Cost Of Data Centers Research Articles

Tensor-Based Optimal Temperature Control of CRACs in Multi-Datacenters

Optimal temperature control of computer room air conditioners (CRACs) is an effective way to lower energy costs in high-density data centers. To break the barrier of dimensionality when jointly optimizing the temperature of CRACs in multiple data centers (multi-datacenters) configured in-row cooler systems, a tensor-based sequential quadratic programming (SQP) method is presented in this study. This method takes the temperature tensors as input and transforms the original high-dimensional optimization problem into several lower-dimensional sub-problems. An effective approach to solving the non-convex optimization of these sub-problems is also proposed. The transformation method not only reduces the dimensionality of optimization but also increases its convergence speed. On the foundation of the tensor-based SQP, an optimized control strategy is constructed to adjust the outlet temperature of CRACs, with the objective of enhancing the cooling efficiency. The convergence behavior, maximum input temperature of racks, and cooling power are analyzed to illustrate the effectiveness of the proposed tensor-based optimization and control strategy.

Improvement of the Dynamic Priority Scheduling Algorithm Based on a Heapsort

The earliest deadline first (EDF) scheduling algorithm is a typical representative of the dynamic priority scheduling algorithm. However, once the system is overloaded, the deadline miss rate increases and the scheduling performance deteriorates sharply, which causes a reduction in system resource utilization. To overcome this problem, we proposed an improved dynamic priority scheduling algorithm based on heap sorting. The task deadline, task value, energy consumption, and other parameters were introduced. The fuzzy analytic hierarchy process (FAHP) and the value density method were then used to determine the comprehensive priority of tasks. A heapsort algorithm with a lower time complexity was used to sort the comprehensive priority index so as to reduce the sorting overhead of the system. The system sorting overhead was then introduced to improve the decision condition of the priority scheduling subset and expand the schedulable range of the algorithm. The experimental results showed that the improved method reduced the deadline miss rate by an average of 0.1789, which improved the scheduling performance of the algorithm. The optimized scheduling algorithm can be applied to industrial control to improve system efficiency, and reasonable resource scheduling can reduce data center costs.

A smart coordinated temperature feedback controller for energy-efficient data centers

Energy cost plays a big role in the running cost of data centers and cutting it would get great economic and green benefits. This paper presents a coordinated MPC-based (Model Predictive Control) scheduling strategy called Co-ThermoRing to smartly reduce energy cost in data centers. Co-ThermoRing makes use of an online hierarchical feedback control mechanism which is composed by a global cluster-level temperature controller and many local node-level efficiency controllers. The inlet temperatures of all nodes can be kept balanced to minimize the heat recirculation by the temperature controller, and DVFS (Dynamic Voltage and Frequency Scaling) technology is adopted by each efficiency controller to utilize every computing node intelligently. This method can also contain temperature and utilization fluctuations with little performance degradation. With a TPC-W (Transaction Processing Performance Benchmark™ W) run in a real data center to simulate an online bookstore behavior our method is proved to have less energy consumption in normal cases and emergency cases compared with existing solutions such as LRHex, C-Oracle-F and ThermoRing.

Reducing costs in HSM-based data centers

Reducing costs in HSM-based data centers

Reducing the Operational Cost of Cloud Data Centers through Renewable Energy

The success of cloud computing services has led to big computing infrastructures that are complex to manage and very costly to operate. In particular, power supply dominates the operational costs of big infrastructures, and several solutions have to be put in place to alleviate these operational costs and make the whole infrastructure more sustainable. In this paper, we investigate the case of a complex infrastructure composed of data centers (DCs) located in different geographical areas in which renewable energy generators are installed, co-located with the data centers, to reduce the amount of energy that must be purchased by the power grid. Since renewable energy generators are intermittent, the load management strategies of the infrastructure have to be adapted to the intermittent nature of the sources. In particular, we consider EcoMultiCloud , a load management strategy already proposed in the literature for multi-objective load management strategies, and we adapt it to the presence of renewable energy sources. Hence, cost reduction is achieved in the load allocation process, when virtual machines (VMs) are assigned to a data center of the considered infrastructure, by considering both energy cost variations and the presence of renewable energy production. Performance is analyzed for a specific infrastructure composed of four data centers. Results show that, despite being intermittent and highly variable, renewable energy can be effectively exploited in geographical data centers when a smart load allocation strategy is implemented. In addition, the results confirm that EcoMultiCloud is very flexible and is suited to the considered scenario.

