Data Centers

The exponential rise of artificial intelligence (AI), cloud computing, and big data is driving unprecedented energy demand in data centers. By 2030, data centers are projected to consume 10% of the world's electricity, with cooling systems alone accounting for nearly 40% of total energy consumption (International Energy Agency [IEA], 2024). Conventional cooling solutions, such as mechanical and evaporative cooling, contribute significantly to carbon emissions, high operational costs, and water resource depletion (Ghamkhari & Mohsenian-Rad, 2012). Geothermal energy, specifically ground-source heat exchangers (GSHEs) and enhanced geothermal systems (EGS), presents a low-carbon, cost-effective alternative for data center cooling. This study explores AI-driven geothermal reservoir optimization, Computational Fluid Dynamics (CFD) modeling, and lifecycle cost analysis to assess the feasibility of geothermal-powered cooling in data centers (National Renewable Energy Laboratory [NREL], 2024). Findings indicate that geothermal cooling can reduce energy consumption by 40-50%, while AI-powered reservoir management can enhance efficiency by 25%, significantly reducing operational costs (Google LLC, 2023). Additionally, this paper evaluates case studies from Google, Microsoft, Fervo Energy, and Amazon, assessing policy frameworks, financial models, and regulatory incentives for geothermal adoption. Future research must focus on hybrid geothermal-solar-wind integration, AI-automated geothermal drilling, and real-time energy optimization for next-generation carbonneutral data centers.

The complex turbulent flow regimes encountered in many thermal-fluid engineering applications have proven resistant to the effective application of systematic design because of the computational expense of model evaluation and the inherent variability of turbulent systems. In this paper the integration of a novel reduced order turbulent convection modeling approach based upon the proper orthogonal decomposition technique with the application of robust design principles implemented using the compromise decision support problem is investigated as an effective design approach for this domain. In the example application considered, thermally efficient computer server cabinet configurations that are insensitive to variations in operating conditions are determined. The computer servers are cooled by turbulent convection and have unsteady heat generation and cooling air flows, yielding substantial variability, yet have some of the most stringent operational requirements of any engineering ...

Here, we report on the design and performance of a silicon photonic micro-transceiver required to operate in 5G and 6G environments at high ambient temperatures above 105 °C. The four-channel “IOCore” micro-transceiver incorporates a 1310 nm quantum dot laser system and operates at a data rate of 25 Gbps and higher. The 5 × 5 mm micro-transceiver chip benefits from a multimode coupling interface for low-cost assembly and robust connectivity at high temperatures as well as an optical redundancy scheme, which increases reliability by over an order of magnitude.

The term “just transition” has proliferated in recent years but remains a deeply contested term. While the focus has increasingly shifted to ensuring just processes as well as outcomes as we transition to a low-carbon economy, there has also been growing recognition of the necessity of place-based approaches. This paper shares a mixed method, co-creation case study of three Irish communities, drawing on the Capability Approach (CA) in order to operationalise a place-based approach to/for a just transition. We focus on identifying those factors that convert resources into capabilities and enhance well-being. Examining these conversion factors (personal, environmental, social and economic) paves the way for understanding barriers to and pathways towards a just transition in particular places. Our research identifies the need to interrogate the relevance of the “just transition” to particular communities and to recognise “varieties of transitions” matched to local conditions. We argue that Just Transition must be seen within the wider history of regional, social and spatial inequalities and thus an agonistic approach that uncovers past injustice is critical to imagining a new future. Finally, we argue that significant governance innovation is required that is both bottom-up and coupled with targeted resourcing of existing and new institutions. Without a focus on spatial and social justice, our responses to the climate and biodiversity crises will beget new crises of wellbeing and quality of life. With a focus on spatial and social justice we can give momentum to climate action and simultaneously address historical and existing socio-spatial inequalities.

Parlem de think tanks i centres de dades només per donar una visió general del tema, amb alguns exemples en què apareixeran Kimberley Kagan -presidenta de l'Institute for the Study of War (ISW)-, Robert Kagan, William Kristol i Larry Fink, el president de BlackRock.
We talk about think tanks and data centres just to give an overview of the topic, with some examples in which Kimberley Kagan -president of the Institute for the Study of War (ISW)-, Robert Kagan, William Kristol and Larry Fink, the president of BlackRock, will appear.
The text is written in Catalan, with long quotes in English and Spanish.

