A Review of QoS-Driven Task Scheduling Algorithms and Their Impact on Data Quality in Process Management

The term "cloud computing" has been widely studied and used by major corporations ever since it was originally created. From the point of view of cloud computing, a variety of research topics and viewpoints have been considered, dealt with, and handled. Some examples of these include resource management, cloud security, and energy efficiency, to mention just a few. But, cloud computing is still faced with the significant obstacle of determining how to most effectively schedule tasks and manage available resources. We need effective scheduling strategies to handle these resources due to the size and dynamic resource provisioning of current data centres. The purpose of this work is to provide an overview of the various task scheduling methods that are utilized in the cloud computing environment till date. An attempt has been made to categorize current methods, investigate problems, and identify important problems that are currently present in this area. Our data reveals that 34% of researchers are concentrating on makespan for QoS (Quality of Service) metrics, 17% on cost, 15% on load balancing, 10% on deadline, and 9% on energy usage. Other criteria for the QoS parameter contribute far less than the ones mentioned above. According to this study, the scheduling algorithms that are used by researchers 80% of the time include the genetic algorithm in bio-inspired systems and particle swarm optimization in swarm intelligence. According to the available literature, 70% of the studies have utilized cloudsim as their simulation tool of choice. This paper also highlights a variety of ongoing problems and potential future directions in QoS-driven task scheduling algorithms for use in cloud computing environments.