Cloud Service Failure Prediction on Google’s Borg Cluster Traces Using Traditional Machine Learning
Adrian-Ioan Tuns, Adrian Spătaru · 2023
The ability to predict failures in complex systems is crucial for maintaining their optimal performance, opening the possibility of reducing downtime and minimizing costs. In the context of cloud computing, cloud failure represents one of the most relevant problems, which not only leads to substantial financial losses but also negatively impacts the productivity of both industrial and end users. This paper presents a comprehensive study on the application of failure prediction techniques, by exploring four machine learning algorithms, namely Decision Tree, Random Forest, Gradient Boosting, and Logistic Regression.The research focuses on analyzing the workload of an industrial set of clusters, provided as traces in Google’s Borg cluster workload traces. The aim was to develop highly accurate predictive models for both job and task failures, a goal which was achieved. A job classifier having a performance of $83.97 \%$ accuracy (Gradient Boosting) and a task classifier of $\mathbf{9 8 . 7 9 \%}$ accuracy performance (Decision Tree) were obtained.