The high replication cost of Byzantine fault-tolerance (BFT) methods has been a major barrier to their widespread adoption in commercial distributed applications. We present ZZ, a new approach that reduces the replication cost of BFT services from 2f + 1 to practically f + 1. The key insight in ZZ is to use f + 1 execution replicas in the normal case and to activate additional replicas only upon failures. In data centers where multiple applications share a physical server, ZZ reduces the aggregate number of execution replicas running in the data center, improving throughput and response times. ZZ relies on virtualization-a technology already employed in modern data centers-for fast replica activation upon failures, and enables newly activated replicas to immediately begin processing requests by fetching state on-demand. A prototype implementation of ZZ using the BASE library and Xen shows that, when compared to a system with 2f + 1 replicas, our approach yields lower response times and up to 33% higher throughput in a prototype data center with four BFT web applications. We also show that ZZ can handle simultaneous failures and achieve sub-second recovery.

In today's fast-paced digital age, data centers play a crucial role in supporting essential internet operations such as cloud computing, artificial intelligence (AI), and machine learning (ML). As these technologies become more complex and widespread, the need for faster, more efficient, and environmentally sustainable digital infrastructures grows. It's increasingly important to incorporate advanced optical network technologies early in data center projects. Data center interconnects turned to optical technologies almost a decade ago, and the recent acceleration in data center requirements is expected to further drive fiber optic technologies deeper into the systems architecture. This paper analyses the role of advanced fiber optic technologies in the revolutionary journey of U.S. Data Centers and Technologies. It critically studies the existing data center infrastructure to unearth the challenges and opportunities and proposes the use of advanced fiber optic technologies in data centers to increase efficiency, security and sustainability which is a critical issue for investors. The proposition is in line with the US national interest by expanding and securing the data infrastructure thereby bolstering economic growth through the creation of skilled job opportunities fostering a robust labor market in telecommunications and maintaining the US as a leader in technological advancements.

Modern day data centers coordinate hundreds of thousands of heterogeneous tasks and aim at delivering highly reliable cloud computing services. Although offering equal reliability to all users benefits everyone at the same time, users may find such an approach either too inadequate or too expensive to fit their individual requirements, which may vary dramatically. In this paper, we propose a novel method for providing reliability as an elastic and on-demand service. Our scheme makes use of peer-to-peer checkpointing and allows user reliability levels to be jointly optimized based on an assessment of their individual requirements and total available resources in the data center. We show that the joint optimization can be efficiently solved by a distributed algorithm using dual decomposition. The solution improves resource utilization and presents an additional source of revenue to data center operators. Our validation results suggest a significant improvement of reliability over existing schemes.

The high replication cost of Byzantine fault-tolerance (BFT) methods has been a major barrier to their widespread adoption in commercial distributed applications. We present ZZ, a new approach that reduces the replication cost of BFT services from 2f + 1 to practically f + 1. The key insight in ZZ is to use f + 1 execution replicas in the normal case and to activate additional replicas only upon failures. In data centers where multiple applications share a physical server, ZZ reduces the aggregate number of execution replicas running in the data center, improving throughput and response times. ZZ relies on virtualization-a technology already employed in modern data centers-for fast replica activation upon failures, and enables newly activated replicas to immediately begin processing requests by fetching state on-demand. A prototype implementation of ZZ using the BASE library and Xen shows that, when compared to a system with 2f + 1 replicas, our approach yields lower response times and up to 33% higher throughput in a prototype data center with four BFT web applications. We also show that ZZ can handle simultaneous failures and achieve sub-second recovery.

Efficient resource management in data centers and clouds running large distributed data processing frameworks like MapReduce is crucial for enhancing the performance of hosted applications and increasing resource utilization. However, existing resource scheduling schemes in Hadoop MapReduce allocate resources at the granularity of fixed-size, static portions of nodes, called slots. In this work, we show that MapReduce jobs have widely varying demands for multiple resources, making the static and fixed-size slot-level resource allocation a poor choice both from the performance and resource utilization standpoints. Furthermore, lack of coordination in the management of multiple resources across nodes prevents dynamic slot reconfiguration, and leads to resource contention. Motivated by this, we propose MROrchestrator, a MapReduce resource Orchestrator framework, which can dynamically identify resource bottlenecks, and resolve them through fine-grained, coordinated, and on-demand resource allocations. We have implemented MROrchestrator on two 24-node native and virtualized Hadoop clusters. Experimental results with a suite of representative MapReduce benchmarks demonstrate up to 38% reduction in job completion times, and up to 25% increase in resource utilization. We further demonstrate the performance boost in existing resource managers like NGM and Mesos, when augmented with MROrchestrator.

