OPTIMIZED PARTICLE SWARM OPTIMIZATION BASED DEADLINE CONSTRAINED TASK SCHEDULING IN HYBRID CLOUD

Abstract
Cloud Computing is a dominant way of sharing of computing resources that can be configured and provisioned easily. Task scheduling in Hybrid cloud is a challenge as it suffers from producing the best QoS (Quality of Service) when there is a high demand. In this paper a new resource allocation algorithm, to find the best External Cloud provider when the intermediate provider’s resources aren’t enough to satisfy the customer’s demand is proposed. The proposed algorithm called Optimized Particle Swarm Optimization (OPSO) combines the two metaheuristic algorithms namely Particle Swarm Optimization and Ant Colony Optimization (ACO). These metaheuristic algorithms are used for the purpose of optimization in the search space of the required solution, to find the best resource from the pool of resources and to obtain maximum profit even when the number of tasks submitted for execution is very high. This optimization is performed to allocate job requests to internal and external cloud providers to obtain maximum profit. It helps to improve the system performance by improving the CPU utilization, and handle multiple requests at the same time. The simulation result shows that an OPSO yields 0.1% - 5% profit to the intermediate cloud provider compared with standard PSO and ACO algorithms and it also increases the CPU utilization by 0.1%.

Authors
Dhananjay Kumar, B. Kavitha, M. Padmavathy, B. Harshini, E. Preethi, P. Varalakshmi
Anna University, MIT Campus, Chennai, India

Keywords
Hybrid Cloud, Particle Swarm Optimization, Ant Colony Optimization, Task Scheduling
Published By :
ICTACT
Published In :
ICTACT Journal on Soft Computing
( Volume: 6 , Issue: 2 )
Date of Publication :
January 2016

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.