Power provisioning for a warehouse-sized computer

The development of energy management systems (EMS) has attracted increasing attention during the last years. One of the main goals of EMS is to balance the power usage and generation, while also maintaining the quality of life (QoL) of the users. In this paper, a distributed coordination framework for on-line scheduling of appliances and control of the aggregated power demand of households is proposed. Each household consists of a set of appliances, and each appliance is modeled using a probabilistic generative model of its power usage profile, which can be updated through the day to indicate changes in user preferences. The coordination framework is formulated as a receding horizon distributed optimization, where the households' QoL, and the deviation from a scheduled usage are taken into account. The implemented distributed optimization can be seen as a negotiation among the households and a coordinator: the coordinator seeks to balance the aggregated power consumption by minimizing the deviation from a scheduled aggregated power usage, while each household tries not to deviate much from its preferred usage pattern.

Cloud infrastructures increasingly include a heterogeneous mix of components in terms of performance, power, and energy usage. As the size of cloud infrastructures grows, power consumption becomes a significant constraint. We use Apache Mesos and Apache Aurora, which provide massive scalability to web-scale applications, to demonstrate how a policy driven approach involving bin-packing workloads according to their power profiles, instead of the default allocation by Mesos and Aurora, can effectively reduce the peak-power and energy usage as well as the node utilization, when workloads are co-scheduled. Our experimental results show reductions of 11% in peak power, 86% for total energy usage, and an increase in utilization of 148% for memory and 8% CPU for the different policies.

The smart grid systems, in replace of the traditional power grid systems, have been widely used among some well-known telecommunication, IT and power industries. These systems have multiple advantages such as energy efficiency, reliability and self-monitoring. To prevent power outage, threshold based power usage control (PUC) in a smart grid considers a situation where the utility company sets a threshold to control the total power usage of a neighborhood. If the total power usage exceeds the threshold, certain households need to reduce their power consumption. In PUC, the utility company needs to frequently collect power usage data from smart meters. It has been well documented that these power usage data can reveal a person’s daily activity and violate personal privacy. To avoid the privacy concern, privacy-preserving power usage control (P-PUC) protocols have been introduced. However, the existing P-PUC protocols are not very efficient and the computations cannot be outsourced to a cloud server. Thus, the utility company cannot take advantage of the cloud computing paradigm to potentially reduce its operational cost. The goal of this paper is to develop a P-PUC protocol whose computation/execution is outsourceable to a cloud. In addition, the proposed protocol is much more efficient than the existing P-PUC protocols. We will provide extensive empirical study to show the practicality of our proposed protocol.KeywordsSmart gridPrivacy-preservingPower usage control

In July 2000, the United Technologies Research Center (UTRC) was one of five recipients of a US Department of Energy contract under the Advanced Microturbine System (AMS) program managed by the Office of Distributed Energy (DE). The AMS program resulted from several government-industry workshops that recognized that microturbine systems could play an important role in improving customer choice and value for electrical power. That is, the group believed that electrical power could be delivered to customers more efficiently and reliably than the grid if an effective distributed energy strategy was followed. Further, the production of this distributed power would be accomplished with less undesirable pollutants of nitric oxides (NOx) unburned hydrocarbons (UHC), and carbon monoxide (CO). In 2000, the electrical grid delivered energy to US customers at a national average of approximately 32% efficiency. This value reflects a wide range of powerplants, but is dominated by older, coal burning stations that provide approximately 50% of US electrical power. The grid efficiency is also affected by transmission and distribution (T&D) line losses that can be significant during peak power usage. In some locations this loss is estimated to be 15%. Load pockets can also be so constrained that sufficient power cannotmore » be transmitted without requiring the installation of new wires. New T&D can be very expensive and challenging as it is often required in populated regions that do not want above ground wires. While historically grid reliability has satisfied most customers, increasing electronic transactions and the computer-controlled processes of the 'digital economy' demand higher reliability. For them, power outages can be very costly because of transaction, work-in-progress, or perishable commodity losses. Powerplants that produce the grid electrical power emit significant levels of undesirable NOx, UHC, and CO pollutants. The level of emission is quoted as either a technology metric or a system-output metric. A common form for the technology metric is in the units of PPM {at} 15% O2. In this case the metric reflects the molar fraction of the pollutant in the powerplant exhaust when corrected to a standard exhaust condition as containing 15% (molar) oxygen, assuring that the PPM concentrations are not altered by subsequent air addition or dilution. Since fuel combustion consumes oxygen, the output oxygen reference is equivalent to a fuel input reference. Hence, this technology metric reflects the moles of pollutant per mole of fuel input, but not the useful output of the powerplant-i.e. the power. The system-output metric does embrace the useful output and is often termed an output-based metric. A common form for the output-based metric is in the units of lb/MWh. This is a system metric relating the pounds of pollutant to output energy (e.g., MWh) of the powerplant.« less

