A distributed dynamic and customized load balancing algorithm for virtual instances

Shah, Vedang; Trivedi, Harshal

doi:10.1109/nuicone.2015.7449630

Cited by 6 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new framework is proposed by Gulshan Soni et al that provides power aware, scalable, energy efficient Cloud computing architecture using variable resource management, power-aware scheduling techniques, and live migration with minimized VM design [14]. Vedang Shah et al [15] proposed a hybrid Particle Swarm Optimization (HPSO) whose results show improvement in execution ratio and decrease in average schedule length. M. Sridhar et al [16] proposed a Distributed Dynamic and Customized Load Balancing (DDCLB) algorithm to handle the arriving user's requests dynamically (as in Amazon EC2 instances).…”

Section: Related Workmentioning

confidence: 99%

Untitled

2020

IJCSENET

View full text Add to dashboard Cite

Cloud Computing is a technique involving multiple resources being requested by versatile cloud users for allocation of shared resources. The tasks of application requests are allotted to virtual machines (VMs). In different situation different machines get different load. So, load balancing becomes necessary among different VMs. A decentralized load balancer is used to identify best number of tasks to be allocated to each VM. During load allocation to VM, for execution of tasks, the most optimal VM is identified for the load which is best capable of handling the task. The cloud user's application task is them mapped onto that VM to reduce the energy consumption and total execution time. In this paper, decentralized load balancing technique is used to distribute the load on each virtual machine which is enhanced using particle swarm optimization (PSO) which is a swarm based heuristic optimization technique. Moreover, the results are analyzed and compared with centralized load balancer for energy efficiency and throughput parameters.

show abstract

Section: Related Workmentioning

confidence: 99%

Untitled

2020

IJCSENET

View full text Add to dashboard Cite

show abstract

“…Cloud computing has emerged as a solution for scaling instances by using clusters as web services [1,3,4]. In [18], a customised load balancing and a distributed dynamic algorithm were proposed for auto-scaling of virtual clusters with a load balancer which can handle the requests sent from users for the EC2 instances in a dynamic manner. The EC2 virtual instances can be either increased or decreased as per-the-CPU use and with respect to incoming user requests on the virtual nodes, whereas the load balancer can distribute the incoming data traffic automatically on the EC2 instances, containers and network IP addresses.…”

Section: Related Workmentioning

confidence: 99%

An Auto-Scaling Framework for Analyzing Big Data in the Cloud Environment

et al. 2019

View full text Add to dashboard Cite

Processing big data on traditional computing infrastructure is a challenge as the volume of data is large and thus high computational complexity. Recently, Apache Hadoop has emerged as a distributed computing infrastructure to deal with big data. Adopting Hadoop to dynamically adjust its computing resources based on real-time workload is itself a demanding task, thus conventionally a pre-configuration with adequate resources to compute the peak data load is set up. However, this may cause a considerable wastage of computing resources when the usage levels are much lower than the preset load. In consideration of this, this paper investigates an auto-scaling framework on cloud environment aiming to minimise the cost of resource use by automatically adjusting the virtual nodes depending on the real-time data load. A cost-effective auto-scaling (CEAS) framework is first proposed for an Amazon Web Services (AWS) Cloud environment. The proposed CEAS framework allows us to scale the computing resources of Hadoop cluster so as to either reduce the computing resource use when the workload is low or scale-up the computing resources to speed up the data processing and analysis within an adequate time. To validate the effectiveness of the proposed framework, a case study with real-time sentiment analysis on the universities’ tweets is provided to analyse the reviews/tweets of the people posted on social media. Such a dynamic scaling method offers a reference to improving the Twitter data analysis in a more cost-effective and flexible way.

show abstract