of unexpected variation of the energy production. With this aim, a real data centre, owned by Engineering S.p.A., is simulated as connected to the Medium Voltage IEEE 14-bus test grid where some RES-based generators are supposed to exist. Simulations are carried out in order…

Power managementEngineeringOperations researchbusiness.industryProcess (engineering)Event (computing)020209 energyEnergy Engineering and Power Technology020206 networking & telecommunications02 engineering and technologyGridRenewable energyAncillary servicesSettore ING-IND/33 - Sistemi Elettrici Per L'EnergiaSmart gridPower system managementPower system dynamics0202 electrical engineering electronic engineering information engineeringProduction (economics)Data centerGreen Data CentresElectrical and Electronic EngineeringSpinning reservebusinessTelecommunicationsElectric Power Systems Research
researchProduct

Combined IT and power supply infrastructure sizing for standalone green data centers

2021

International audience; In this work, we propose a two-step methodology for designing and sizing a data center solely powered by local renewable energy. The first step consists in determining the necessary IT equipment for processing a given IT workload composed of batch and service tasks. We propose an adapted binary search algorithm and prove its optimality to find the minimum number of servers to handle the IT workload. When the IT sizing is computed, the second step consists in defining the supplying electrical infrastructure using wind turbines and photovoltaic panels as primary sources. Batteries and a hydrogen system are added as secondary sources for short- and long-term energy stor…

Renewable energyBinary search algorithmWind powerGeneral Computer Sciencebusiness.industryComputer scienceInfrastructure sizing020209 energyReal-time computingPhotovoltaic systemSustainable Computing: Informatics and Systems Renewable energy020206 networking & telecommunicationsWorkload02 engineering and technology7. Clean energyGreen data centerSizingEnergy storageServer0202 electrical engineering electronic engineering information engineeringData center[INFO.INFO-OS]Computer Science [cs]/Operating Systems [cs.OS][INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC]Electrical and Electronic EngineeringbusinessSustainable Computing: Informatics and Systems
researchProduct

Integrating Variability Management in Data Center Networks

2017

International audience; Data centers have an important role in supporting cloud computing services (i.e. checking social media, sending emails, video conferencing,..). Hence, data centers topologies design became more important and must be able to respond to ever changing service requirements and application demands. An ultimate challenge in this research is the design of data center network that interconnects the massive number of servers, and provides efficient and fault-tolerant routing algorithm. Several topologies such as DCell, FlatNet and ScalNet have been proposed. However, these topologies generally seek to improve the scalability without taking into consideration the energy usage …

Service (systems architecture)[ INFO ] Computer Science [cs]Computer scienceDistributed computing0211 other engineering and technologies02 engineering and technology[INFO] Computer Science [cs]computer.software_genreNetwork topologyInfrastructure costVideoconferencingServer[INFO]Computer Science [cs]Average path lengthEnergy021103 operations researchbusiness.industryCloud computing servicesData center networkEnergy consumptionAverage path lengthaverage path lengthScalabilitydata center networkData centerbusinessinfrastructure costcomputerComputer networkenergy
researchProduct

A survey of wireless data center networks

2015

Data centers are becoming more and more popular for a wide variety of applications. However, the efficiency of data centers are restricted by many issues like cabling and maintenance problems in addition to performance problems like oversubscription. Wireless technology was proposed as it has the capability and the flexibility to offer feasible approaches to solve some of these problems. In this paper, we conduct a deep investigation about wireless data center networks, describe some works that enhance the performance of the network, then give some remarks and critiques. 2015 IEEE. Scopus

Wi-Fi arrayWireless networkbusiness.industryComputer scienceDistributed computingWireless WANData center networkWireless data center networkKey distribution in wireless sensor networksWireless site survey60Ghz technologybusinessFixed wirelessWireless sensor networkMunicipal wireless networkComputer network2015 49th Annual Conference on Information Sciences and Systems (CISS)
researchProduct

PTNet: An efficient and green data center network

2017

International audience; In recent years, data centers have witnessed an exponential growth for hosting hundreds of thousands of servers as well as to accommodating a very large demand for resources. To fulfill the required level of demand, some approaches tackled network aspects so to host a huge number of servers while others focused on delivering rapid services to the clients by minimizing the path length between any two servers. In general, network devices are often designed to achieve 1:1 oversubscription. Alternatively, in a realistic data center environment, the average utilization of a network could vary between 5% and 25%, and thus the energy consumed by idle devices is wasted. This…

