Reliability-Aware Cost-Efficient Scientific Workflows Scheduling Strategy on Multi-Cloud Systems

Abstract : Nowadays, more and more computation-intensive scientific applications with diverse needs are migrating to cloud computing systems. However, the cloud systems alone cannot meet applications' requirements at all times with the increasing demands from users. Therefore, the multi-cloud systems that can provide scalable storage and computing resources become a good solution. The main challenges for such systems are multiple billing mechanisms, virtual resources heterogeneity, and systems reliability. In response to these challenges, we first build a multi-cloud systems fault-tolerant workflow scheduling framework, which tries to improve the scientific applications execution reliability and reduce their execution cost. Then, we use Weibull distribution to analyze task execution reliability and hazard rate, which is used to duplicate task with high execution hazard rate. Thirdly, we integrate different multi-cloud providers' billing mechanism into the proposed scheduling framework, and we also formulate this workflow scheduling problem as a linear programming problem. Fourthly, we define the DAG tasks cost-efficient bottom level, and propose a fault-tolerant cost-efficient workflow scheduling algorithm (FCWS) that minimizes application execution cost, time while ensuring their reliability. Finally, The results clearly demonstrate that our proposed FCWS algorithm outperforms existing FR-MOS, CWS in terms of cost and reliability, and FCWS is also better than CWS.

 EXISTING SYSTEM :

 ? We address existing research related to optimising data transfer and enhancing reliability constraints in distributed computing systems such as grid and cloud infrastructures. ? The approach proposed in this work goes beyond existing approaches by considering both performance optimization and trust QoS constraints for resource scheduling. ? It checks whether the user’s tasks in the queue are schedulable or not according to the existing VM types, then we can obtain the candidate VMs for corresponding tasks. ? Thus, the existing multi-objective scheduling algorithms cannot directly be applied in a multicloud environment.

 DISADVANTAGE :

 ? In the recent past due to the wide application of cloud computing, there exist a variety of approaches to the scheduling problem. ? We are required to undoubtedly recognize the drawbacks related to various scheduling procedures to overcome these problems and advance toward effective scheduling algorithms. ? Over-provisioning type of problem can happen because at a single VM there is a chance of executing more tasks, as a result, performance begins to decline. ? Excessive wastage of resources and time problems in over-provisioning and underprovisioning increases the cost of services. ? To define the task scheduling problem it is required to observe both resources of VM utilization and makespan.

 PROPOSED SYSTEM :

 • The proposed algorithm optimised a parameter while meeting constraints of the two others. • They proposed three novel workflow scheduling heuristics which were based on ant colony system. • Our approach is proposed in the context of an IaaS cloud with multiple data centres, where workflow applications have to be scheduled on different data centres for execution. • We plan to expand our proposed approach to investigate additional constraints such as cost and energy consumption in multiple cloud data centres. • We would like to consider variable costs to access resources that change across multiple data centres.

 ADVANTAGE :

 • In a cloud environment, if the jobs are not organized properly, performance decreases and does not provide the outcomes which are supposed to provide as the cloud processes a vast quantity of data. • Internal and external essentials of the resources are set aside and the requirements such as data storage, security, resource expenditures, bandwidth and efficiency regarding time and performance may vary for each job in cloud computing. • The overarching goal in cloud computing is to attain excellent performance at the lowermost possible costs by keeping network settings and storage optimal. • The alignment of cost-effective plan ensures the expected benefit in cloud and provide a good balance between cost and performance.