An Efficient Cloud Computing Method for Large-Scale Data Analysis

In this paper, we employ a self-adaptive cluster analysis, and this strategy is effective at reducing wait times. For the mining task, the former model relies on several different distribution formulas, while the later makes use of a deep learning model to maximize cloud performance. In the first section, we explore how to better meet the needs of our clients by enhancing the performance of data analysis using subtask resources. The mapReduce slot that supplies these resources is crucial to the cloud computing paradigm, total calculation task, speed and distribution probability planning process. This study employs Hadoop's dynamic slot allocation to pick idle VMs to shorten the overall runtime and lower resource consumption. A presumption of autonomy for the entire work is made. In the task mining process, tasks are automatically executed, which lessens the mining load and runtime. It has been shown through simulation that the proposed solution speeds up the completion of tasks, boosts network performance, and makes the cloud computing paradigm more flexible. The simulation results demonstrate that the suggested data mining approach is superior to the state-of-the-art methods for selecting VM.