Decoupled Speed Scaling: Analysis and Evaluation

Elahi, Maryam; Williamson, Carey; Woelfel, Philipp

doi:10.1109/qest.2012.35

Cited by 4 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Capacity right-sizing: Over the past decade there has been a large amount of attention given to the design of hardware and algorithms that can adapt energy usage to create "power proportional" systems, that use power in proportion to the utilization of the computing system. Such designs focus on speed-scaling [8], [16], [26], [82], [84], [94], power-capping [15], [32], moving servers into and out of power saving modes [43], [55], [63], [65], [103], and many other features.…”

Section: A Why Data Centers?mentioning

confidence: 99%

Opportunities and challenges for data center demand response

Wierman

Liu

et al. 2014

International Green Computing Conference

160

View full text Add to dashboard Cite

This paper surveys the opportunities and challenges in an emerging area of research that has the potential to significantly ease the incorporation of renewable energy into the grid as well as electric power peak-load shaving: data center demand response. Data center demand response sits at the intersection of two growing fields: energy efficient data centers and demand response in the smart grid. As such, the literature related to data center demand response is sprinkled across multiple areas and worked on by diverse groups. Our goal in this survey is to demonstrate the potential of the field while also summarizing the progress that has been made and the challenges that remain.

show abstract

Section: A Why Data Centers?mentioning

confidence: 99%

Opportunities and challenges for data center demand response

Wierman

Liu

et al. 2014

International Green Computing Conference

160

View full text Add to dashboard Cite

show abstract

“…These decoupled speed scaling policies determine the speed based on the occupancy of a shadow PS scheduler that works on the same arrival process. The analytical result in [7] shows that for all load configurations, FSP-PS performs at least as well as PS for both slowdown and the sum of average response time and energy consumption (i.e., the cost). Further investigation is required to quantify the improvement under different load regimes.…”

Section: Fairness Studymentioning

confidence: 97%

“…In spite of the growing interest in the study of speedscaling policies, to the best of our knowledge there is no public-domain tool for the simulation of scheduling with speed scaling. There are a number of simulation results presented for speed scaling designs in recent literature [7,12,13]. A recent public-domain simulation tool for a single speed server has been developed to study size-based scheduling when exact knowledge of job sizes is not available [5].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simulation Modeling for Speed Scaling Designs

Elahi

Williamson

2017

Proceedings of the 10th EAI International Conference on Performance Evaluation Methodologies and Tools

Self Cite

View full text Add to dashboard Cite

This paper introduces an extensible simulation tool for the study of speed scaling designs for a single server with variable service rates. This simulator facilitates detailed performance analysis of scheduling and speed scaling policies under different background settings. Our component-based design separates the system configuration, like the power consumption model and the incoming workload, from the policy components for scheduling and speed scaling. Furthermore, the simulator allows for custom implementations of the data logger, so the instrumentation could be fine tuned to the desired level of detail for each run of the simulation. We present the design of the main components of our simulator. We then show example results to highlight the versatility of the simulator for studying different speed scaling configurations.

show abstract

Turbocharged Speed Scaling: Analysis and Evaluation

Elahi

Williamson

Woelfel

2014

2014 IEEE 22nd International Symposium on Modelling, Analysis &Amp; Simulation of Computer and Telecommunication Systems

Self Cite

View full text Add to dashboard Cite

In speed scaling systems, the execution speed of a processor can be adjusted dynamically under operating system control to provide tradeoffs between response time, fairness, and energy consumption. In this paper, we propose and evaluate an approach called envelope-based turbocharging, applied in conjunction with Fair Sojourn Protocol (FSP) scheduling and job-count-based speed scaling. This approach restores the strict dominance of FSP over Processor Sharing (PS) in speed scaling systems, and preserves fairness. We evaluate our new approach using analysis and simulation. The simulation results show that Turbocharged FSP (T-FSP) outperforms PS in response time, and often in energy consumption as well. Furthermore, the energy consumption of T-FSP is typically within 15% of optimal.

show abstract

Decoupled Speed Scaling: Analysis and Evaluation

Cited by 4 publications

References 33 publications

Opportunities and challenges for data center demand response

Opportunities and challenges for data center demand response

Simulation Modeling for Speed Scaling Designs

Turbocharged Speed Scaling: Analysis and Evaluation

Contact Info

Product

Resources

About