Power efficient server consolidation for Cloud data center
| Autor: | Somnath Mazumdar, Marco Pranzo |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Computer Networks and Communications
Computer science Distributed computing Cloud computing 02 engineering and technology computer.software_genre Cloud Integer linear programming Optimisation Server consolidation Virtual Machine allocation Software Hardware and Architecture 0202 electrical engineering electronic engineering information engineering Resource management Integer programming 020203 distributed computing business.industry 020206 networking & telecommunications Server farm Virtual machine Snapshot (computer storage) Resource allocation business Heuristics computer |
| Zdroj: | Future Generation Computer Systems. 70:4-16 |
| ISSN: | 0167-739X |
| DOI: | 10.1016/j.future.2016.12.022 |
| Popis: | Cloud computing has become an essential part of the global digital economy due to its extensibility, flexibility and reduced costs of operations. Nowadays, data centers (DCs) contain thousands of different machines running a huge number of diverse applications over an extended period. Resource management in Cloud is an open issue since an efficient resource allocation can reduce the infrastructure running cost. In this paper, we propose a snapshot-based solution for server consolidation problem from Cloud infrastructure provider (CIP) perspective. Our proposed mathematical formulation aims at reducing power cost by employing efficient server consolidation, and also considering the issues such as (i) mapping incoming and failing virtual machines (VMs), (ii) reducing a total number of VM migrations and (iii) consolidating running server workloads. We also compare the performance of our proposed model to the well-known Best Fit heuristics and its extension to include server consolidation via VM migration denoted as Best Fit with Consolidation (BFC). Our proposed mathematical formulation allows us to measure the solution quality in absolute terms, and it can also be applicable in practice. In our simulations, we show that relevant improvements (from 6% to 15%) over the widely adopted Best Fit algorithm achieved in a reasonable computing time. Propose a MILP mathematical formulation for the Server Consolidation Problem.Show that it can find optimal/near optimal allocation of VMs in short computing times.Truncated runs of the model improve over Best-Fit up to 15%.Use a LB provided by the MILP to compute the absolute theoretical improvement. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect