SLA Violation Prediction In Cloud Computing: A Machine Learning Perspective
This work addresses SLA violation prediction for cloud service providers to avoid penalties, but it is incremental as it applies existing methods to a specific domain.
The paper tackled the problem of predicting SLA violations in cloud computing, which are rare events (~0.2%), by exploring machine learning models like Naive Bayes and Random Forest with re-sampling methods, achieving an accuracy of 99.88% and an F1 score of 0.9980 with Random Forest and SMOTE-ENN.
Service level agreement (SLA) is an essential part of cloud systems to ensure maximum availability of services for customers. With a violation of SLA, the provider has to pay penalties. In this paper, we explore two machine learning models: Naive Bayes and Random Forest Classifiers to predict SLA violations. Since SLA violations are a rare event in the real world (~0.2 %), the classification task becomes more challenging. In order to overcome these challenges, we use several re-sampling methods. We find that random forests with SMOTE-ENN re-sampling have the best performance among other methods with the accuracy of 99.88 % and F_1 score of 0.9980.