With the significant advances in Information and Communications Technology (ICT) over the last half century, there is an increasingly perceived vision that computing will one day be the 5th utility (after water, electricity, gas, and telephony). This computing utility, like all other four existing utilities, will provide the basic level of computing service that is considered essential to meet the everyday needs of the general community. To deliver this vision, a number of computing paradigms have been proposed, of which the latest one is known as Cloud computing. Hence, in this paper, we define Cloud computing and provide the architecture for creating Clouds with market-oriented resource allocation by leveraging technologies such as Virtual Machines (VMs). We also provide insights on market-based resource management strategies that encompass both customer-driven service management and computational risk management to sustain Service Level Agreement (SLA)-oriented resource allocation. In addition, we reveal our early thoughts on interconnecting Clouds for dynamically creating global Cloud exchanges and markets. Then, we present some representative Cloud platforms, especially those developed in industries along with our current work towards realizing market-oriented resource allocation of Clouds as realized in Aneka enterprise Cloud technology. Furthermore, we highlight the difference between High Performance Computing (HPC) workload and Internet-based services workload. We also describe a meta-negotiation infrastructure to establish global Cloud exchanges and markets, and illustrate a case study of harnessing 'Storage Clouds' for high performance content delivery. Finally, we conclude with the need for convergence of competing IT paradigms to deliver our 21st century vision.

Data Centers are the physical locations of the internet and are experiencing rapid growth. They stand at the intersection of multiple United Nations Sustainable Development Goals (SDGs) due to their impact on human health and the environment. According to MIT Technology Review (September 2024), the increased use of artificial intelligence (AI) could surge the energy consumption of data centers by about 160% within this decade. This surge in electricity demands, and resulting carbon emissions, contributes to the present global climate crisis. The findings of this research show that physics-informed neural networks (PINNs) as a promising methodology for estimating trends in data centers and emissions growth. Our sensitivity analyses reveal that data centers and population carrying capacity as well as the carbon sequestration rate seem to have significant impact on carbon emissions. Future work should seek to optimize parameters to inform policy decisions at the county level.

With the rapid growth of cloud computing, the number of data centers (DCs) continuously increases, leading to a high-energy consumption dilemma. Cooling, apart from IT equipment, represents the largest energy consumption in DCs. Passive design (PD) and active design (AD) are two important approaches in architectural design to reduce energy consumption. However, for DC cooling, few studies have summarized AD, and there are almost no studies on PD. Based on existing international research (2005-2024), this paper summarizes the current state of cooling strategies for DCs. PD encompasses floors, ceilings, and layout and zoning of racks. Additionally, other passive strategies not yet studied in DCs are critically examined. AD includes air, liquid, free, and two-phase cooling. This paper systematically compares the performance of different AD technologies on various KPIs, including energy, economic, and environmental indicators. This paper also explores the application of different cooling design strategies through best-practice examples and presents advanced algorithms for energy management in operational DCs. This study reveals that free cooling is widely employed, with Artificial Neural Networks emerging as the most popular algorithm for managing cooling energy. Finally, this paper suggests four future directions for reducing cooling energy in DCs, with a focus on the development of passive strategies. This paper provides an overview and guide to DC energy-consumption issues, emphasizes the importance of implementing passive and active design strategies to reduce DC cooling energy consumption, and provides directions and references for future energy-efficient DC designs.

The study presents an experimental investigation of a thermal energy storage vessel for load-shifting purposes. The new heat storage vessel is a plate-type heat exchanger unit with water as the working fluid and a phase change material (PCM) as the energy storage medium. The thermal characteristics of the heat exchanger such as heat transfer coefficient, effectiveness, efficiency, water exit temperature, heat storage rate, total energy storage capacity and storage time were experimentally evaluated as a function of various inlet conditions. The compact parallel plate design showed an enhanced the performance compared to conventional storage systems with an effectiveness up to 83.1% even when a PCM of low thermal conductivity is used. The proposed phase change energy storage system not only can deliver substantial benefits as a thermal energy storage medium, but also provides cost savings in infrastructure, equipment, and maintenance/operations compared to conventional systems. 16-17°C or lower water temperature from cooling towers to store "cold" energy in PCM during off-peak hoursat nightwithout mechanical chiller systems. The PCM storage vessel can be cooled during

Currently the national project “Digital Economy of the Russian Federation” is being implemented in Russia, providing for the digitalization of large cities, including the port city of Vladivostok. The article discusses some problems of digitalization of Vladivostok, which require solutions in order to make the process of introducing information technology and creating a “smart city” as efficient as possible and at the same time minimize the costs of its implementation.

