| Popis: |
Nowadays, choosing a reliable cloud provider has grown to be quite difficult due to the exponential growth of cloud services. A thorough evaluation of cloud services from numerous angles necessitates an accurate decision-making process. Further study is required to provide more authentic decision making outcomes because of the enormous complexity and limits of current methodologies, which undermine the credibility of the energy efficient cloud selection process. This work aims to improve Hybrid machine learning (ML)-based Energy Efficient Framework. Methods: In this paper, we present a machine learning-based method for predicting Energy Efficient Cloud Selection (EEF-OCS), in which we use our proposed model to analyse various risk factors and predict Energy Efficient Cloud Selection, and we compare this method to other ML approaches like Logistic Regression, KNN, Decision Tree and MLP. Results: Among ML approaches, our suggested model EEF-OCS has produced the best prediction. We were able to get an accuracy of 91.78%, a precision of 92.00%, a recall of 91.78%, and f1 score of 91.71%. |
