An energy-efficient topology-aware virtual machine placement in Cloud Datacenters: A multi-objective discrete JAYA optimization

• Published in: Sustainable computing informatics and systems Vol. 38; p. 100856
• Main Author: Hosseini Shirvani, Mirsaeid
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.04.2023
• Subjects: Cloud computing; Data center networks; JAYA optimization algorithm; Multi-objective optimization algorithm; Topology-aware Scheme; Virtual machine placement; Topology-aware Scheme; Cloud computing; Multi-objective optimization algorithm; JAYA optimization algorithm; Virtual machine placement; Data center networks
• ISSN: 2210-5379
• DOI: 10.1016/j.suscom.2023.100856

By the advent of cloud computing and the numerous related web applications, data center networks (DCNs) are becoming complex to provide all-to-all communications between underlying devices; it is done by spending a huge amount of electricity consumption. Energy consumption management is the first class concern for cloud providers in this energy hungry devices and also for the green computing goals. In the large DCs, the power management of hundreds or even many thousands idle switches can be a promising approach toward overall cost reduction. The virtual machine placement (VMP) scheme which is aware of both VMs affinity and underlying network topology for co-hosting dependent VMs as physically near as possible and lowering down power state of idle devices can enhance sustainability objectives. On the other hand, resource wastage lowers system utilization which leads more physical server usage causing more power consumption as a consequence. To address the issue, this paper presents an energy-efficient topology-aware VM placement scheme in the cloud DCs which is formulated to a multi-objective optimization problem with power consumption and resource wastage minimization perspective. To deal with this combinatorial problem, an advanced multi-objective discrete version of JAYA (MOD-JAYA) algorithm is presented since the search space of VMP is discrete in nature. The proposed algorithm is validated by intensively variable circumstances and simulations upon conducted scenarios. The simulation results prove the superiority of the proposed advanced MOD-JAYA algorithm in solving VMP problem in comparison with other existing schemes in terms of prominent assessment metrics. •It presents server power consumption model by contributing processors as the chief electricity consumer.•It presents DCNs’ power consumption model by contributing switches as variable electricity consumer between network elements.•It presents server dissipation model by considering processor and memory utilization.•It formulates VMP problem into a multi-objective optimization model with power consumption and resource dissipation perspective.•It presents an advanced multi-objective discrete JAYA optimization algorithm to solve the stated problem.