The high replication cost of Byzantine fault-tolerance (BFT) methods has been a major barrier to their widespread adoption in commercial distributed applications. We present ZZ, a new approach that reduces the replication cost of BFT services from 2f + 1 to practically f + 1. The key insight in ZZ is to use f + 1 execution replicas in the normal case and to activate additional replicas only upon failures. In data centers where multiple applications share a physical server, ZZ reduces the aggregate number of execution replicas running in the data center, improving throughput and response times. ZZ relies on virtualization-a technology already employed in modern data centers-for fast replica activation upon failures, and enables newly activated replicas to immediately begin processing requests by fetching state on-demand. A prototype implementation of ZZ using the BASE library and Xen shows that, when compared to a system with 2f + 1 replicas, our approach yields lower response times and up to 33% higher throughput in a prototype data center with four BFT web applications. We also show that ZZ can handle simultaneous failures and achieve sub-second recovery.

A performance counter is that part of a microprocessor that measures and gathers performance-relevant events on the microprocessor. The number and type of available events differ significantly between existing microprocessors, because there is no commonly accepted specification, and because each manufacturer has different priorities on analyzing the performance of architectures and programs. Looking at the supported events on the different microprocessors, it can be observed that the functionality of these events differs from the requirements of an expert application programmer or a performance tool writer. PCL, the Performance Counter Library, establishes a common platform for performance measurements on a wide range of computer systems. With a common interface on all systems and a set of applicationoriented events defined, the application programmer is able to do program optimization in a portable way and the performance tool writer is able to rely on a common interface on different systems. PCL has functions to query the functionality, to start and to stop counters, and to read the values of counters. Performance counter values are returned as 64 bit integers on all systems. PCL supports nested calls to PCL functions thus allowing hierarchical performance measurements. Counting may be done either in system or in user mode. All interface functions are callable in C, C++, Fortran, and Java. v vi

A performance counter is that part of a microprocessor that m easures and gathers performance-relevant events on the microprocessor. The number and type of availab le events differ significantly between existing microprocessors, because there is no commonly accepted spe cification, and because each manufacturer has different priorities on analyzing the performance of archi tectures and programs. Looking at the supported events on the different microprocessors, it can be observed that the functionality of these events differs from the requirements of an expert application programmer or a pe formance tool writer. PCL, the Performance Counter Library, establishes a common platform for performance measurements on a wide range of computer systems. With a common interface o n all systems and a set of applicationoriented events defined, the application programmer is able to do program optimization in a portable way and the performance tool writer is able to rely on a common int erface on d...

Call for Abstracts (Deadline: September 15, 2024): "En/Countering Tracking. Resisting spatiotemporal media operations in computational culture"
A special issue of Computational Culture, a Journal of Software Studies
Edited by Kathrin Friedrich and Sebastian Randerath

see also – http://computationalculture.net/cfps-events/

During the past decade the cloud service market is one of the fastest growing segments around the world. The amount of companies that turned to the cloud has been steadily growing, since paying for a “shared” Cloud service over а given period of time reduces the capital expenditures and turned out to be better than using a dedicated hardware. This paper is focused on the architecture and the design of a shared public cloud service provider. The primary goal of the paper is to present a complete integrated solution for a single communication platform providing Cloud services to end-users. The paper, first, provides a literature review of some Cloud computing aspects, including the requirements for Cloud computing services and the key performance indicators to be evaluated. Second, it is described a real network infrastructure design approach, which allows smooth implementation of additional services and functionalities. All of the applicable functionalities are built to be managed an...

Governments worldwide are embracing digital transformation, envisioning limitless data capacities for public policy. However, this paper uncovers a crucial oversight: the neglect of material resources sustaining digital ecosystems. This paper introduces contested “digital capacities” in public policy, to show how the aspiration for unlimited data processing strains local resources. Through a comparative analysis of national digitization strategies in the United States and the United Kingdom, this paper reveals a disconnect between the sociotechnical imaginaries and infrastructural demands underpinning these strategies. The infrastructural demands are leading to social and environmental tradeoffs in regional areas strained by digital infrastructure development. I argue that these competing digital capacities – the capacity to govern through digitization and related resource capacities – provide productive data friction for governments to pause and assess the broader social and ecological costs of their national digitization policies. As such, this article emphasizes the need for policymakers to align national digital governance strategies with regional planning for equitable outcomes. By reevaluating competing digital capacities encompassed in national sociotechnical imaginaries, this paper highlights the urgent need for a balanced approach to digitization.

Cloud operators increasingly need many fine-grained rules to better control individual network flows for various management tasks. While previous approaches have advocated placing rules either on hypervisors or switches, we argue that future data centers would benefit from leveraging rule processing capabilities at both for better scalability and performance. In this paper, we propose vCRIB, a virtualized Cloud Rule Information Base that allows operators to freely define different management policies without the need to consider underlying resource constraints. The challenge in our approach is the design of a vCRIB manager that automatically partitions and places rules at both hypervisors and switches to achieve a good trade-off between resource usage and performance.

Multi-cloud networking has become an important part of modern network design as cloud computing has become more popular. When it comes to putting multi-cloud networking into practice, this article talks about the idea, and its pros and cons. Multicloud networking has many benefits, such as lower operational costs, greater vendor freedom, better resilience and availability, access to the best services, and compliance with data sovereignty laws. However, multi-cloud networking has some intricacies, like architectural complexities, security and compliance issues, management, employees' skills and training, etc. The article uses different studies, polls, and real-life examples to show these pros and cons. It stresses the importance of dealing with these problems to maximize the benefits of multi-cloud networking

Organizations widely use cloud computing to outsource their computing needs. One crucial issue of cloud computing is that services must be available to clients at all times. However, the cloud services may be temporarily unavailable due to maintenance of the cloud infrastructure, load balancing of services, defense against cyber attacks, power management, proactive fault tolerance, or resource usage. The unavailability of cloud services impacts negatively on the business model of cloud providers. One solution to tackle the service unavailability is Live Virtual Machine Migration (LVM), that is, moving virtual machines (VMs) from the source host machine to the destination host without disrupting the running application. Pre-copy memory migration is a common LVM approach used in most networked systems such as the cloud. The main difficulty with this approach is the high rate of frequently updating memory pages, referred to as "dirty pages. Transferring these updated or dirty pages during the pre-copy migration approach prolongs the total migration time. After a predefined iteration, the pre-copy approach enters the stop-and-copy phase and transfers the remaining memory pages. If the remaining pages are huge, the downtime or service unavailability will be very high-resulting in a negative impact on the availability of the running services. To minimize such service downtime, it is critical to find an optimal time to migrate a virtual machine in the pre-copy approach. To address the issue, this paper proposes a machine learning-based method to optimize pre-copy migration. It has mainly three stages (i) Feature selection (ii) Model generation and (iii) Application of the proposed model in pre-copy migration. The experiment results show that our proposed model outperforms other 1 Springer Nature 2021 L A T E X template 2 Article Title machine learning models in terms of prediction accuracy and it significantly reduces downtime or service unavailability during the migration process.

In the design of a data centre (DC), engineers are increasingly using specialized commercial computational fluid dynamics (CFD) software packages to predict thermal loads for various cooling configurations. This paper is the first to demonstrate how a set of open source software tools, namely OpenFOAM, Octave and paraview can be used to simulate and visualize the airflow in a real live 55kW private DC, with a particular focus on energy savings and reduction of hotspots. Keywords Data centre airflow, computational fluid dynamics, open source software, OpenFOAM. Nomenclature Text in courier font refers to Octave and OpenFOAM specific components and any third party OpenFOAM applications.

h i g h l i g h t s Experimental investigation of bypass of cooling in data centres employing aisle containment systems. Effect of bypass on total power consumption investigated using a new system model. Practical measures for reducing bypass shown to reduce power consumption. Optimum level of aisle pressure investigated.

As mobile devices get ubiquitous and grow in computational power, their management of interdependent data also becomes increasingly important. The mobile environment exhibits all the characteristics of a distributed database plus the feature of whimsical connectivity. Consequently, transactions respecting data consistency can suffer unbounded and unpredictable delays at both mobile and stationary nodes. The currently popular multi-tier model, in which mobile devices are in one end and always-connected stationary servers in the other, has certain practical advantages. However, it assumes that all integrity constraints are evaluated at the servers and hence relies on the semantics of operations for any autonomy enhancement of the mobile devices. In this paper, we examine the idea of constraint localization in cases where two mobile nodes each own data that share a constraint. It relies on reformulation of a constraint into more flexible local constraints that give more autonomy to the mobile nodes. The scheme also involves dynamic changes of these local constraints through negotiation, which we call re-localization. To overcome the problem of simultaneous requests for such re-localization, we give algorithms along with experimental results indicating their effectiveness.

