task scheduling

Today, many scientific problems require high computational power and storage space. Cloud computing is a model for easy access to different resources such as storage space with minimal need for service provider interaction. The cloud environment has been used for many benefits, but security and privacy issues are important challenges due to outsourcing. On the other hand, task scheduling is a fundamental issue in distributed systems such as cloud computing. Because there are several tasks to be performed that require different resources while resources are limited. Therefore, cloud tasks must be intelligently scheduled so that system performance and provider profitability are maximized. To solve this challenge, various techniques such as gradient-based algorithms for continuous and single-model problems are common. In cloud computing, due to the large search space and complex nature, these algorithms may not provide a suitable solution. Efficient meta-heuristic techniques can deal with these problems and find near-optimal solutions in a reasonable time. In this paper, a security-based scheduling algorithm using an improved Particle Swarm Optimization algorithm is presented. The improved algorithm uses multi adaptive learning to provide diversity in a population. Therefore, a good balance between exploration and exploitation. The proposed task scheduling algorithm simultaneously considers five parameters (i.e., round trip time, load, energy consumption, cost, and security) to provide load balancing and reduce energy consumption. The proposed algorithm is implemented using the CloudSim simulator and compared with the relevant strategies (i.e., CJS, OTSS, GTSA, and JSSS). The simulation results show that the proposed algorithm, considering the characteristics of tasks and resources, has significant efficiency and effectiveness in the cloud environment, especially at high workloads.

In recent years, cloud computing is becoming eminent in the field of information technology. In a cloud computing environment, there is a potential for faults. There are different methods for dealing with faults, but with regard to the features and characteristics of the cloud computing environment, the use of fault tolerance methods is the best choice for this environment.One of the biggest issues in fault tolerance methods is the efficient use of resources. The optimal use of resources is important for cloud providers and customers. Unfortunately, the optimal use of resources in fault tolerance methods has not been much considered by researchers and cloud service providers. In this paper taking into account the dependence between tasks, an attempt has been made to provide a fault tolerance method on virtual machines, which in addition to being tolerant of fault, achieves optimum use of resources. In this method, by using a priority scheduler, each task is assigned a priority, then tasks are sent by the order of priority to their virtual  machines for processing. The results of simulation by the cloudsim simulator show that the proposed method has been able to improve the use of resources more than other methods and with 95% confidence intervals it has achieved (29.15% and 22.74%) improvement in the number of processors, (30.76% and 22.34%) improvement in memory usage and (29.71% and 22.88%) improvement in the use of bandwidth.

While private clouds provide high security and low cost for scheduling workflow, public clouds are potentially exposed to the risk of data and computation breach as well as their higher costs. In real world, however, we may need high performance resources and high capacity storage devices encouraging organizations to use public clouds. Task scheduling, therefore, is one of the most important challenges in cloud computing. In this paper a new scheduling method is proposed for workflow applications in hybrid cloud, while considering the security issue as well. Specifically, in adition to sensitivity of tasks, that considered in recent works, security requirement for data and security strength for both resources and channels are taken into account. Proposed scheduling method is implemented by improved particle swarm optimization algorithm and is named PSO-WSCS. The goal function is to minimize the security distance of data and workflow from security strengths of resources and channels so that time and budget constraints are met. The proposed PSO-WSCS algorithm is compared with three state of the art scheduling algorithms, namely VNPSO, MPSO and MPSO-SA, in hybrid cloud. Evaluations show the effectiveness of our algorithm by finding resources having security aspects resemblance to the security requirements. In average, improvement of 40% is resulted for the given samples.