Original scientific paper
https://doi.org/10.1080/00051144.2023.2223479
Optimization of virtual machines performance using fuzzy hashing and genetic algorithm-based memory deduplication of static pages
N. Jagadeeswari
; Department of CSE, Thanthai Periyar Government Institute of Technology, Vellore, India
*
V. Mohanraj
; Department of IT, Sona College of Technology, Salem, India
Y. Suresh
; Department of IT, Sona College of Technology, Salem, India
J. Senthilkumar
; Department of IT, Sona College of Technology, Salem, India
* Corresponding author.
Abstract
The demand for memory capacity has increased, and cloud energy usage has soared. The performance and scalability of virtualization interfaces in cloud computing are hampered by a lack of sufficient memory. To figure out this problem, a technique defined as memory deduplication is widely used to reduce memory consumption utilizing the page-sharing method. However, this method of memory deduplication using KSM has significant drawbacks, such as overhead owing to many online comparisons, which will consume so many CPU resources. In this research, a modified approach of Memory Deduplication of Static Memory Pages (mSMD), which is based on the identification of similar applications by Fuzzy hashing and clustering them using the Hierarchical Agglomerative Clustering approach, followed by similarity detection between static memory pages based on Genetic Algorithm and details stored in Multilevel shared page table, both operations performed in offline and final memory deduplication is carried out during online, is proposed for achieving performance optimization in virtual machines by reducing memory capacity requirements. When compared to existing techniques, the simulation results indicate that the proposed approach mSMD efficaciously minimizes the memory capacity required while improving performance.
Keywords
Memory deduplication; cloud computing; classification; genetic algorithm; fuzzy hashing; hierarchical agglomerative clustering
Hrčak ID:
315944
URI
Publication date:
27.6.2023.
Visits: 299 *