Energy-related Denial of Service (DoS) attacks have the potential to impact not only the quality or availability of services provided by large-scale data center (DC) infrastructures but also the operating expenses incurred by the organizations managing them, essentially in terms of energy bills. More specifically, the impact on the overall energy usage and, consequently, on the associated expenses, increases with the amount of time required to identify the attack. Therefore, the degradation of the environmental control systems in the buildings/facilities hosting the computing or storage nodes poses an especially insidious threat, which could result in a novel kind of attack to the involved infrastructures. Due to the limited ability to observe events in cyber-physical systems, recognizing these violations is extremely challenging for data center administrators. This paper proposed a new methodology for detecting cooling systems attacks based on continuous Power Usage Effectiveness (PUE) monitoring. This kind of measurement is quite simple to arrange in a data center, and can help to detect, in a limited amount of time, both attacks and failures on a DC cooling system, thus helping the system administration to limit expenses and service outages.

FPGA-based accelerators are becoming a first class citizen in data centers. Adding FPGAs in data centers can lead to higher compute densities with improved energy efficiency for latency critical workloads, such as financial applications. However deployment of FPGAs in datacenters is hindered, as both developers and cloud providers face difficulties. Application writers need to deal with FPGA interfacing as well as application logic/algorithms. On the other hand, cloud providers are reluctant to deploy FPGAs in large scale, due to the FPGAs lack of sharing that results in reduced utilization and questionable ROI. In this paper, we introduce VineTalk, a framework that reduces the programming effort associated with FPGA-based accelerators and FPGA virtualization. We integrate VineTalk with the Xilinx SDAccel development framework and we map it to the Kintex UltraScale FPGA. Our preliminary evaluation with a use-case of financial applications shows that VineTalk can offer effective FPGA sharing introducing less than 4% overhead to application execution time.

Cloud computing is a popular emerging computing technology that has revolutionized information technology through flexible provisioning of computing resources. Therefore, efforts to develop an effective resource management approach have found that implementing efficient resource sharing among multiple customers that considers power saving, service-level agreements, and network traffic simultaneously is difficult. This paper proposes a practical integrated pipeline that can use various algorithms. The performance of each algorithm is evaluated independently to obtain the combination of algorithms that guarantees a resource-effective cloud data center framework. This integrated resource management pipeline approach would optimize performance based on several key performance indicators, such as power saving, network traffic, and service-level agreements, for either the whole system or the end-user. The performance of the proposed resource management framework was evaluated using a real...

Energy efficiency has become a prime concern in this evolving era of cloud computing. In recent years, several VM consolidation techniques were proposed. However, they involve single-criterion-based host selection methods, which are unsuitable for the dynamic cloud environment. Cloud data centers need an efficient utilization of physical host resources. The selected hosts for VMs deployment must ensure the least energy consumption and service-level agreement (SLA) violations simultaneously. There is a lack of multi-criteria-based solution which considers multiple resources to select hosts for the deployment of VMs. This paper presents a VM deployment framework that considers multiple criteria, i.e., reducing energy consumptions and SLA violations simultaneously while determining target hosts for VMs placement. The article proposes an Improved Technique for Order of Preference by Similarity to Ideal Solution-based Host Selection Policy for VM deployment on the target hosts in terms of energy efficiency. It manages the trade-off between energy consumption and SLA compliance. A case study is demonstrated to prove the usefulness and appropriateness of the proposed framework. The results show that our framework is promising and provides more efficiency in the use of cloud resources and maintaining SLA.

In fact, to improve the quality of system service, for user job requests, which already have waited for a long time in queues of a busy cluster, cloud vendors often migrate the jobs to other available clusters. This strategy brings about the occurrence of job abandonment phenomenon in data centers, which disturbs the server management mechanisms in the manner of decreasing effectiveness control, increasing energy consumptions, and so on. In this paper, based on the three-state model proposed in previous works, we develop a novel model and its management strategy for cloud data centers using a finite queue. Our proposed model is tested in a simulated cloud environment using CloudSim. The achieved outcomes show that our three-state server model for data centers operates well under the job abandonment phenomenon.