[ INFO ] Computer Science [cs]Computer Networks and CommunicationsComputer scienceDistributed computing02 engineering and technologyNetwork topology[ INFO.INFO-AO ] Computer Science [cs]/Computer ArithmeticTheoretical Computer Science03 medical and health sciences[INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI]0302 clinical medicineArtificial IntelligenceRobustness (computer science)Energy savingServerArchitecture0202 electrical engineering electronic engineering information engineering[INFO.INFO-RB]Computer Science [cs]/Robotics [cs.RO][INFO]Computer Science [cs]ComputingMilieux_MISCELLANEOUSAverage path lengthInterconnectionNetwork topologyEnergy[INFO.INFO-DB]Computer Science [cs]/Databases [cs.DB]business.industry[INFO.INFO-AO]Computer Science [cs]/Computer ArithmeticScalability020206 networking & telecommunicationsData center networkAverage path lengthNetworking hardware[INFO.INFO-GR]Computer Science [cs]/Graphics [cs.GR]Hardware and Architecture030220 oncology & carcinogenesis[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]ScalabilityData center[INFO.INFO-DC]Computer Science [cs]/Distributed Parallel and Cluster Computing [cs.DC]businessSoftwareComputer network
researchProduct

Network architectures and energy efficiency for high performance data centers

2017

The increasing trend to migrate applications, computation and storage into more robust systems leads to the emergence of mega data centers hosting tens of thousands of servers. As a result, designing a data center network that interconnects this massive number of servers, and providing efficient and fault-tolerant routing service are becoming an urgent need and a challenge that will be addressed in this thesis. Since this is a hot research topic, many solutions are proposed like adapting new interconnection technologies and new algorithms for data centers. However, many of these solutions generally suffer from performance problems, or can be quite costly. In addition, devoted efforts have n…

[INFO.INFO-AR]Computer Science [cs]/Hardware Architecture [cs.AR][INFO.INFO-AR] Computer Science [cs]/Hardware Architecture [cs.AR]Qualité de service[INFO.INFO-NI] Computer Science [cs]/Networking and Internet Architecture [cs.NI][INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]Scalability[INFO.INFO-DS] Computer Science [cs]/Data Structures and Algorithms [cs.DS]Centres de donnéesAlgorithmes de routage[INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI]Quality of servicePower efficiencyData centerConsommation d’énergieRouting
researchProduct

Topologies réseau pour la réduction des coûts et l'amélioration de la qualité du service dans les centres de données massives

2017

Data centers (DC) are being built around the world to provide various cloud computing services. One of the fundamental challenges of existing DC is to design a network that interconnects massive number of nodes (servers)1 while reducing DC' cost and energy consumption. Several solutions have been proposed (e.g. FatTree, DCell and BCube), but they either scale too fast (i.e., double exponentially) or too slow. Effcient DC topologies should incorporate high scalability, low latency, low Average Path Length (APL), high Aggregated Bottleneck Throughput (ABT) and low cost and energy consumption. Therefore, in this dissertation, different solutions have been proposed to overcome these problems. F…

[INFO.INFO-OH] Computer Science [cs]/Other [cs.OH]Energy consumptionInfrastructure costLe coût de l'infrastructureAverage path lengthCloud computing servicesCentre de donnéesTopologies[INFO.INFO-OH]Computer Science [cs]/Other [cs.OH]Cloud computingData center networkConsommation d'énergie
researchProduct

Generalization Capacity Analysis of Non- Intrusive Load Monitoring using Deep Learning

2020

Appliance Load Monitoring is a technique used to monitor devices existing in homes, industry or naval vessels. Acquisition of device-level data can provide great benefits in many areas such as energy management, demand response, and load forecasting. However, the monitoring process is often provided with a costly installation, as it requires a large number of sensors and a data center. Non-Intrusive Load Monitoring (NILM) is an alternative and cost-efficient load monitoring solution. Simply put, NILM is the process of obtaining device-level data by analyzing the aggregated data read from the main meter that measures the electricity consumption of the whole house. Before NILM analysis is per…

energy managementComputer scienceEnergy managementbusiness.industryDeep learningReal-time computingenergy disaggregationProcess (computing)deep learningload monitoringDemand responsedemand responseMetreData centerMicrogridElectricityArtificial intelligencebusiness
researchProduct