© 2017, IJCSE All Rights Reserved 7 International Journal of Computer Sciences and Engineering Open Access Review Paper Volume-5, Issue-6 E-ISSN: 2347-2693 Workflow Scheduling Mechanism Using PCSO n Cloud: Case Study Prachi Chaturvedi 1* , Sanjiv Sharma 2 1* Dept. of CSE/IT, Madhav Institute of Technology and Science, Gwalior, India 2 Dept. of CSE/IT, Madhav Institute of Technology and Science, Gwalior, India *Corresponding Author: pchaturvedi1118@gmail.com, Mob.: +91-9406983296 Available online at: www.ijcseonline.org Received: 12/May/2017, Revised: 20/May/2017, Accepted: 17/Jun/2017, Published: 30/Jun/2017 Abstract— Cloud Computing has emerged as a service model that enables on-demand network get right of entry to a massive number of available virtualized resources and applications with a minimal management attempt and a minor rate. The unfold of Cloud Computing technology allowed handling complicated applications together with Scientific Workflows, which consists of a set of extensive computational and data manipulation operations. Cloud Computing enables such Workflows to dynamically provision compute and storage assets necessary for the execution of its responsibilities way to the pliancy asset of those assets. However, the dynamic nature of the Cloud incurs new challenges, as a few allocated assets may be overloaded or out of get entry to all through the execution of the Workflow. Moreover, for data extensive responsibilities, the allocation strategy have to keep in mind the facts placement constraints on the grounds that facts transmission time can growth extensively in this example which implicates the growth of the general of completion time and value of the Workflow. Likewise, for in depth computational responsibilities, the allocation strategy must consider the form of the allocated digital machines, greater specifically its CPU, reminiscence and network capacities. Yet, an essential venture is the way to correctly schedule the Workflow obligations on Cloud resources to optimize its ordinary best of provider. In this paper, we endorse a QoS aware algorithm for Scientific Workflows scheduling that objectives to enhance the overall quality of service (QoS) with the aid of considering the metrics of execution time, data transmission time, price, sources availability and facts placement constraints. We prolonged the Parallel Cat Swarm Optimization (PCSO) algorithm to put in force our proposed method. We tested our algorithm inside pattern Workflows of various scales and we compared the consequences to the ones given by the same old PSO, the CSO and the PCSO algorithms. The consequences display that our proposed algorithm improves the general satisfactory of provider of the tested Workflows. Keywords— Cloud Computing; Workflow; IaaS; virtual machine; storage; quality of service; scheduling algorithm; Parallel Cat Swarm Optimization... I. INTRODUCTION Cloud Computing is a carrier version that permits on-demand Community access to a huge range of available virtualized resources and packages with minimal management attempt and a minor charge. This version can be prepared into 3 layers of services, particularly, Software as a Service (or SaaS) which englobes software packages, Platform As A Service (or PaaS) enclosing platform packages and growing equipment, and Infrastructure As A Service (or IaaS) together with hardware assets including CPU ability, garage and network. The Cloud computing surroundings gives a couple of advantages for hosting and executing complex applications which include Scientific Workflows. Scientific Workflows are designed particularly to compose and execute a sequence of in depth computational and data manipulation steps [1]. They are often being used to model complex phenomena, to analyse instrumental information, to tie collectively information from disbursed sources, and to pursue other clinical endeavours [2]. They may be finished the usage of IaaS services on the Cloud as virtual machines. Cloud Computing facilitates Workflow programs to dynamically provision compute and garage resources essential for the execution of its responsibilities thanks to the elasticity asset of those sources. It permits, also, Workflows to limit the execution value and meet defined deadlines by allocating resources on-demand the use of the ”pay in line with-use” pricing model. However, the dynamic nature of the Cloud Computing surroundings can incur new challenges as a few allocated assets can be overloaded or out of get right of entry to during the execution of the Workflow which might also motive the failure of the general method of execution. For this reason, the allocation method needs to take into account the supply of sources and insure exceptions handling. Moreover, for facts intensive duties (along with a huge quantity of records to manipulate), the allocation strategy must recollect the statistics placement constraints imposed