Dynamic Fair Priority Optimization Task Scheduling Algorithm in Cloud Computing: Concepts and Implementations

Abstract

Cloud computing has become buzzword today. It is a digital service where dynamically scalable and virtualized resources are provided as a service over internet. Task scheduling is premier research topic in cloud computing. It is always a challenging task to map variety of complex task on various available heterogenous resources in scalable and efficient way. The very objective of this paper is to dynamically optimize task scheduling at system level as well as user level. This paper relates benefit-fairness algorithm based on weighted-fair Queuing model which is much more efficient than simple priority queuing. In proposed algorithm, we have classified and grouped all tasks as deadline based and minimum cost based constraints and after dynamic optimization, priority of fairness is applied. Here different priority queue (high, mid, low) are implemented in round-robin fashion as per weights assign to them .We recompile the CloudSim and simulate the proposed algorithm and results of this algorithm is compared with sequential task scheduling and simple constraints (cost and deadline) based task scheduling algorithm. The experimental results indicates that proposed algorithm is, not only beneficial to user and service provider, but also provides better efficiency and fairness at priority level, i.e. benefit at system level.

Utility based load balancing using firefly algorithm in cloud

“…The max-min algorithm (Bhoi and Ramanuj 2013) picks the task which has maximum size after a minimum size task is picked. There are many works existing on priority based scheduling (Ghanbari and Othman 2012;Ghanbari et al 2015;Yang 2012;Bansal et al 2012;Deepika Saxena 2016;Jain et al 2015), wherein different methods to prioritize the jobs have been considered to perform fair scheduling. But these legacy algorithms are not a very good option for complex environments where users request/ demand for resources/services is uncertain.…”

A Preference-Based Supervising of Virtual Machines in Cloud Environment

“…When compared to the existing system, the proposed model reduces the communication problem in network. The Fitness calculation [20] produce the accurate result. So, we can easily find the less load virtual machine.…”

Energy Consumption in Mobile Phones

“…The mobile phones can help to motivate the scientists to present the most optimized tools that may be used for minimizing the less energy dissipation in mobile devices during processing, less energy consumption by memory, reduce the power usage during transmission of data on any network or any cloud computing environment [89][90][91].…”