Unbound growth in the cloud computing service models have motivated the companies building traditional software to be migrated into the clouds. During the high demand of the traditional applications, the performance and quality of the software were evaluated by the popular and globally accepted metrics. Nevertheless, after the migration of the same applications into the cloud, the expectation and definition of performance and quality has been changed. The beneficiaries of these applications are setting new milestones for the applications. Hence, the recent demand of the research trend is to build new software metric models to match the trade of between the new expectations from the beneficiaries and the software quality policies for organization or individual or state. Thus this work makes an attempt to understand the traditional software quality metrics and try to justify the applicability of these parameters in the trend of cloud based software applications. This work also proposes a novel metric method for performance evaluation for the migrated applications into the cloud, with the intension of formalizing and standardizing the cloud based metric methods unlike the recent trends.
In this paper, high efficient Virtual Machine (VM) migration using GSO algorithm for cloud computing is proposed. This algorithm contains 3 phases: (i) VM selection, (ii) optimum number of VMs selection, (iii) VM placement. In VM selection phase, VMs to be migrated are selected based on their resource utilization and fault probability. In phase-2, optimum number of VMs to be migrated are determined based on the total power consumption. In VM placement phase, Glowworm Swarm Optimization (GSO) is used for finding the target VMs to place the migrated VMs. The fitness function is derived in terms of distance between the main server and the other server, VM capacity and memory size. Then the VMs with best fitness functions are selected as target VMs for placing the migrated VMs. The proposed algorithms are implemented in Cloudsim and performance results show that PEVM-GSO algorithm attains reduced power consumption and response delay with improved CPU utilization.
Cloud computing offers end users a scalable and cost-effective way to access multi-platform data. While the Cloud Storage features endorse it, resource loss is also likely. A fault-tolerant mechanism is therefore required to achieve uninterrupted cloud service performances. The two widely used defect-tolerant mechanisms are task relocation and replication. But the replication approach leads to enormous overhead storage and computing as the number of tasks gradually increases. When a large number of defects occur, it creates more overhead storage and time complexity depending on task criticalities. An Integrated Fault Reduction Scheduling (IFRS) cloud computing model is used to resolve these problems. The probability of failure of a VM is calculated by finding the previous failures and active executions in this model. Then a fault-related adaptive recovery timer is retained, modified depending on the fault type. Experimental findings showed that IFRS reached 67% lower storage costs and 24% less response time when comparing with the current technique for sensitive tasks.
Cloud computing provides flexible and cost effective way for end users to access data from multiplatform environment. Despite of support by the features of cloud computing, there are also chances of resource failure. Hence there is a need of a fault tolerant mechanism to achieve undisrupted performance of cloud services. The task reallocation and duplication are the two commonly used fault tolerant mechanisms. But task replication method results in huge storage and computational overhead, when the number of tasks is increasing gradually. If the number of faults is high, it incurs more storage overhead and time complexity based on task criticality. In order to solve these issues, we propose to develop a Cost Effective Hybrid Fault Tolerant Scheduling (CEHFTS) Model for cloud computing. In this model, the Failure Occurrence Probability (FoP) of each VM is estimated by finding the previous failures and successful executions. Then an adaptive fault recovery timer is maintained during a fault, which is adjusted based on the type of faults. Experimental results have shown that CEHFTS model achieves 43% reduced storage cost and 13% reduced response delay for critical tasks, when compared to existing technique.
Cloud computing can be online based network engineering which contributed with a rapid advancement at the progress of communication technological innovation by supplying assistance to clients of assorted conditions with aid from online computing sources. It's terms of hardware and software apps together side software growth testing and platforms applications because tools. Large-scale heterogeneous distributed computing surroundings give the assurance of usage of a huge quantity of computing tools in a comparatively low price. As a way to lessen the software development and setup onto such complicated surroundings, high speed parallel programming languages exist which have to be encouraged by complex operating techniques. There are numerous advantages for consumers in terms of cost and flexibility that come with Cloud computing anticipated uptake. Building on well-established research in Internet solutions, networks and utility computing, virtualization et cetera Service-Oriented Architectures and the Internet of Services (IoS) have implications for a wide range of technological issues such as parallel computing and load balancing as well as high availability and scalability. Effective load balancing methods are essential to solving these issues. Adaptive task load model is the name of the method we suggest in our article for balancing the workload (ATLM). We developed an adaptive parallel distributed computing paradigm as a result of this (ADPM). While still maintaining the model's integrity, ADPM employs a more flexible synchronization approach to cut down on the amount of time synchronous operations use. As well as the ATLM load balancing technique, which solves the straggler issue caused by the performance disparity between nodes, ADPM also applies it to ensure model correctness. The results indicate that combining ADPM and ATLM improves training efficiency without compromising model correctness.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.