Research on memory failure prediction based on ensemble learning

• Published in: PloS one Vol. 20; no. 4; p. e0321954
• Main Authors: Zhang, Peng, Zhang, Jialiang, Li, Yi
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 23.04.2025; Public Library of Science (PLoS)
• Subjects: Accuracy; Algorithms; Biology and Life Sciences; Cloud computing; Collaboration; Computer and Information Sciences; Computer centers; Data centers; Decision making; Decision trees; Deep learning; Engineering and Technology; Ensemble Learning; Failure; Forecasts and trends; Humans; Machine Learning; Memory - physiology; Models, Theoretical; Physical Sciences; Predictions; Research and Analysis Methods; Sensors; Social Sciences; System failures (Engineering); China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0321954

Timely prediction of memory failures is crucial for the stable operation of data centers. However, existing methods often rely on a single classifier, which can lead to inaccurate or unstable predictions. To address this, we propose a new ensemble model for predicting CE-driven memory failures, where failures occur due to a surge of correctable errors (CEs) in memory, causing server downtime. Our model combines several strong-performing classifiers, such as Random Forest, LightGBM, and XGBoost, and assigns different weights to each based on its performance. By optimizing the decision-making process, the model improves prediction accuracy. We validate the model using in-memory data from Alibaba’s data center, and the results show an accuracy of over 84%, outperforming existing single and dual-classifier models, further confirming its excellent predictive performance.