Systematic Approach to Deal with Internal Fragmentation and Enhancing Memory Space during COVID-19

The data scientists all over the world have observed and predicted the trend of COVID-19. Till date, it is observed that no new data analytics techniques have been found, which could aid in the recovery process. Tech developers and start-up companies throughout the world are facing the issue of cloud management and several storage issues due to the unforeseen COVID-19 pandemic. This work also serves as a solution for recovery and storage maintenance using data analytical tools like R programming and also implements various machine learning (ML) algorithms for analysis and prediction. The analysis and prediction are done based on algorithms like Linear Regression and Lasso Regression. The result of the ML algorithm is compared with the outcome of memory bank approach done using Scilab and the accuracy of the number of companies who use cloud storage is obtained. The above-mentioned ML algorithms are used to get a clear and better perspective of the proposed storage technique, which also helps to prevent internal fragmentation. This also serves to be one of the best algorithms to procure results with high precision and to avoid redundancy. The dataset used for this work is obtained from reliable sources like Google cloud platform and Enlyft. The dataset comprises the decreasing percentage of companies who have adopted cloud storage technique. The obtained results are also analyzed in the form of graph using R programming. Hence, it is proved through the data analytics results that this approach aids the micro companies to save their investment on cloud storage and adopt memory bank approach during the financial crunch caused by COVID-19. © 2022 Taylor & Francis Group, LLC.