umu.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Energy-efficient cloud computing: autonomic resource provisioning for datacenters
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap. (Cloud computing)
2018 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

Energy efficiency has become an increasingly important concern in data centers because of issues associated with energy consumption, such as capital costs, operating expenses, and environmental impact. While energy loss due to suboptimal use of facilities and non-IT equipment has largely been reduced through the use of best-practice technologies, addressing energy wastage in IT equipment still requires the design and implementation of energy-aware resource management systems. This thesis focuses on the development of resource allocation methods to improve energy efficiency in data centers. The thesis employs three approaches to improve efficiency for optimized power and performance: scaling virtual machine (VM) and server processing capabilities to reduce energy consumption; improving resource usage through workload consolidation; and exploiting resource heterogeneity.

To achieve these goals, the first part of the thesis proposes models, algorithms, and techniques that reduce energy usage through the use of VM scaling, VM sizing for CPU and memory, CPU frequency adaptation, as well as hardware power capping for server-level resource allocation. The proposed online performance and power models capture system behavior while adapting to changes in the underlying infrastructure. Based on these models, the thesis proposes controllers that dynamically determine power-efficient resource allocations while minimizing performance penalty.

These methods are then extended to support resource overbooking and workload consolidation to improve resource utilization and energy efficiency across the cluster or data center. In order to cater for different performance requirements among collocated applications, such as latency-sensitive services and batch jobs, the controllers apply service differentiation among prioritized VMs and performance isolation techniques, including CPU pinning, quota enforcement, and online resource tuning.

This thesis also considers resource heterogeneity and proposes heterogeneousaware scheduling techniques to improve energy efficiency by integrating hardware accelerators (in this case FPGAs) and exploiting differences in energy footprint of different servers. In addition, the thesis provides a comprehensive study of the overheads associated with a number of virtualization platforms in order to understand the trade-offs provided by the latest technological advances and to make the best resource allocation decisions accordingly. The proposed methods in this thesis are evaluated by implementing prototypes on real testbeds and conducting experiments using real workload data taken from production systems and synthetic workload data that we generated. Our evaluation results demonstrate that the proposed approaches provide improved energy management of resources in virtualized data centers.

sted, utgiver, år, opplag, sider
Umeå: Umeå University , 2018. , s. 63
Serie
Report / UMINF, ISSN 0348-0542 ; 18.05
Emneord [en]
Cloud computing, datacenter, energy-efficiency, performance management, virtualization
HSV kategori
Identifikatorer
URN: urn:nbn:se:umu:diva-145926ISBN: 978-91-7601-862-0 (tryckt)OAI: oai:DiVA.org:umu-145926DiVA, id: diva2:1192294
Disputas
2018-04-16, MA121, MIT-building, Umeå, 10:15 (engelsk)
Opponent
Veileder
Tilgjengelig fra: 2018-03-26 Laget: 2018-03-22 Sist oppdatert: 2018-06-09bibliografisk kontrollert
Delarbeid
1. A combined frequency scaling and application elasticity approach for energy-efficient cloud computing
Åpne denne publikasjonen i ny fane eller vindu >>A combined frequency scaling and application elasticity approach for energy-efficient cloud computing
2014 (engelsk)Inngår i: Sustainable Computing: Informatics and Systems, ISSN 2210-5379, E-ISSN 2210-5387, Vol. 4, nr 4, s. 205-214Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Energy management has become increasingly necessary in large-scale cloud data centers to address high operational costs and carbon footprints to the environment. In this work, we combine three management techniques that can be used to control cloud data centers in an energy-efficient manner: changing the number of virtual machines, the number of cores, and scaling the CPU frequencies. We present a feedback controller that determines an optimal configuration to minimize energy consumption while meeting performance objectives. The controller can be configured to accomplish these goals in a stable manner, without causing large oscillations in the resource allocations. To meet the needs of individual applications under different workload conditions, the controller parameters are automatically adjusted at runtime based on a system model that is learned online. The potential of the proposed approach is evaluated in a video encoding scenario. The results show that our combined approach achieves up to 34% energy savings compared to the constituent approaches—core change, virtual machine change, and CPU frequency change policies, while meeting the performance target.

