Energy-efficient policies for embedded clusters

Xu, Ruibin; Zhu, Dakai; Rusu, Cosmin; Melhem, Rami; Mossé, Daniel

doi:10.1145/1065910.1065912

Cited by 52 publications

(20 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The leakage power consumption function of the system could be modelled as a nonnegative constant when leakage power consumption is irrelevant to the temperature (Xu et al 2005;Jian-Jia et al 2007). When the leakage power consumption is related to the temperature, it could be approximately modelled by a linear function of the temperature (Chantem et al 2008).…”

Section: Power Modelmentioning

confidence: 99%

Schedulability analysis in hard real-time systems under thermal constraints

2010

View full text Add to dashboard Cite

In this paper, we study thermal-constrained hard real-time systems, where real-time guarantees must be met without exceeding safe temperature levels within the processor. Dynamic speed scaling is one of the major techniques to manage power so as to maintain safe temperature levels. As example, we adopt a reactive speed control technique in our work. We design an extended busy-period analysis methodology to perform schedulability analysis for general task arrivals under reactive speed control with First-In-First-Out (FIFO), Static-Priority (SP), and Earliest-Deadline-First (EDF) scheduling. As a special case, we obtain a closed-form formula for the worstcase response time of jobs under the leaky-bucket task arrival model. Our data show how reactive speed control can decrease the worst-case response time of tasks in comparison with any constant-speed scheme.

show abstract

Section: Power Modelmentioning

confidence: 99%

Schedulability analysis in hard real-time systems under thermal constraints

2010

View full text Add to dashboard Cite

show abstract

“…Elnozahy et al evaluated policies that combine DVS and ON/OFF techniques for cluster-wide power management in server farms (Elnozahy et al 2002a;Lefurgy et al 2003). Considering the effects of static power and discrete processing frequencies, Xu et al proposed schemes that adjust the number of active servers based on the system load (Xu et al 2005), and the schemes are extended by considering QoS requirements in heterogeneous clusters (Rusu et al 2006). Sharma et al investigated adaptive algorithms for voltage scaling in QoS-enabled web servers to minimize energy consumption subject to service delay constraints (Sharma et al 2003).…”

Section: Related Workmentioning

confidence: 99%

“…When the system is configured with NMR, there are at most M N NMR groups available. Due to energy considerations (Elnozahy et al 2002a;Xu et al 2005;Rusu et al 2006), it may be more energy efficient to use fewer NMR groups than what is available and turn the unused servers off.…”

Section: Minimize Energy With Fixed Reliability Goalmentioning

confidence: 99%

Energy efficient redundant configurations for real-time parallel reliable servers

2009

Self Cite

View full text Add to dashboard Cite

Modular redundancy and temporal redundancy are traditional techniques to increase system reliability. In addition to being used as temporal redundancy, with technology advancements, slack time in a system can also be used by energy management schemes to save energy. In this paper, we consider the combination of modular and temporal redundancy to achieve energy efficient reliable real-time service provided by multiple servers. We first propose an efficient adaptive parallel recovery scheme that appropriately processes service requests in parallel to increase the number of faults that can be tolerated and thus system reliability. Then we explore schemes to determine the optimal redundant configurations of the parallel servers to minimize system energy consumption for a given reliability goal or to maximize system reliability for a given energy budget. Our analysis results show that small requests, optimistic approaches, and parallel recovery favor lower levels of modular redundancy, while large requests, pessimistic approaches and restricted serial recovery favor higher levels of modular redundancy.

show abstract

“…Computational offloading has been used extensively for power-aware load balancing, for environments ranging from clusters of workstations [22] to embedded devices [28]. The latter performs computational offloading in conjunction with setting CPU frequencies, to minimize energy consumption.…”

Section: Related Workmentioning

confidence: 99%

Energy-Aware Mobile Service Overlays: Cooperative Dynamic Power Management in Distributed Mobile Systems

Seshasayee

Nathuji

Schwan

2007

Fourth International Conference on Autonomic Computing (ICAC'07)

View full text Add to dashboard Cite

With their increasingly powerful computational resources and high-speed wireless communications, future mobile systems will have the ability to run sophisticated applications on collections of cooperative end devices. Mobility, however, requires dynamic management of these platforms' distributed resources, and such management can also be used to meet application quality requirements and prolong application lifetimes, the latter by best using available energy resources. This paper presents energy-aware Mobile Service Overlays (MSOs), a set of mechanisms and associated policies for running mobile applications across multiple, cooperating machines while actively performing power management to extend system usability lifetimes. MSO policies manage energy consumption by (i) allocating application components to available nodes based upon their current energy capacities and resource availabilities, (ii) monitoring for, and responding to changes in energy and resource characteristics, and (iii) dynamically exploiting energy-performance tradeoffs in overprovisioned situations. Coupled with mobility, such cooperation enables multiple mobile platforms to bring their joint resources to bear on complex application tasks, providing significant benefits to application lifetimes and performance. Evaluations of MSOs on a MANET computing testbed indicate an extension in system lifetime of upto 10% for an example application.

show abstract

Energy-efficient policies for embedded clusters

Cited by 52 publications

References 10 publications

Schedulability analysis in hard real-time systems under thermal constraints

Schedulability analysis in hard real-time systems under thermal constraints

Energy efficient redundant configurations for real-time parallel reliable servers

Energy-Aware Mobile Service Overlays: Cooperative Dynamic Power Management in Distributed Mobile Systems

Contact Info

Product

Resources

About