SummaryThe emergence of power efficiency as a primary constraint in processor and system design poses new challenges concerning power and energy awareness for numerical libraries and scientific applications. Power consumption also plays a major role in the design of data centers, which may house petascale or exascale‐level computing systems. At these extreme scales, understanding and improving the energy efficiency of numerical libraries and their related applications becomes a crucial part of the successful implementation and operation of the computing system. In this paper, we study and investigate the practice of controlling a compute system's power usage, and we explore how different power caps affect the performance of numerical algorithms with different computational intensities. Further, we determine the impact, in terms of performance and energy usage, that these caps have on a system running scientific applications. This analysis will enable us to characterize the types of algorithms that benefit most from these power management schemes. Our experiments are performed using a set of representative kernels and several popular scientific benchmarks. We quantify a number of power and performance measurements and draw observations and conclusions that can be viewed as a roadmap to achieving energy efficiency in the design and execution of scientific algorithms.

Smart metering, the gateway between power users and power utilities, is one of the key devices in smart grid. In order to decrease the data volume for power consumption report sent from smart meters to power utilities, it is more desirable to use differential transmission scheme, in which a smart meter transmits data only when power consumption is changed. However, such a scheme incurs vulnerabilities. Since, in the differential transmission scheme, the corresponding radio activity is proportional to the power activity. This information can be used by attacker to detect whether the power user is at home. In this paper, we study the privacy of power user for the transmission scheme. When the power user is not present, two defense plans are proposed to generate null packets during idle time to emulate the packet transmission during busy time in order to elude the attacker. Then, Kolmogorov-Smirnov statistic based attack methods are proposed to combat the defense plan. Numerical results are used to illustrate the efficiency of the proposed defense plans.

Controlling energy usage in data centers, and storage in particular, continues to rise in importance. Many systems and models have examined energy efficiency through intelligent spin-down of disks and novel data layouts, yet little work has been done to examine how power usage over the course of months to years is impacted by the characteristics of the storage devices chosen for use. Long-term power usage is particularly important for archival storage systems, since it is a large contributor to overall system cost. In this work, we begin exploring the impact that broad policies (e.g. utilize high-bandwidth devices first) have upon the power efficiency of a disk based archival storage system of heterogeneous devices over the course of a year. Using a discrete event simulator, we found that even simple heuristic policies for allocating space can have significant impact on the power usage of a system. We show that our system growth policies can cause power usage to vary from 10% higher to 18% lower than a naive random data allocation scheme. We also found that under low read rates power is dominated by that used in standby modes. Most interestingly, we found cases where concentrating data on fewer devices yielded increased power usage.

Increased power consumption is a critical concern for smartphone users. While multi-core processors in smartphones have already emerged in market, current applications are yet to take full advantage of this new architecture, particularly in the area of managing power consumption. This paper addresses the issue of managing power consumption in multicore smartphones via a middleware layer that schedules optimal number of cores for currently running applications taking into account the tradeoff between power consumption, performance and user experience. The paper first describes a simple and accurate method to measure the overall power consumption and then studies the impact of scheduling seven different popular applications over one to four cores on the overall power consumption. Based on this study, the paper proposes three new power-aware scheduling algorithms that dynamically schedule optimal number of cores as well as dynamically adjust the voltage frequency of each online core to achieve the best tradeoff between power consumption, application performance and user experience under the current context. Evaluation from a prototype implementation of the middleware on a quad-core HTC One shows that these algorithms result in significant reduction in power consumption while ensuring good performance and user experience.