Datacentre Total Cost of Ownership (TCO) Models : A Survey

Datacenter total cost of ownerships (TCO) tools and spreadsheets can be used to estimate the capital and operational costs required for running datacenters. These tools are helpful for business owners to improve and evaluate the costs and the underlying efficiency of such facilities or evaluate the costs of alternatives, such as off-site computing. Well understanding of the cost drivers of TCO models can provide more opportunities to business owners to control costs .In addition, they also introduce an analytical structure in which anecdotal information can be cross-checked for consistency with other well-known parameters driving data center costs. This work focuses on comparing between number of proposed tools and spreadsheets which are publicly available to calculate datacenter total cost of ownership (TCO), The comparison is based on many aspects such as what are the parameters included and not included in such tools and whether the tools are documented or not. Such an approach presents a solid ground for designing more and better tools and spreadsheets in the future.

Datacentre Total Cost of Ownership (TCO) Models: A Survey

Datacenter total cost of ownerships (TCO) tools and spreadsheets can be used to estimate the capital and operational costs required for running datacenters. These tools are helpful for business owners to improve and evaluate the costs and the underlying efficiency of such facilities or evaluate the costs of alternatives, such as off-site computing. Well understanding of the cost drivers of TCO models can provide more opportunities to business owners to control costs .In addition, they also introduce an analytical structure in which anecdotal information can be cross-checked for consistency with other well-known parameters driving data center costs. This work focuses on comparing between number of proposed tools and spreadsheets which are publicly available to calculate datacenter total cost of ownership (TCO), The comparison is based on many aspects such as what are the parameters included and not included in such tools and whether the tools are documented or not. Such an approach presents a solid ground for designing more and better tools and spreadsheets in the future.

A stochastic process-based server consolidation approach for dynamic workloads in cloud data centers

With the development of information technology, there is a need for computational works everywhere and every time. Thus, people should be able to carry out their heavy computations without having the burden of purchasing expensive hardware and software. Cloud computing is an attractive solution to such needs, but the high energy consumption of physical machines in a Cloud data center is a matter of great concern. Therefore, some of the low-loaded machines can be turned off or switched into low energy mode using server consolidation approaches. In this paper, a Stochastic Process-Based Dynamic Server Consolidation (SB-DSC) policy is developed to reduce the total cost of data centers while satisfying the required quality of service. A novel algorithm, which we call it Stochastic Process-Based BFD (SBBFD), is employed in SB-DSC policy to perform virtual machine placements over time. SBBFD overcomes most drawbacks of other algorithms proposed in the literature. The simulation results on real workload data show that SB-DSC leads to a noticeable reduction in total cost in terms of power consumption, SLA violations, number of mode switching and number of migrations.

Thermal benchmarking and modeling for HPC using big data applications

Characterizing thermal profiles of cluster nodes is an integral part of any approach that addresses thermal emergencies in a data center. Most existing thermal models make use of CPU utilization to estimate power consumption, which in turn facilitates outlet-temperature predictions. Such utilization-based thermal models may introduce errors due to inaccurate mappings from system utilization to outlet temperatures. To address this concern in the existing models, we eliminate utilization models as a middleman from the thermal model. In this paper, we propose a thermal model, tModel, that projects outlet temperatures from inlet temperatures as well as directly measured multicore temperatures rather than deploying a utilization model. In the first phase of this work, we perform extensive experimentation by varying applications types, their input data sizes, and cluster sizes. Simultaneously, we collect inlet, outlet, and multicore temperatures of cluster nodes running these diverse bigdata applications. The proposed thermal model estimates the outlet air temperature of the nodes to predict cooling costs. We validate the accuracy of our model against data gathered by thermal sensors in our cluster. Our results demonstrate that tModel estimates outlet temperatures of the cluster nodes with much higher accuracy over CPU-utilization based models. We further show that tModel is conducive of estimating the cooling cost of data centers using the predicted outlet temperatures.

Towards thermal-aware Hadoop clusters

With the exponential increase in cooling costs of large-scale data centers, thermal management must be adequately addressed. Recent trends have discovered one of the critical reasons behind the temperature rise turns out to be heat re-circulation within data center. In this study, we proposed a new resource- and thermal-aware scheduler in Hadoop clusters; our scheduler aims at minimizing peak inlet temperature across all nodes to reduce power consumption and cooling cost in data centers. The proposed dynamic scheduler makes job scheduling decisions based on current CPU/disk utilization and number of tasks running as well as the feedback given by all slave nodes at run-time. We deploy a thermal model to project respective temperature of each slave node in addition to neighbor’s heat contribution. The thermal-aware scheduler is integrated with the Hadoop’s scheduling mechanism. We test our schedulers by running a set of Hadoop benchmarks (e.g., WordCount, DistributedGrep, PI and TeraSort) under various temperature conditions, utilization thresholds, and cluster sizes. The experimental results show that our scheduler achieves an average inlet temperature reduction by 2.5 °C over the default FIFO scheduler; our scheduling solution saves approximately 15% of cooling cost with marginal performance degradation.

Model for Automated and Improved Utilization of Existing Computer Resources on an Example of Web Servers

Information technology is under constant innovation pressure to provide the highest level of data availability – i.e., the continuous functioning of operating systems. This is the very reason for an accelerated development of complex systems encompassed by the term cloud computing. Among other things, such solutions are aimed to ensure high-level availability of complex systems and architecture. Numerous studies indicate that the main cause of high cost of data centers are procurement and maintenance costs of servers. Furthermore, this paper presents concrete practice examples which confirm that there are systems whose resources are not sufficiently exploited, but still have to be provided due to their importance. The high costs and inadequate utilization of the existing computer resources constitute the main motivation for the present research. In this study, we present a new model for automated and improved utilization of the existing computing resources. The model is verified by using an application for automated management of computer resources that was developed for this research and by several tests conducted on Web clusters.

Towards a Cost Optimal Design for a 5G Mobile Core Network Based on SDN and NFV

With the rapid growth of user traffic, service innovation, and the persistent necessity to reduce costs, today’s mobile operators are faced with several challenges. In networking, two concepts have emerged aiming at cost reduction, increase of network scalability and deployment flexibility, namely Network Functions Virtualization (NFV) and Software Defined Networking (SDN). NFV mitigates the dependency on hardware, where mobile network functions are deployed as software virtual network functions on commodity servers at cloud infrastructure, i.e., data centers. SDN provides a programmable and flexible network control by decoupling the mobile network functions into control plane and data plane functions. The design of the next generation mobile network (5G) requires new planning and dimensioning models to achieve a cost optimal design that supports a wide range of traffic demands. We propose three optimization models that aim at minimizing the network load cost as well as data center resources cost by finding the optimal placement of the data centers as well the SDN and NFV mobile network functions. The optimization solutions demonstrate the trade-offs between the different data center deployments, i.e., centralized or distributed, and the different cost factors, i.e., optimal network load cost or data center resources cost. We propose a Pareto optimal multi-objective model that achieves a balance between network and data center cost. Additionally, we use prior inference, based on the solutions of the single objectives, to pre-select data center locations for the multi-objective model that results in reducing the optimization complexity and achieves savings in run time while keeping a minimal optimality gap.

Energy-proportional profiling and accounting in heterogeneous virtualized environments

The costs of current data centers are mostly driven by their energy consumption (specifically by the air conditioning, computing and networking infrastructure). Yet, current pricing models are usually static and rarely consider the facilities’ energy consumption per user. The challenge is to provide a fair and predictable model to attribute the overall energy costs per virtual machine (VM) in heterogeneous environments. In this paper we introduce EPAVE, a model for Energy-Proportional Accounting in VM-based Environments. EPAVE allows transparent, reproducible and predictive cost calculation for users and for Cloud providers. It provides a full-cost model that does not account only for the dynamic energy consumption of a given VM, but also includes the proportional static cost of using a Cloud infrastructure. It comes with PowerIndex, a profiling and estimation model, which is able to profile the energy cost of a VM on a given server architecture and can then estimate its energy cost on a different one. We provide performance results of PowerIndex on real hardware, and we discuss the use cases and applicability of EPAVE.

