Hybrid meta‐heuristic algorithm for optimal virtual machine placement and migration in cloud computing

Abstract

Data sharing in cloud computing happens with multiple participants to freely distribute the group data, which focuses on advancing the effectiveness of work in cooperative backgrounds and has attained widespread benefits. The main intent of this article is to accomplish a virtual machines (VMs) placement and migration model using a hybrid meta-heuristic concept. A new meta-heuristic algorithm named DJ-HA is developed for optimal VM placement and migration to reduce the count of active servers, and minimization of makespan, and energy consumption with a faster convergence rate in a cloud background. Then, the VM migration is done based on the multi-objective function concerning energy consumption and makespan using the same hybrid DJ-HA.From the result analysis, the energy consumption of the DJ-HA is correspondingly secured at 4.3%, 3.5%, 31%, and 33% more advanced than PSO, GWO, DHOA, and JA, at the 100th iteration for Experiment 1. Accordingly, the cost function of the suggested DJ-HA is secured at 88.8%, 89.4%, 33.3%, and 50% increased than PSO, GWO, DHOA, and JA at the 100th iteration for Experiment 4. Hence, it is proved that the suggested VM migration using DJ-HA is enriched than the other conventional algorithms.

Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS

“…The comparison between Balanced-DRL and some typical works in related research in terms of field, problem type, approach, and achievements is shown in Table 6. The papers [10,16,19,22] focus on optimizing job allocation in cloud computing platforms. Each paper proposes optimization algorithms with varying key performance indicators, such as latency and energy consumption, while employing different types of algorithms.…”

“…By maximizing resource utilization using three stages-parallelization, task allocation, and task redistribution-the algorithm aims to provide better services. Infantia et al [16] proposed a novel meta-heuristic algorithm for virtual machine (VM) placement and migration in cloud environments, aiming to achieve optimal VM placement and migration, reduce the number of active servers, and minimize completion time and energy consumption. Ghobaei-Arani et al [17] proposed an efficient IoT service deployment solution based on the whale optimization algorithm to address the deployment problem of IoT applications in fog computing.…”

TMaLB: A Tolerable Many-Objective Load Balancing Technique for IoT Workflows Allocation

“…Many researchers have explored the many-objective loadbalancing optimization problem using swarm intelligence algorithms based on the population in the IoT, which has generated a set of optimized solutions. Researchers have gradually improved/combined evolutionary algorithms to achieve load-balancing techniques to have optimal QoS and performance with several objectives [28], [35]. Also, A divide-and-conquer optimization method has been performed for complex problems to facilitate finding the best solutions [44].…”

An Efficient and Robust Method for Data Privacy and Security on a Public Cloud Using a Novel Hybrid Technique

“…To protect data from being accessed without authorization and to verify that the data have not been tampered with, a plan has been developed that, in addition to resolving the issues of privacy and consistency, also addresses the issue of unauthorized access. The author of article [10] suggested a hybrid technique called PHECC (Polynomial-based Hashing and Elliptic Curve Cryptography). This approach combines PH with ECC security procedures in order to guarantee the customers that users' data will be secure while they are stored on the cloud.…”