Energy-aware job assignment in server farms with setup delays under LCFS and PS

Hyytiä, Esa; Righter, Rhonda; Aalto, Samuli

doi:10.1109/itc.2014.6932946

Cited by 15 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the average file size l is large, µ is relatively smaller under condition (19) than that under (20), and thus the sleeping probability is low under condition (19), which makes the working power consumption in the second term and the switching cost in the third term completely outweigh the static power consumption saved from sleeping, so the total power consumption monotonically increases with P t . Otherwise, a larger µ under condition (20) leads to a higher sleeping probability than that in (19), so the static power consumption saved from sleeping plays the main role at first and the total power decreases with P t . However, P (N,Pt) will go up as P t increases further.…”

Section: B Selection Of Sleeping Threshold and Transmit Powermentioning

confidence: 99%

See 1 more Smart Citation

Base-Station Sleeping Control and Power Matching for Energy–Delay Tradeoffs With Bursty Traffic

Bao

Miao

et al. 2016

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

Abstract-In this paper, we study sleeping control and power matching for a single cell in cellular networks with bursty traffic. The base station (BS) sleeps whenever the system is empty, and wakes up when N users are assembled during the sleep period. The service capacity of the BS in the active mode is controlled through adjusting its transmit power. The total power consumption and average delay are analyzed, based on which the impact of parameter N and transmit power on the energy-delay tradeoff is studied. It is shown that given the average traffic load, the more bursty the traffic is, the less the total power is consumed, while the delay performance of more bursty traffic is better only under certain circumstances. The optimal energy-delay tradeoff is then obtained through joint sleeping control and power matching optimization. The relationship between the optimal control parameters and the asymptotic performance are also provided. Moreover, the influence of the traffic autocorrelation is explored, which shows less impact on the system performance compared with that of the burstiness. Numerical results show the energy saving gain of the joint sleeping control and power matching scheme, as well as the impact of burstiness on the optimal energy-delay tradeoff.

show abstract

Section: B Selection Of Sleeping Threshold and Transmit Powermentioning

confidence: 99%

“…The Poisson model has been used a lot when random traffic arrivals are considered in energy-saving design [7]- [10], [20]- [22]. However, in practice the data traffic usually has bursty features.…”

Section: Introductionmentioning

confidence: 99%

Base-Station Sleeping Control and Power Matching for Energy–Delay Tradeoffs With Bursty Traffic

Bao

Miao

et al. 2016

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

show abstract

“…For example, server farms are vital components in cloud computing and advanced multi-server queueing models that include features essential for characterizing scheduling performance as well as energy efficiency need to be developed. Recent results in this area include [29,40,41] and analyze fundamental structural properties of policies that optimize the performance-energy trade-off. On the other hand, several works exist [20,67] that employ energy-driven Markov Decision Process (MDP) solutions.…”

Section: Energy-aware Network and Service Controlmentioning

confidence: 99%

State of the Art and Research Challenges in the Area of Autonomous Control for a Reliable Internet of Services

Mei

Berg²,

Ганчев

et al. 2018

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The explosive growth of the Internet has fundamentally changed the global society. The emergence of concepts like service-oriented architecture (SOA), Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service (IaaS), Network as a Service (NaaS) and Cloud Computing in general has catalyzed the migration from the information-oriented Internet into an Internet of Services (IoS). This has opened up virtually unbounded possibilities for the creation of new and innovative services that facilitate business processes and improve the quality of life. However, this also calls for new approaches to ensuring quality and reliability of these services. The goal of this book chapter is to first analyze the state-of-the-art in the area of autonomous control for a reliable IoS and then to identify the main research challenges within it. A general background and high-level description of the current state of knowledge is presented. Then, for each of the three subareas, namely the autonomous management and real-time control, methods and tools for monitoring and service prediction, and smart pricing and competition in multi-domain systems, a brief general introduction and background are presented, and a list of key research challenges is formulated. Keywords: Internet of Services (IoS) Á Autonomous control Autonomous management Á Service monitoring Á Service prediction Smart pricing 3 Autonomous Management and Real-Time Control On a fundamental level, the working group WG1, associated with this research sub-area, was primarily concerned with the management and control of networks, services, applications, and compositions of services or applications. Of particular interest were management and control techniques that span multiple levels, e.g., the network and service level.

show abstract

“…In this setting the use of MDP (Markov Decision Process) and Policy Iteration has been recently considered by Gebrehiwot et al in [28], where the data center is assumed to consist of two kinds of servers: normal always-on servers and instant-off servers, which go to sleep immediately after queue empties, i.e., there are no idle timers, and an explicit near optimal policy is obtained for minimizing the ERWS metric that uses as state the number of jobs in the queues and the busy/sleep status. Also, size-aware approaches with MDP have been recently applied by Hyytiä et al in [24,25].…”

Section: Optimal Sleep State Control In M/g/1 Queuementioning

confidence: 99%

Energy vs. QoX Network- and Cloud Services Management

Blanco

Liberal

Lassila

et al. 2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Network Performance (NP)-and more recently Quality of Service/Experience/anything (QoS/QoE/QoX)-based network management techniques focus on the maximization of associated Key Performance Indicators (KPIs). Such mechanisms are usually constrained by certain thresholds of other system design parameters. e.g., typically, cost. When applied to the current competitive heterogeneous Cloud Services scenario, this approach may have become obsolete due to its static nature. In fact, energy awareness and the capability of modern technologies to deliver multimedia content at different possible combinations of quality (and prize) demand a complex optimization framework. It is therefore necessary to define more flexible paradigms that make it possible to consider cost, energy and even other currently unforeseen design parameters not as simple constraints, but as tunable variables that play a role in the adaptation mechanisms. In this chapter we will briefly introduce most commonly used frameworks for multi-criteria optimization and evaluate them in different Energy vs. QoX sample scenarios. Finally, the current status of related network management tools will be described, so as to identify possible application areas.

show abstract

Energy-aware job assignment in server farms with setup delays under LCFS and PS

Cited by 15 publications

References 26 publications

Base-Station Sleeping Control and Power Matching for Energy–Delay Tradeoffs With Bursty Traffic

Base-Station Sleeping Control and Power Matching for Energy–Delay Tradeoffs With Bursty Traffic

State of the Art and Research Challenges in the Area of Autonomous Control for a Reliable Internet of Services

Energy vs. QoX Network- and Cloud Services Management

Contact Info

Product

Resources

About