A Machine Learning-Based Approach for Efficient Cloud Service Selection

Abstract

Cloud computing can be considered a revolutionizing invention of decay. The computing resources are externally supplied to the user with benefits of scalability, accessibility, pay-as-you-go, serverless, etc. With its ever-growing market, there is a multitude of cloud service providers (CSPs) with different offerings available to small and medium enterprises (SMEs) or users. Due to the availability of numerous CSPs with different offerings, it becomes complicated for the user to pick the right services. In the presented paper, a supervised learning-based model based on Random Forest Regressor is proposed. The proposed model has been trained for Multi Criteria Decision Making Methods (MCDM) methods such as Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS), VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR), and Weighted Sum Method (WSM). The score obtained from these MCDM methods has been used to rank the services. Results show the acceptability of the proposed model in the cloud environment. © 2022, Springer Nature Switzerland AG.