Study of Energy-Efficient Virtual Machine Migration with Assurance of Service-Level Agreements

Panwar, Suraj Singh; Rauthan, M. M. S.; Barthwal, Varun; Gaur, Sachin; Mehra, Nidhi

doi:10.1007/978-981-97-0641-9_52

Cited by 1 publication

(1 citation statement)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research [13] concentrated on addressing energy consumption issues in cloud environments by proposing an integrated paradigm for IoT and cloud to optimise resource utilisation, achieve load balancing, and investigate energy consumption [14]. Virtualization is an essential prerequisite of cloud computing, where VMs are mapped to PMs.…”

Section: Introductionmentioning

confidence: 99%

A Modified Genetic-Based solution for Power-Aware Placement of Virtual Machines

Panwar,

Rauthan,

Barthwal

2024

Preprint

View full text Add to dashboard Cite

Cloud computing has developed as a ubiquitous technology for delivering services like storage, computing, etc. via the Internet. With the rising demand by customers for cloud computation and associated services, cloud service providers are developing various approaches that enhance the performance, reliability, and availability of cloud systems. Cloud computing uses virtualization to optimise resource usage and minimise power utilisation in data centers (DC). Efficient virtual machine (VM) placement strategies are crucial, especially when using advanced genetic techniques. This research paper introduces the use of a genetic meta-heuristic approach, named PowerGA, to optimise the integration of virtual machines (VM) onto the least number of physical machines (PMs) in cloud DCs. PowerGA optimises VM deployment in cloud DCs to minimise energy utilisation and Service Level Agreement (SLA) breaches, considering factors such as VM migration, host shutdown, overload count, and active physical machines. Extensive simulations using real workload data showed significant improvements over traditional strategies like PABFD, with PowerGA achieving a 25% reduction in energy consumption (EC), 43% fewer VM migrations, a 58% improvement in SLA violations, and a 72% reduction in host shutdowns over ten days of data from PlanetLab. These results highlight PowerGA's effectiveness in energy management and SLA enhancement, demonstrating the benefits of a meta-heuristic genetic algorithm in optimising VM placement for cloud computing efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%