Joint Optimization of Operational Cost and Performance Interference in Cloud Data Centers

Virtual machine (VM) scheduling is an important technique for the efficient operation of the computing resources in a data center. Previous work has mainly focused on consolidating VMs to improve resource utilization and to optimize energy consumption. However, the interference between collocated VMs is usually ignored, which can result in much worse performance degradation of the applications running on the VMs due to the contention of the shared resources. Based on this observation, we aim at designing efficient VM assignment and scheduling strategies in which we consider optimizing both the operational cost of the data center and the performance degradation of the running applications. We then propose a general model that captures the tradeoff between the two contradictory objectives. We present offline and online solutions for this problem by exploiting the spatial and temporal information of performance interference of VM collocation, where VM scheduling is performed by jointly considering the combinations and the life-cycle overlap of the VMs. Evaluation results show that the proposed methods can generate efficient schedules for VMs, achieving low operational cost while significantly reducing the performance degradation of applications in cloud data centers.

Learning-Based Run-Time Power and Energy Management of Multi/Many-Core Systems: Current and Future Trends

Multi/Many-core systems are prevalent in several application domains targeting different scales of computing such as embedded and cloud computing. These systems are able to fulfil the ever-increasing performance requirements by exploiting their parallel processing capabilities. However, effective power/energy management is required during system operations due to several reasons such as to increase the operational time of battery operated systems, reduce the energy cost of datacenters, and improve thermal efficiency and reliability. This article provides an extensive survey of learning-based run-time power/energy management approaches. The survey includes a taxonomy of the learning-based approaches. These approaches perform design-time and/or run-time power/energy management by employing some learning principles such as reinforcement learning. The survey also highlights the trends followed by the learning-based run-time power management approaches, their upcoming trends and open research challenges.

ОСОБЕННОСТИ ПОСТРОЕНИЯ WEB-ПРИЛОЖЕНИЙ ИНФОРМАЦИОННОГО ОБЕСПЕЧЕНИЯ СИСТЕМ АВТОМАТИЧЕСКОГО УПРАВЛЕНИЯ

The article focuses on development telecommunication functions providing remote control of technological processes, their visualizing, and executive mechanisms of different processing facilities (e.g. executive mechanisms of a small-size dryer created in Murmansk State Technical University in order to smoke and dry fish). The solution of the problem became possible due to the web application developed according to ASP (Active Server Pages) technology and used on top the web-server controlled by IIS (Internet Information Services), Microsoft. The advantage of the web-application is that it allows logging onto the automated control system irrespective of a small-size dryer location (i.e. working place is mobile), and technological process control is possible from any mobile platforms and operational systems. Due to using MS SQL Server Express it became possible to organize nonstop data exchange between automatic system of the small dryer and the end user (simultaneous work of several users is possible). The article presents the scheme of the user and web-application interface. Class of the project safety (III) has been determined, as well as corresponding basic protection measures, which provide implementing the user identification and authentication systems, antivirus and network intrusion systems. Project costs proved to be lower than the cost of software TRACE MODE Data Center (35.000 rubles instead of 58.000 rubles), which is found a truly sustainable solutions to realize a remote access to the automation facility. A growing number of users doesn’t affect the final cost of the project.

A Comparative Study of Metaheuristics based Task Scheduling in Distributed Environment

Objectives: To make an extensive survey on various meta-heuristic and hybrid task scheduling along with their classification patterns and to find the scope of improvement in these techniques. Method: This paper carries to the deep study of 99 reputed research papers from Springer, IEEE, Elsevier, Scopus indexed; SCI indexed of well-known renowned journals. These research papers are selected by taking into consideration of relevance to research area. These scheduling algorithms are compared in terms of their performance metrics, environments and results. Findings: This paper described that there are various renowned researchers who have proposed various meta-heuristic task scheduling techniques to achieve the optimum results but after the extensive survey of various scheduling techniques based on genetic, Simulated Annealing (SA), ACO, PSO and hybrid reveals that a lot of dimensions are yet to be explored in terms of datacenter cost, virtual machine migration, energy consumption and Service-Level Agreement etc. Application: It discusses numerous meta-heuristic based task scheduling algorithms with their classification patterns so as to find the gap in the already proposed algorithm and suggest the untouched areas for the further research.