This essay delves into the complex interplay between historical data recording systems and modern data infrastructures, focusing on the quipus—an ancient Incan system for recording information. Otero Verzier explores the juxtaposition of the quipus on display at the Museo Chileno de Arte Precolombino with contemporary global data networks and centers in Santiago, Chile. She argues that modern data infrastructures, like those supporting massive data centers and astronomical observatories, mirror the extractivist and colonial dynamics historically entrenched in the exploitation of knowledge and natural resources.

The paper provides a critical analysis of how these modern infrastructures perpetuate colonial legacies through their environmental impact and the commodification of data. By tracing the transformation of the Inca Trail into a hub for global digital communications, the paper highlights the continuity of data extraction and its implications for local communities and ecosystems.

Otero Verzier critically examines the role of quipus as both a cultural artifact and a potent symbol of resistance against colonial domination. She discusses the ongoing efforts to decipher quipus using modern technologies and the ethical considerations these entail, emphasizing the need for a respectful engagement with indigenous knowledge systems. The paper concludes by advocating for a more conscientious approach to data handling that acknowledges the intrinsic value of cultural memory and challenges the prevailing extractivist data practices.

In order to meet the insatiable demands for cloud-based services, today's data centers may have hundreds of thousands of servers. During the past decade, many topologies have been proposed to interconnect a large number of servers in a data center network. However, existing topologies face several challenges including the rigid structure, high network cost, and packet relay overheads on servers. In this paper, we propose a novel switch-centric network topology, called DCCube, which offers many desirable properties for data center networking. DCCube is a flexible structure because, given the switches degree and the network diameter, it is possible to construct different structures with different number of connected servers, bisection bandwidth and network cost. Furthermore, DCCube can accommodate a large number of servers with high bisection bandwidth, low cost, small diameter and desirable path diversity. By comparing with existing data center network topologies, we show that DCCube achieves both high performance and low network cost. We also design both minimal and non-minimal routing algorithms for the proposed topology. Simulation results reveal that non-minimal routing is preferred for unbalanced traffic patterns.

The complex turbulent flow regimes encountered in many thermal-fluid engineering applications have proven resistant to the effective application of systematic design because of the computational expense of model evaluation and the inherent variability of turbulent systems. In this paper the integration of a novel reduced order turbulent convection modeling approach based upon the proper orthogonal decomposition technique with the application of robust design principles implemented using the compromise decision support problem is investigated as an effective design approach for this domain. In the example application considered, thermally efficient computer server cabinet configurations that are insensitive to variations in operating conditions are determined. The computer servers are cooled by turbulent convection and have unsteady heat generation and cooling air flows, yielding substantial variability, yet have some of the most stringent operational requirements of any engineering ...

In response to the increasing demand for efficient resource utilization in data center networks (DCNs), the development of intelligent load-balancing algorithms has become crucial. This article introduces the dual double deep Q network (D 2 DQN) algorithm, designed for software-defined networking (SDN) environments within data centers. By leveraging deep reinforcement learning,

Data collected from an operational Google data center during 29 days represent a very rich and very useful source of information for understanding the main features of a data center. In this paper, we highlight the strong heterogeneity of jobs. The distribution of job execution duration shows a high disparity, as well as the job waiting time before being scheduled. The resource requests in terms of CPU and memory are also analyzed. The knowledge of all these features is needed to design models of jobs, machines and resource requests that are representative of a real data center.

Data Center (DC) management aims at promptly serving user requests while minimizing the energy consumed. This is achieved by turning off unnecessary servers to save energy and adapting the number of servers that are on to the time-varying and heterogeneous user requests. A great change in the number of servers on leads to a considerable management effort, also called control effort in the literature, which should be reduced as much as possible. Since feedback control can improve the performance of computing systems and networks, we propose to use it to achieve this dynamic capacity provisioning of the DC. In order to design this feedback control, first, we developed a dynamic model of the DC. The purpose of this paper is to design a feedback control strategy based on the DC model, able to optimize i) the Quality of Service, ii) the energy consumed and iii) the management effort. A simple Reactive open-loop Control which provides an amount of energy equal to the amount requested in the previous time interval is considered as a benchmark for comparison. Second, two feedback controls based on the balance equations of the DC are studied, namely i) Reactive Feedback Control providing an amount of energy equal to that provided by the reactive open-loop control but adding the accumulated demand that has not yet been served, and ii) Model Predictive Control optimizing a constrained cost that weights the management effort and the prediction error. Reactive Control, Reactive Feedback Control and Model Predictive Control are compared in terms of energy consumed, energy error and management effort. Quantitative results of the comparative performance evaluation are given, based on a data set collected from a real DC. INDEX TERMS Data center management, energy efficiency, quality of service, dynamic capacity provisioning, reactive control, reactive feedback control, model predictive control.

