A Review of the Various Machine Learning Algorithms for Cloud Computing

Abstract

Cloud computing (CC) provides network services on request, especially data storage and processing capacity, without users' specific and direct management. CC recently became a collection of public and private data centers that provide the customer with a shared Internet network. Edge Computing is an emerging computing and knowledge storage model that puts end-users closer together to increase reaction times and save communication power. However, CC and edge computing face protection issues, including customer risk and corporate recognition, that hinder the swift implementation of computing modelling. One solution to this problem, because of its complexity and severity, is Machine Learning (ML) which consists of researching computational algorithms and naturally advancing knowledge. The problem and solution issues are raised by the overview article that analyses CC safety risks, problems, and solutions that use one or more ML algorithms. Study various ML algorithms, such as controlled, unmonitored, semi-supervised, and enforced training, to solve cloud protection problems. The paper assesses each technique's efficiency based on its characteristics, advantages, and drawbacks. In addition, it will have potential study guidance on safeguarding CC usage and applications.