sted, utgiver, år, opplag, sider
Amsterdam: Elsevier, 2014
Emneord
Cloud computing, Energy-efficiency, Quality-of-service, Virtualization, Frequency scaling, Application elasticity
HSV kategori
Forskningsprogram
datalogi
Identifikatorer
urn:nbn:se:umu:diva-100656 (URN)10.1016/j.suscom.2014.08.007 (DOI)000209576700002 ()
Forskningsfinansiär
Swedish Research Council, 2012-5908 f
Tilgjengelig fra: 2015-03-05 Laget: 2015-03-05 Sist oppdatert: 2018-06-07bibliografisk kontrollert
2. Autonomic resource management for optimized power and performance in multi-tenant clouds
Åpne denne publikasjonen i ny fane eller vindu >>Autonomic resource management for optimized power and performance in multi-tenant clouds
2016 (engelsk)Inngår i: 2016 IEEE INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING (ICAC) / [ed] Samuel Kounev, Holger Giese, Jie Liu, LOS ALAMITOS: IEEE Computer Society, 2016, s. 85-94Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We present an autonomic resource management framework that takes advantage of both virtual machine resizing (CPU and memory) and physical CPU frequency scaling to reduce the power consumption of servers while meeting performance requirements of colocated applications. We design online performance and power model estimators that capture the complex relationships between applications' performance and server power (respectively), and resource utilization. Based on these models, we devise two optimization strategies to determine the most power efficient configuration. We also show that an operator can tune the tradeoff between power and performance. Our evaluation using a set of cloud benchmarks compares the proposed solution in power savings against the Linux ondemand and performance CPU governors. The results show that our solution achieves power savings between 12% to 20% compared to the baseline performance governor, while still meeting applications' performance goals.

sted, utgiver, år, opplag, sider
LOS ALAMITOS: IEEE Computer Society, 2016
Serie
Proceedings of the International Conference on Autonomic Computing, ISSN 2474-0756
HSV kategori
Identifikatorer
urn:nbn:se:umu:diva-121089 (URN)10.1109/ICAC.2016.32 (DOI)000390681200013 ()978-1-5090-1654-9 (ISBN)
Konferanse
13th IEEE International Conference on Autonomic Computing (ICAC), JUL 17-22, 2016, Würzburg, Germany
Tilgjengelig fra: 2016-05-26 Laget: 2016-05-26 Sist oppdatert: 2018-06-07bibliografisk kontrollert
3. OptiBook: Optimal Resource Booking for Energy-efficient Datacenters
Åpne denne publikasjonen i ny fane eller vindu >>OptiBook: Optimal Resource Booking for Energy-efficient Datacenters
2017 (engelsk)Inngår i: 2017 IEEE/ACM 25th International Symposium on Quality of Service (IWQoS), IEEE Communications Society, 2017Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

A lack of energy proportionality, low resource utilization, and interference in virtualized infrastructure make the cloud a challenging target environment for improving energy efficiency. In this paper we present OptiBook, a system that improves energy proportionality and/or resource utilization to optimize performance and energy efficiency. OptiBook shares servers between latency-sensitive services and batch jobs, over- books the system in a controllable manner, uses vertical (CPU and DVFS) scaling for prioritized virtual machines, and applies performance isolation techniques such as CPU pinning and quota enforcement as well as online resource tuning to effectively improve energy efficiency. Our evaluations show that on average, OptiBook improves performance per watt by 20% and reduces energy consumption by 9% while minimizing SLO violations. 

sted, utgiver, år, opplag, sider
IEEE Communications Society, 2017
HSV kategori
Identifikatorer
urn:nbn:se:umu:diva-145492 (URN)10.1109/IWQoS.2017.7969135 (DOI)000428199300029 ()978-1-5386-2704-4 (ISBN)978-1-5386-2705-1 (ISBN)
Konferanse
2017 IEEE/ACM 25th International Symposium on Quality of Service (IWQoS), Vilanova i la Geltrú, Spain, June 14-16, 2017
Tilgjengelig fra: 2018-03-07 Laget: 2018-03-07 Sist oppdatert: 2018-06-09bibliografisk kontrollert
4. Power and Performance Optimization in FPGA-accelerated Clouds
Åpne denne publikasjonen i ny fane eller vindu >>Power and Performance Optimization in FPGA-accelerated Clouds
Vise andre…
2018 (engelsk)Inngår i: Concurrency and Computation, ISSN 1532-0626, E-ISSN 1532-0634, Vol. 30, nr 18, artikkel-id e4526Artikkel i tidsskrift (Annet vitenskapelig) Published
Abstract [en]

Energy management has become increasingly necessary in data centers to address all energy-related costs, including capital costs, operating expenses, and environmental impacts. Heterogeneous systems with mixed hardware architectures provide both throughput and processing efficiency for different specialized application types and thus have a potential for significant energy savings. However, the presence of multiple and different processing elements increases the complexity of resource assignment. In this paper, we propose a system for efficient resource management in heterogeneous clouds. The proposed approach maps applications' requirement to different resources reducing power usage with minimum impact on performance. A technique that combines the scheduling of custom hardware accelerators, in our case, Field-Programmable Gate Arrays (FPGAs) and optimized resource allocation technique for commodity servers, is proposed. We consider an energy-aware scheduling technique that uses both the applications' performance and their deadlines to control the assignment of FPGAs to applications that would consume the most energy. Once the scheduler has performed the mapping between a VM and an FPGA, an optimizer handles the remaining VMs in the server, using vertical scaling and CPU frequency adaptation to reduce energy consumption while maintaining the required performance. Our evaluation using interactive and data-intensive applications compare the effectiveness of the proposed solution in energy savings as well as maintaining applications performance, obtaining up to a 32% improvement in the performance-energy ratio on a mix of multimedia and e-commerce applications.

