Article Preview
TopIntroduction
Cloud computing is the growing computational technique that depends upon virtualization equipment in response to the user’s request via the Internet and dynamic distribution of resources. The services provided by cloud computing are becoming increasingly more diverse and the ability to perform varied and complex tasks involving extremely large amounts of task data, has become necessary. Researches, aimed at meeting the needs of cloud-computing systems considering wider cloud service resource types and collaborative resource scheduling has become the main topic in current studies, which contain cloud computing architecture, management mechanisms, reliability, security, and scalability of resources in cloud-computing environments, and which are capable of hosting more resource models, modeling methods for cloud service resources, resource allocation with collaborative strategy for cloud service, and formulating an optimal, dynamic scheduling method of cloud resources allocation.
Improving the utilization of computing resources, enabling a shorter time to complete tasks, decreasing response time, and improving service quality are the main objectives of resource scheduling in cloud computing, which is primarily achieved by allocating tasks to different computing resources in a reasonable manner (Yuan, et al., 2021).
With the growth and applications of the cloud-computing environments, the scheduling problems have achieved gradually more research focuses in recent years. Resource scheduling is the main issue in cloud computing and considers several features, such as total execution cost, fault tolerance, resource utilization, execution time, and energy consumption. The significant measure in task scheduling is load balancing (Jia et al., 2019). It is critical to increase the speed of completing computing tasks and to store less data to take up as little space as possible for customers of pay-as-you-go cloud computing. At the same time, to solve more customers’ computing and storage tasks, the cloud service providers improve the efficiency of computing resources by allocating computing resources scientifically and rationally to address specific computing tasks (Gabi et al., 2022). It is critical to reduce the task completion time of users and reasonably consume the resources of operators in order to avoid the waste of computing resources by adapting an effective resource scheduling strategy (Houssein et al., 2021). In selecting the scheduling algorithm, researchers need to concentrate on decreasing the task execution time and makespan value (Sanaj & Prathap, 2020). It is a very critical issue to find an efficient and appropriate cloud-computing resource scheduling strategy and its related algorithm in a cloud-computing environment. The virtual machine plan utilization requests the physical machine (PM) for a certain data point. In consideration of the alterations in the workload over time in the cloud-computing environment, the static algorithms cannot operate; thereby, it requires dynamic methods for balancing the workload among the virtual machines (Abdullahi et al., 2019). Due to the dynamic assets of the cloud-computing environment and heterogeneity, resource scheduling is considered as the nondeterministic polynomial (NP)-hard problem.