I/O access frequency-aware cache method on KVM/QEMU

Together with the rapid development of IT technology, cloud computing has been considered as the next generation's computing infrastructure. One of the essential part of cloud computing is the virtual machine technology that enables to reduce the data center cost with better resource utilization. Especially, virtual desktop infrastructure (VDI) is receiving explosive attentions from IT markets because of its advantages of easier software management, greater data protection, and lower cost. However, sharing physical resources in VDI to consolidate multiple guest virtual machines (VMs) on a host has a tradeoff that can lead to significant I/O degradation. Optimizing I/O virtualization overhead is a challenging task because it needs to scrutinize multiple software layers between guest VMs and host where those VMs are executing. In this paper, we present a hypervisor-level cache, called hyperCache, which is possible to provide a shortcut in KVM/QEMU. It intercepts I/O requests in the hypervisor and analyses their I/O access patterns to select data retaining high access frequency. Also, it has a capability of maintaining the appropriate cache memory size by utilizing the cache block map. Our experimental results demonstrate that our method improves I/O bandwidth by up to 4.7x over the existing QEMU.

Extending Demand Response to Tenants in Cloud Data Centers via Non-Intrusive Workload Flexibility Pricing

Participating in demand response programs is a promising tool for reducing energy costs in data centers by modulating energy consumption. Toward this end, data centers can employ a rich set of resource management knobs, such as workload shifting and dynamic server provisioning. Nonetheless, these knobs may not be readily available in a cloud data center (CDC) that serves cloud tenants/users, because workloads in CDCs are managed by tenants themselves who are typically charged based on a usage-based or flat-rate pricing and often have no incentive to cooperate with the CDC operator for demand response and cost saving. Toward breaking such “split incentive” hurdle, a few recent studies have tried market-based mechanisms, such as dynamic pricing, inside CDCs. However, such mechanisms often rely on complex designs that are hard to implement and difficult to cope with by tenants. To address this limitation, we propose a novel incentive mechanism that is not dynamic, i.e., it keeps pricing for cloud resources unchanged for a long period. While it charges tenants based on a usage-based pricing (UP) as used by today's major cloud operators, it rewards tenants proportionally based on the time length that tenants set as deadlines for completing their workloads. This new mechanism is called UP with monetary reward (UPMR). We demonstrate the effectiveness of UPMR both analytically and empirically, showing: 1) UPMR can effectively reduce the CDC's peak power consumption and energy cost without decreasing the CDC's profit and 2) UPMR outperforms the state-of-the-art approaches that are used by today's CDC operators to charge their tenants in terms of the profit gained by the CDC.

BOSS: An Efficient Data Distribution Strategy for Object Storage Systems With Hybrid Devices

Hybrid object storage systems provide opportunities to achieve high performance and energy efficiency with low cost for enterprise data centers. Existing object storage systems, however, distribute data objects in the system without considering the heterogeneity of the underlying devices and the asymmetric data access patterns. Therefore, the system performance and energy efficiency may degrade as data are placed on improper storage devices. For example, energy-efficient high-density archive hard disk drives (archive HDDs) are significantly slower than normal HDDs and solid state disks (SSDs), which mean that the archive HDDs are not appropriate for storing frequently accessed objects. Besides, flash-based SSDs have limited write endurance, which makes SSDs vulnerable for storing write-intensive objects. In this paper, we analyze various real enterprise workloads and find that read and write requests are not uniformly distributed to data objects. Based on the observations, we propose a novel strategy, biased object storage strategy (BOSS), to reduce writes to SSDs and improve system performance for hybrid object storage systems. Different from conventional uniform and fixed data distribution strategies, the BOSS can distribute and migrate data objects to various types of devices dynamically, according to the data access patterns collected online. The experimental results show that the BOSS can reduce 64% of writes on SSDs and improve system performance by 29.51% on average, while maintaining a high level of load balance.