An intelligent task scheduling approach for the enhancement of collaborative learning in cloud computing

Abstract

Cloud computing is the foremost technology that reliably connects end-to-end users. Task scheduling is a critical process affecting the performance enhancement of cloud computing. The scheduling of the enormous data results in increased response time, makespan time, and makes the system less efficient. Therefore, a unique Squirrel Search-based AlexNet Scheduler (SSbANS) is created for adequate scheduling and performance enhancement in cloud computing suitable for collaborative learning. The system processes the tasks that the cloud users request. Initially, the priority of each task is checked and arranged. Moreover, the optimal resource is selected using the fitness function of the squirrel search, considering the data rate and the job schedule. Further, during the scheduled task-sharing process, the system continuously checks for overloaded resources and balances based on the squirrel distribution function. The efficacy of the model is reviewed in terms of response time, resource usage, makespan time, and throughput. The model achieved a higher throughput and resource usage rate with a lower response and makespan time.