Managing cost, performance, and reliability tradeoffs for energy-aware server provisioning

Guenter, Brian; Jain, Navendu; Williams, Charles

doi:10.1109/infcom.2011.5934917

Cited by 210 publications

(147 citation statements)

References 12 publications

Supporting

Mentioning

147

Contrasting

Order By: Relevance

“…A way to obtain optimal solutions consists of formulating the problem in terms of some mathematical program, for instance by using Integer Linear Programming, and using an existing solver to calculate the solution [37]. However, packing problems are known to be NP-hard.…”

Section: Optimization Problem Solvingmentioning

confidence: 99%

Toward sustainable data centers: a comprehensive energy management strategy

Guitart

2016

Computing

View full text Add to dashboard Cite

Data centers are major contributors to the emission of carbon dioxide to the atmosphere, and this contribution is expected to increase in the following years. This has encouraged the development of techniques to reduce the energy consumption and the environmental footprint of data centers. Whereas some of these techniques have succeeded to reduce the energy consumption of the hardware equipment of data centers (including IT, cooling, and power supply systems), we claim that sustainable data centers will be only possible if the problem is faced by means of a holistic approach that includes not only the aforementioned techniques but also intelligent and unifying solutions that enable a synergistic and energy-aware management of data centers. In this paper, we propose a comprehensive strategy to reduce the carbon footprint of data centers that uses the energy as a driver of their management procedures. In addition, we present a holistic management architecture for sustainable data centers that implements the aforementioned strategy, and we propose design guidelines to accomplish each step of the proposed strategy, referring to related achievements and enumerating the main challenges that must be still solved.

show abstract

Section: Optimization Problem Solvingmentioning

confidence: 99%

Toward sustainable data centers: a comprehensive energy management strategy

Guitart

2016

Computing

View full text Add to dashboard Cite

show abstract

“…The work of Guenter et al [7] presents an algorithm for a dynamic load distribution based on a load prediction. Additionally, they consider overheads caused by the change from one power state to another.…”

Section: Related Workmentioning

confidence: 99%

Overhead-aware Load Distribution and System Shutdown for Energy-Efficient Computing

Lenhardt

Schiffmann

2015

IJNC

View full text Add to dashboard Cite

The energy consumption of server farms is steadily increasing. This is mainly due to an increasing number of servers which are often underutilized most of the time. In this paper we discuss various strategies to improve the energy efficiency of a datacenter measured by the average number of operations executed per Joule. We assume a collection of heterogeneous server nodes that are characterized by their SPECpower-benchmarks. If a time-variable divisible (work)load should to be executed on such a datacenter the energy efficiency can be improved by a smart decomposition of this load into appropriate chunks. In the paper we discuss a sophisticated load distribution strategy and extend it by an adaptive power management for dynamically switching underutilized servers to performance states with lower energy consumption. Of course, also transitions to higher performance/energy states are possible if required by the current load. We introduce a new time slice model that allows a reduction of the switching overhead by means of a few merge and adjust cycles. The resulting ALD+ strategy was evaluated in a webserver environment with real Wikipedia traces. It achieved significant reductions of the energy consumption by the combination of load distribution and server switching by means of the time slice model. Moreover, ALD+ can be easily integrated into any parallel webserver setup.

show abstract

“…Data centres and manufacturing plants are large energy consumers, in critical need to reduce their electricity costs, which account for a big part of their operational cost (electricity accounts for 30-50% of operating costs) [5,6,7]. Understanding how to optimize price forecasts to deliver good cost-aware schedules is critical for this goal.…”

Section: Related Workmentioning

confidence: 99%

“…The methodology for calculating the price in the Irish all-island market, up to the end of 2011, was as follows: every half-hour of the trading day, the Single Electricity Market Operator (SEMO) 7 calculates the System Marginal Price (SMP). The SMP has two components: the Shadow Price representing the marginal cost per 1MW of power necessary to meet demand in a particular halfhour trading period, within an unconstrained schedule, e.g., no power transmission congestions; and the Uplift component, added to the Shadow Price in order to ensure the generators recover their total costs, e.g., start-up and no-load costs [18].…”

Section: Electricity Price Forecasting For the Irish Marketmentioning

confidence: 99%

Analyzing the impact of electricity price forecasting on energy cost-aware scheduling

Grimes

Ifrim

O’Sullivan

et al. 2014

Sustainable Computing: Informatics and Systems

View full text Add to dashboard Cite

Publication information AbstractEnergy cost-aware scheduling, i.e., scheduling that adapts to real-time energy price volatility, can save large energy consumers millions of dollars every year in electricity costs. Energy price forecasting coupled with energy priceaware scheduling, is a step towards this goal. In this work, we study cost-aware schedules and the effect of various price forecasting schemes on the end schedule-cost. We show that simply optimizing price forecasts based on classical regression error metrics (e.g., Mean Squared Error), does not work well for scheduling. Price forecasts that do result in significantly better schedules, optimize a combination of metrics, each having a different impact on the end-schedulecost. For example, both price estimation and price ranking are important for scheduling, but they carry different weight. We consider day-ahead energy price forecasting using the Irish Single Electricity Market as a case-study, and test our price forecasts for two real-world scheduling applications: animal feed manufacturing and home energy management systems. We show that price forecasts that co-optimize price estimation and price ranking, result in significant energy-cost savings. We believe our results are relevant for many real-life scheduling applications that are currently plagued with very large energy bills.

show abstract

Managing cost, performance, and reliability tradeoffs for energy-aware server provisioning

Cited by 210 publications

References 12 publications

Toward sustainable data centers: a comprehensive energy management strategy

Toward sustainable data centers: a comprehensive energy management strategy

Overhead-aware Load Distribution and System Shutdown for Energy-Efficient Computing

Analyzing the impact of electricity price forecasting on energy cost-aware scheduling

Contact Info

Product

Resources

About