Proficient job scheduling in cloud computation using an optimized machine learning strategy

• Published in: International journal of information technology (Singapore. Online) Vol. 15; no. 5; pp. 2409 - 2421
• Main Authors: Neelakantan, P., Yadav, N. Sudhakar
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.06.2023; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Big Data; Biomedical data; Chemical research; Cloud computing; Computer Imaging; Computer Science; Data mining; Deadlines; Efficiency; Energy consumption; Energy resources; Image Processing and Computer Vision; Machine Learning; Optimization; Original Research; Pattern Recognition and Graphics; Resource allocation; Scheduling; Software Engineering; Virtual environments; Vision; Makespan time; Cloud computing; Whale based convolution neural framework; Deadline; Resource allocation; Scheduling time; Data mining
• ISSN: 2511-2104; 2511-2112
• DOI: 10.1007/s41870-023-01278-8

In contemporary technology, cloud computing is applicable in many fields like biomedical systems, transactions, data mining, etc. In that, cloud computing job scheduling is a problematic task. Consequently, different operating systems and virtual machines have validated the user’s requirements and necessitated effective scheduling techniques in the cloud environment. Moreover, resource allocation and job scheduling are significant features in cloud computing. Nevertheless, the main drawback of the cloud computing model is the higher computation time that causes the deadline of all work. Previously, several approaches were proposed to diminish the computation time, but those techniques only apply to a few tasks. Therefore the novel Whale-based Convolution Neural Framework (WbCNF) strategy can effectively improve the task allocation system and reduce the job execution time. Moreover, the developed approach is implemented in the Python framework, and results show that the computation time has reduced the quantity of the tasks taken for the experimentation. Consequently, to verify the proposed technique’s efficiency, the proposed method is compared with conventional techniques in terms of performance metrices; the outcomes prove the enhancement of the cloud computing system.