Databases serve as the core of enterprise data management, and their stable and efficient operation is directly tied to business continuity. Any failure or performance bottleneck can severely impact operations and decision-making. Therefore, ensuring database health is crucial for enterprise digitalization. To accurately and comprehensively evaluate database health, this paper proposes HPSA-LSTM (Host, Performance, SQL, Alert-based LSTM), a predictive framework for database health metrics based on four dimensions: host, performance, SQL, and alerts. The framework integrates multi-dimensional data such as performance indicators, security status, and resource utilization to compute a comprehensive score that reflects the current health state of the database. With this approach, operators can quickly grasp the overall health condition without delving into individual monitoring metrics, enabling timely identification and resolution of potential issues. Experiments on multiple database instances demonstrate that the proposed model achieves excellent performance in predicting overall database health.

Kai Yan, Jingyu Jia, Lei Lv, Wanglong Han, Haitong Wu, Junpeng An. OceanBase Database Health Status Prediction System Based on the HPSA-LSTM Model. Academic Journal of Computing & Information Science (2025), Vol. 8, Issue 8: 59-66. https://doi.org/10.25236/AJCIS.2025.080809.

[1] P. Fantini, “Memory technology enabling future computing systems,” APL Mach. Learn., vol. 3, no. 2, 2025.

[2] Q. Xu, C. Yang, and A. Zhou, “Native Distributed Databases: Problems, Challenges and Opportunities,” Proc. VLDB Endow., vol. 17, no. 12, pp. 4217–4220, 2024.

[3] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.

[4] Z. Yang et al., “OceanBase: a 707 million tpmC distributed relational database system,” Proc. VLDB Endow., vol. 15, no. 12, pp. 3385–3397, 2022.

[5] J. L. Elman, “Finding structure in time,” Cogn. Sci., vol. 14, no. 2, pp. 179–211, 1990.

[6] C. Qin, L. Chen, Z. Cai, M. Liu, and L. Jin, “Long short-term memory with activation on gradient,” Neural Netw., vol. 164, pp. 135–145, 2023.

[7] I. Loshchilov and F. Hutter, “Sgdr: Stochastic gradient descent with warm restarts,” ArXiv Prepr. ArXiv160803983, 2016.

[8] D. P. Kingma, “Adam: A method for stochastic optimization,” ArXiv Prepr. ArXiv14126980, 2014.

[9] M. A. Hearst, S. T. Dumais, E. Osuna, J. Platt, and B. Scholkopf, “Support vector machines,” IEEE Intell. Syst. Their Appl., vol. 13, no. 4, pp. 18–28, 1998.

[10] S. J. Taylor and B. Letham, “Forecasting at scale,” Am. Stat., vol. 72, no. 1, pp. 37–45, 2018.

[11] D. K. Yadav, K. Soumya, and L. Goswami, “Autoregressive integrated moving average model for time series analysis,” in 2024 International Conference on Optimization Computing and Wireless Communication (ICOCWC), IEEE, 2024, pp. 1–6.