sted, utgiver, år, opplag, sider
John Wiley & Sons, 2018
Emneord
cloud computing, energy efficiency, FPGA-aware
HSV kategori
Identifikatorer
urn:nbn:se:umu:diva-121092 (URN)10.1002/cpe.4526 (DOI)000442575600010 ()
Forskningsfinansiär
Swedish Research Council
Tilgjengelig fra: 2016-05-26 Laget: 2016-05-26 Sist oppdatert: 2019-01-15bibliografisk kontrollert
5. PerfGreen: Performance and Energy Aware Resource Provisioning for Heterogeneous Clouds
Åpne denne publikasjonen i ny fane eller vindu >>PerfGreen: Performance and Energy Aware Resource Provisioning for Heterogeneous Clouds
2018 (engelsk)Inngår i: 2018 IEEE International Conference on Autonomic Computing (ICAC), 2018, s. 81-90Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Improving energy efficiency in a cloud environment is challenging because of poor energy proportionality, low resource utilization, interference as well as workload, application, and hardware dynamism. In this paper we present PerfGreen, a dynamic auto-tuning resource management system for improving energy efficiency with minimal performance impact in heterogeneous clouds. PerfGreen achieves this through a combination of admission control, scheduling, and online resource allocation methods with performance isolation and application priority techniques. Scheduling in PerfGreen is energy aware and power management capabilities such as CPU frequency adaptation and hard CPU power limiting are exploited. CPU scaling is combined with performance isolation techniques, including CPU pinning and quota enforcement, for prioritized virtual machines to improve energy efficiency. An evaluation based on our prototype implementation shows that PerfGreen with its energy-aware scheduler and resource allocator on average reduces energy usage by 53%, improves performance per watt by 64%, and server density by 25% while keeping performance deviations to a minimum.

Serie
Proceedings of the International Conference on Autonomic Computing, ISSN 2474-0756
HSV kategori
Identifikatorer
urn:nbn:se:umu:diva-145925 (URN)10.1109/ICAC.2018.00018 (DOI)000450120900009 ()
Konferanse
15TH IEEE INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING (ICAC 2018), Trento, ITALY, SEP 03-07, 2018
Tilgjengelig fra: 2018-03-22 Laget: 2018-03-22 Sist oppdatert: 2019-01-07bibliografisk kontrollert
6. Virtualization Techniques Compared: Performance, Resource, and Power Usage Overheads in Clouds
Åpne denne publikasjonen i ny fane eller vindu >>Virtualization Techniques Compared: Performance, Resource, and Power Usage Overheads in Clouds
2018 (engelsk)Manuskript (preprint) (Annet vitenskapelig)
Abstract [en]

Virtualization solutions based on hypervisors or containers are enabling technologies

for scalable, flexible, and cost-effective resource sharing. As the fundamental

limitations of each technology are yet to be understood, they need to be regularly

reevaluated to better understand the trade-off provided by latest technological advances.

This paper presents an in-depth quantitative analysis of virtualization

overheads in these two groups of systems and their gaps relative to native environments

based on a diverse set of workloads that stress CPU, memory, storage,

and networking resources. KVM and XEN are used to represent hypervisor-based

virtualization, and LXC and Docker for container-based platforms. The systems

were evaluated with respect to several cloud resource management dimensions including

performance, isolation, resource usage, energy efficiency, start-up time,

and density. Our study is useful both to practitioners to understand the current

state of the technology in order to make the right decision in the selection, operation

and/or design of platforms and to scholars to illustrate how these technologies

evolved over time.

HSV kategori
Identifikatorer
urn:nbn:se:umu:diva-145924 (URN)
Konferanse
ACM/SPEC Internation Conference on Performance Engineering (ICPE)
Tilgjengelig fra: 2018-03-22 Laget: 2018-03-22 Sist oppdatert: 2018-06-09

Open Access i DiVA

fulltext(795 kB)396 nedlastinger
Filinformasjon
Fil FULLTEXT02.pdfFilstørrelse 795 kBChecksum SHA-512
f68bdbd6b927c45efb9b1c59571b4d708f5406bc0af63134bd2ba5a29794d2751ea4b4d2837d1c23c363342ad7ef799057f3bab053d657e733f38b14cbfeb0bb
Type fulltextMimetype application/pdf
spikblad(127 kB)43 nedlastinger
Filinformasjon
Fil SPIKBLAD01.pdfFilstørrelse 127 kBChecksum SHA-512
b10bf0bd5966c036211bd6d3118ec3efb6379477d66f853597af459237f13ef21a0d9f024b7b9f8d387b44a542c77b4dd52b5fb73236d4b9f70f17017054fb61
Type spikbladMimetype application/pdf

Personposter BETA

Tesfatsion, Selome Kostentinos

Søk i DiVA

Av forfatter/redaktør
Tesfatsion, Selome Kostentinos
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 396 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

isbn
urn-nbn

Altmetric

isbn
urn-nbn
Totalt: 1633 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf