Evidence record · UDINUS · SDGs
- Unit
- Rektorat UDINUS
- Period
- 2014
- Goals
- Record
- 3d8787b7-2bd8-4555-aaa9-77696888a929
- Published
- 2026-10-30
Universitas Dian Nuswantoro conducted research on efficient electrical energy consumption in cloud computing through improvement of the virtual machine selection policy in dynamic virtual machine consolidation. The activity was conducted by Shidik, Guruh Fajar and Ashari, Ahmad as participants in the research. The study addressed cloud computing as a computation resource requiring massive electrical energy and focused on the importance of energy efficiency in cloud computing.
The research examined the virtual machine selection phase within the overall dynamic virtual machine consolidation strategy. The strategy consisted of four phases: host overloading detection, virtual machine selection, host underloading detection, and virtual machine placement. The proposed method focused on reducing the time required to select or decide which virtual machine should be migrated from an overloaded host. Selection was performed constantly according to the virtual machine position, namely the first, center, or last position, after an overloaded host had been detected using the Local Regression algorithm.
The performance of the proposed method was evaluated using Energy Consumption, SLAV, SLATAH, and PDAM parameters. The evaluation used real-world workload data from PlanetLab virtual machines. The results showed promising improvement in energy efficiency and acceptable service-level agreement performance compared with other virtual machine selection policy techniques. Through this activity, Universitas Dian Nuswantoro contributed research focused on energy efficiency in cloud computing by investigating a virtual machine selection policy within dynamic consolidation.