Autonomous underwater vehicles (AUVs) are used to execute an increasingly challenging set of missions in commercial, environmental and defense industries. The resources available to the AUV in service of these missions are typically a limited power supply and onboard sensing of its local environment. Optimal path planning is needed to maximize the chances that these AUVs will successfully complete long-endurance missions within their power budget. A time-optimal path planner has been recently developed to minimize AUV mission time required to traverse a dynamic ocean environment at a specified speed through the water. For many missions, time minimization is appropriate because the AUVs operate at a fixed propeller speed. However, the ultimate limiting constraint on AUV operations is often the onboard power supply, rather than mission time. While an empirical or theoretical relationship between mission time and power could be applied to estimate power usage in the path planner, the real power usage and availability on an AUV varies mission-to-mission, as a result of multiple factors, including vehicle buoyancy, battery charge cycle, fin configuration, and water type or quality. In this work, we use data collected from two mid-size AUVs operating in various conditions to learn the mission-to-mission variability in the power budget so that it could be incorporated into the mission planner.

This study presents a comprehensive analysis of power consumption in the context of AR applications on the HoloLens 2. As an ablation study, the research systematically dissects various aspects, shedding light on both hardware and software components. The power consumption was examined in diverse scenarios, ranging from the device at idle to running AR applications of increasing complexity. Overall, the study provides insights into the power management aspects associated with Hololens 2 AR devices and applications, offering cues for optimizing energy efficiency and enhancing the user experience. The findings confirm that display-related factors, such as the screen brightness and content complexity, significantly impact power consumption. However, the results reveal that power usage does not scale linearly with the number of objects in an AR scene due to overhead factors and object occlusion. Furthermore, usage scenarios such as lighting conditions and large/minor user motions are analyzed. Moreover, the influence of different development platforms, Unity and Unreal, on power consumption is discussed, highlighting their respective contributions to energy usage. These findings might be useful for researchers, developers, and users of AR technology.

Virtualisation is a major technology in cloud computing for optimising the cloud data centre's power usage. In the current scenario, most of the services are migrated to the cloud, putting more load on the cloud data centres. As a result, the data center's size expands resulting in increased energy usage. To address this problem, a resource allocation optimisation method that is both efficient and effective is necessary. The optimal utilisation of cloud infrastructure and optimisation algorithms plays a vital role. The cloud resources rely on the allocation policy of the virtual machine on cloud resources. A virtual machine placement technique, based on the Harris Hawk Optimisation (HHO) model for the cloud data centre is presented in this paper. The proposed HHO model aims to find the best place for virtual machines on suitable hosts with the least load and power consumption. PlanetLab's real-time workload traces are used for performance evaluation with existing PSO (Particle Swarm Optimisation) and PABFD (Best Fit Decreasing). The performance evaluation of the proposed method is done using power consumption, SLA, CPU utilisation, RAM utilisation, Execution time (ms) and the number of VM migrations. The performance evaluation is done using two simulation scenarios with scaling workload in scenario 1 and increasing resources for the virtual machine to study the performance in underloaded and overloaded conditions. Experimental results show that the proposed HHO algorithm improved execution time(ms) by 4%, had a 27% reduction in power consumption, a 16% reduction in SLA violation and an increase in resource utilisation by 17%. The HHO algorithm is also effective in handling dynamic and uncertain environments, making it suitable for real-world cloud infrastructures.

With the ever growing popularity of cloud computing and web services, Internet companies are in need of increased computing capacity to serve the demand. However, power has become a major limiting factor prohibiting the growth in industry: it is often the case that no more servers can be added to datacenters without surpassing the capacity of the existing power infrastructure. In this work, we first investigate the power utilization in Facebook datacenters. We observe that the combination of provisioning for peak power usage, highly fluctuating traffic, and multi-level power delivery infrastructure leads to significant power budget fragmentation problem and inefficiently low power utilization. To address this issue, our insight is that heterogeneity of power consumption patterns among different services provides opportunities to re-shape the power profile of each power node by re-distributing services. By grouping services with asynchronous peak times under the same power node, we can reduce the peak power of each node and thus creating more power head-rooms to allow more servers hosted, achieving higher throughput. Based on this insight, we develop a workload-aware service placement framework to systematically spread the service instances with synchronous power patterns evenly under the power supply tree, greatly reducing the peak power draw at power nodes. We then leverage dynamic power profile reshaping to maximally utilize the headroom unlocked by our placement framework. Our experiments based on real production workload and power traces show that we are able to host up to 13% more machines in production, without changing the underlying power infrastructure. Utilizing the unleashed power headroom with dynamic reshaping, we achieve up to an estimated total of 15% and 11% throughput improvement for latency-critical service and batch service respectively at the same time, with up to 44% of energy slack reduction.

Modern vending machines operate to serve the consumer easy-access demand for daily items such as food, drinks, or books. Purchasing processes are carried out via automation from item selection, payment, up to the item dispensing are done without interaction to the human and this can be carried out for 24 hours a day and 7 days a week. However, the vending machines operates for 24/7, consumes the same electrical load regardless of if there is a transaction. Despite the advancements of Industrial Revolution 4.0 (IR4.0) in many sectors, electrical power of vending machine is yet to be optimized. This research aims to optimize vending machine power consumption by using camera to detect human near to the vending machine and relays to control the power usage. Human can be detected via camera via Artificial Intelligence (AI) and this becomes the input to the Smart Relay. Abnormality such as electrical leakage that draws more power can be detected as well. IoE dashboard is developed for vending operator to monitor the power usage, leakage potential, optimization, and prediction of power consumption. The system saves about to 50 percent of electrical power usage in the vending machine and low energy wastage while maintaining the same vending machine capabilities.

Massive multiple-input multiple-output (MIMO) systems are designed to increase data capacity systems. However, there are growing social and economic concerns in developing these communication technologies. Energy efficient systems are desirable for these systems considering the costs and minimizing resources. Thus, the optimization of these approaches is significant in the advancement of green communication. This paper converges on the circuit power in modelling massive MIMO systems. Specifically, to apply various power consumption of the transceiver chains, to determine the desired power of the base station value for maximum energy efficiency, and to define the effects of a realistic circuit power consumption model in Massive MIMO systems. Mathematical models were developed, and the corresponding codes were simulated using MATLAB. Different processing schemes were also studied, namely, maximum ratio transmission/maximum ratio combining, and zero forcing for the perfect and imperfect single-cells scenario. In contrast, multiple cells consider different re-use factors. As observed, a low power wattage consumption of transceiver chains and base stations is desired to produce a more remarkable relative change in energy efficiency. Local oscillators' power usage is also recommended to be low wattage. Low-power systems utilize low energy consumption but not disregarding higher energy efficiency. Other factors in data throughput – bandwidth, transmit power, noise power spectral density, and path loss, can be studied to optimize energy-efficient massive MIMO systems.

Introduction: The substantial energy usage in the cloud computing system is a significant drawback both for the cloud providers along with the cloud service users. In order to decrease the amount of energy used, it is necessary to implement virtualization techniques. Objectives: this paper employs a GA to optimize the migration of VMs and reduce energy usage in a cloud environment. Methods: The VM consolidation method effectively handles cloud resources, meeting the needs of both cloud consumers and suppliers. Moreover, it helps in enhancing the efficiency of servers while simultaneously decreasing the excessive energy usage in data canters. Nevertheless, the unnecessary activities of the VM consolidation technique result in inadequate VM selection and improper VM assignment, causing low performance, QoS, and violations of SLAs. Data center management struggles with energy consumption. VM migration and placement works well for this. Data centers require energy-saving solutions without affecting other parameters. Results: The performance of the proposed method has been evaluated utilizing factors like CPU usage, memory usage, network speed, power usage, and SLA breaches. Conclusions: The comparative analysis of the proposed approach with existing methods highlights its effectiveness and trustworthiness.