Your article is protected by copyright and all rights are held exclusively by Springer-Verlag London. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to self-archive your article, please use the accepted manuscript version for posting on your own website. You may further deposit the accepted manuscript version in any repository, provided it is only made publicly available 12 months after official publication or later and provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at link.springer.com".

Cloud computing and data centers that support this paradigm are rapidly evolving in order to satisfy new demands. These ever-growing needs represent an energy-related challenge to achieve sustainability and cost reduction. In this paper, we define an expert and intelligent system that applies various energy policies. These policies are employed to maximize the energy-efficiency of data-center resources by simulating a realistic environment and heterogeneous workload in a trustworthy tool. An environmental and economic impact of around 20% of energy consumption can be saved in high-utilization scenarios without exerting any noticeable impact on data-center performance if an adequate policy is applied.

Cloud computing has emerged as a new paradigm for providing on-demand computing resources and outsourcing software and hardware infrastructures. Load balancing is one of the major concerns in cloud computing environment means how to distribute load efficiently among all the nodes. For solving such a problem, we need some load balancing algorithms, so in this paper we will compare the existing algorithms for web application.and based on results obtained we choose the best among them.

Recent developments in storage class memory (SCM) such as PCM, MRAM, resistive RAM (RRAM), and spin-transfer torque (STT)-RAM have strengthened their leadership as storage media for memory-based file systems. Traditional Linux memory-based file systems such as Ramfs and Tmpfs utilize the Linux page cache as a file system. These file systems have unnecessary overheads when adopted for SCM file system. Therefore, we propose a new memory-based file system using Memory Zone Partitioning called ZonFS, by extending the Linux Ramfs. In particular, we define a storage zone for SCM, modify the Ramfs to allocate a file system page from SCM. ZonFS avoids running Linux VM kernel codes such as (i) inserting pages allocated from SCM into the LRU list for VM page replacement and (ii) checking dirty pages for writeback to disk. Our extensive evaluations indicate that ZonFS has up to 9.1 and 14.1% higher I/O throughputs than native Ramfs and Tmpfs. Moreover, we also analyze performance behavior of ZonFS under the non-uniform memory access architecture of SCMs on a 40 manycore machine with various configurations such as file sharing level and file stripping level. Our evaluations show that memory controller contention and inter-node link congestion significantly affect the file system's performance and scalability.

Now a days organizing the Network is very complex and challenging issue. To control, manage, and to provide a secure communication network, network managers must grapple with low-level vendor-specific configuration to implement complex high-level network policies .Most of the previous proposals to make networks easier to manage, many solutions to network management problems amount to stop-gap solutions because of the complexity of changing the underlying infrastructure. The rigidity of the underlying infrastructure presents few considerations for innovation or improvement, since network devices have generally been closed, proprietary, and vertically integrated. A new approach in networking, software defined networking (SDN), suggests separating the data plane and the control plane, making network switches and routers in the data plane simple packet forwarding devices and leaving a logically centralized software program to manage the behavior of the entire network. SDN introduces new...

Software-Defined Networking (SDN) has been gaining increasing attention in both the research and the industry communities. Separating the control and data planes has brought many advantages such as greater control plane programmability, more vendor independence, possibility of network virtualization, and lower operational expenses. SDN deployments are possible in a variety of contexts: Enterprise networks, Datacenter networks, and Wide Area Networks (WANs). However, SDN raises several concerns for WANs including performance limitations due to the larger propagation delays, the increased controller work load due to a larger number of network elements, and concerns about performance impacts of the controller placement. This study attempts to address some of these issues by examining the effects of using source routing as an alternative to traditional distributed routing in SDN-based WANs. Our simulations and analysis show that source routing can bring significant gains in SDN performance in WANs, improve network scalability, and reduce the network performance sensitivity to controller placement.

The research introduced in this paper focuses on controller scalability and performance issues in Software-Defined Networks (SDNs), and discusses a new routing scheme that leverages a variation of Source Routing for use in OpenFlow-based networks. The research aims to reduce the state needed to be distributed to the network devices by the controller(s) in SDNs, and in return improve the scale, convergence time, fault tolerance and cost of such network architectures.