Efficient Task Scheduling in a Cloud Environment based on Dynamic Priority and Optimized Technique

Cloud computing is an emerging field process with an enormous task of handling resources. From an application perspective, the study of task scheduling mechanisms for data transfer in large cloud computing environments needs to be performed better. Unbalanced scheduling leads to traffic load, energy loss, and hardware control failure. In addition, residents' devices are not considered to reduce power consumption delay. So, the Internet of things (IoT) rules the modern trends of the Internet. The enormous number of things (objects), which are associated with the Internet, produces a large amount of information that needs a ton of exertion and task preparation to make it valuable. To resolve this problem, we propose a dynamic multi-level task scheduling (DMLTS) based on cascade shrink priority (CSP) to allocate the task to optimize the scheduling. With intent, a Tactical Load Balancer (TLB) and The Preemptive Flow Manager (PFM) are responsible for applying a load balancing strategy based on the mixed load balancing algorithm to improve the task allocation better to balance the load to improve the response time. Experimental results have been demonstrated concerning better load balancing, lower power rate, and time consumption rate in both phase and random uniform propagation. Simulated results performance of this process can reduce data processing time and achieve load neutralization.