Name
Abstract | ||
|---|---|---|
Increasing power consumption of IT infrastructures and growing electricity prices have led to the development of several energy-saving techniques in the last couple of years. Virtualization and consolidation of services is one of the key technologies in data centers to reduce overprovisioning and therefore increase energy savings. This paper shows that the energy-optimal allocation of virtualized services in a heterogeneous server infrastructure is NP-hard and can be modeled as a variant of the multidimensional vector packing problem. Furthermore, it proposes a model to predict the performance degradation of a service when it is consolidated with other services. The model allows considering the tradeoff between power consumption and service performance during service allocation. Finally, the paper presents two heuristics that approximate the energy-optimal and performance-aware resource allocation problem and shows that the allocations determined by the proposed heuristics are more energy-efficient than the widely applied maximum-density consolidation. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1007/s10586-012-0214-y | Cluster Computing |
Keywords | Field | DocType |
Resource management,Energy efficiency,Modeling,Optimization,Performance,Data center,Cloud computing | Virtualization,Resource management,Computer science,Efficient energy use,Real-time computing,Heuristics,Resource allocation,Consolidation (soil),Data center,Cloud computing,Distributed computing | Journal |
Volume | Issue | ISSN |
16 | 3 | 1386-7857 |
Citations | PageRank | References |
31 | 1.02 | 9 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gergö Lovász | 1 | 38 | 2.68 |
| Florian Niedermeier | 2 | 79 | 6.25 |
| Hermann Meer | 3 | 137 | 11.27 |