Artificial bee colony optimized VM migration and allocation using neural network architecture
Journal: International Journal of Advanced Technology and Engineering Exploration (IJATEE) (Vol.10, No. 102)Publication Date: 2023-05-30
Authors : Sudhir Kumar Sharma; Wiqas Ghai;
Page : 590-607
Keywords : VM migration; VM allocation; Artificial bee colony (ABC); Artificial neural network (ANN).;
Abstract
The concept of cloud computing has emerged to address the challenges posed by advancements in internet technology, which attract internet users to access various online resources using multiple applications managed by third parties. Despite its numerous advantages, the cloud computing environment faces challenges such as service level agreement (SLA) violations and increased energy consumption. In this context, a proposed scheme for optimized virtual machine (VM) allocation and migration aims to be energy efficient and minimize violations while meeting the demand for storage space. The allocation of tasks involves using an artificial bee colony (ABC) optimization approach to reduce the overall computation cost. This information is then fed to the support vector machine (SVM), which sends the optimized feature vector to an artificial neural network (ANN) to complete the migration task. Comparative analysis against existing work demonstrates an overall improvement of 3% to 9% in VM migrations, 1% to 6% in energy consumption, and 1% to 5.5% in SLA violations. Furthermore, the effectiveness of the proposed power-aware ABC-based VM allocation and migration is evaluated based on the success rate, which claims better resource allocation for delivering high-end quality of service (~10%) in terms of the number of delivered packets and (~4%) improvement in response time for completing jobs in minimum time. Additionally, the work demonstrates minimal overall migration cost (~3%) involved in delivering better service using the proposed approach.
Other Latest Articles
- Detection of whitefly pests in crops employing image enhancement and machine learning
- Implicit aspect based sentiment analysis for restaurant review using LDA topic modeling and ensemble approach
- Additive LOG transformation distributed feature embedding convolutional neural learning classifier for early COVID-19 prediction
- Classification of capsicum leaf disease from a complex cluster of leaves using an improved multiple layers ShuffleNet CNN model
- An effective crop recommendation method using machine learning techniques
Last modified: 2023-06-19 16:42:17