TELEMETRY DATA PROCESSING AND IDENTIFICATION OF RELEVANT FEATURES FOR A DECISION SUPPORT SYSTEM IN THE CONTEXT OF ASSESSING THE FUNCTIONAL STATE OF RELATIONAL DATABASES
DOI:
https://doi.org/10.32689/maup.it.2026.2.12Keywords:
telemetry, feature selection, join paths, extreme learning, incident, feature matrix, decision support systemAbstract
The object of the study is the processing of Oracle Database 21c telemetry data and the formation of a relevant feature space for a decision support system intended to assess the functional state of a relational database. The problem is that a large initial set of metrics simultaneously contains diagnostically significant, contextual, redundant, and narrowly specialized indicators, while their direct use in the model complicates interpretation and may reduce assessment stability. A methodology is proposed that combines streaming V$ views and historical Automatic Workload Repository tables, the construction of join paths and relational trees, UTC-based temporal synchronization, aggregation, normalization, and temporal feature generation. Feature selection is performed using domain-informed criteria of diagnostic significance, non-redundancy, interpretability, and suitability for temporal alignment. As a result, ten groups of candidate metrics were divided into six core, two contextual, and two redundant groups: CPU, Database Wait Time Ratio, Buffer Cache Hit Ratio, Active Sessions, wait events / wait classes, and I/O waits were included in the core set; Executes and Physical Reads were partially included, whereas DB Block Gets and Background CPU Time were excluded. Incident labels are generated by combining deterministic rules with fuzzy membership functions. The resulting feature space was used to construct a time-ordered matrix and classify the functional state of the database using an extreme learning neural network model with information-guided hidden-neuron selection. An experiment conducted on a one-week dataset containing approximately 10,080 one-minute observations yielded an accuracy of approximately 0.64 at the selected operating point; analysis of the ROC curve and calibration plot indicated the need for additional tuning of the classification threshold. The practical significance of the study lies in providing a reproducible transition from heterogeneous telemetry to a compact, explainable feature space suitable for use in a decision support system.
References
James, C., Corbett, J., Dean, J., Epstein, M., Fikes, A., Frost, C., Furman, J.J., Ghemawat, S., Gubarev, A., Heiser, C., Hochschild, P., et al. (2013). Spanner: Google’s globally distributed database. ACM Transactions on Computer Systems (TOCS), Vol. 31. PP. 1–22. DOI:10.1145/2491245.
Yang, Z., Yang, C., Han, F., Zhuang, M., Yang, B., Yang, Z., Cheng, X., Zhao, Y., Shi, W., Xi, H., et al. (2022). OceanBase: a 707 million tpmC distributed relational database system. Proceedings of the VLDB Endowment, Vol. 15. PP. 3385–3397. DOI:10.14778/3554821.3554837.
Huang, D., Liu, Q., Cui, Q., Fang, Z., Ma, X., Xu F., Shen, L., Tang, L., Zhou, Y., Huang, M., et al. (2020). TiDB: a Raft-based HTAP database. Proceedings of the VLDB Endowment, Vol. 13. PP. 3072–3084. DOI:10.14778/3415478.3415535.
He, P., Liu, J., Lyu, M.R., Zhu, J., He, S. (2023). Loghub: A large collection of system log datasets towards automated log analytics, arXiv:2307.09227.
Zhang, X., Xu, Y., Lin, Q., Qiao, B., Zhang, H., Dang, Y., Xie, C., Yang, X., Cheng, Q., Li, Z., et al. (2019). Robust log-based anomaly detection on unstable log data. Proceedings of the 27th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, PP. 807–817. DOI:10.1145/3338906.3338964.
Du, M., Li, F., Zheng, G., Srikumar, V. (2017). Deeplog: Anomaly detection and diagnosis from system logs through deep learning. Proceedings of the ACM SIGSAC Conference on Computer and Communications Security, PP. 1285–1298. DOI:10.1145/3133956.3134015.
Meng, W., Liu, Y., Zhu, Y., Zhang, S., Pei, D., Liu, Y., Chen, Y., Zhang, R., Tao, S., Sun, P., et al. (2019). Loganomaly: Unsupervised detection of sequential and quantitative anomalies in unstructured logs. Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI), PP. 4739–4745.
Yin, K., Yan, M., Xu, L., Xu, Z., Li, Z., Yang, D., Zhang, X. (2020). Improving log-based anomaly detection with component-aware analysis. 2020 IEEE International Conference on Software Maintenance and Evolution (ICSME), PP. 667–671. DOI:10.1109/ICSME46990.2020.00077.
Guo, H., Yuan, S., Wu, X. (2021). Logbert: Log anomaly detection via BERT. Proceedings of the International Joint Conference on Neural Networks (IJCNN). IEEE, PP. 1–8. DOI:10.1109/IJCNN52387.2021.9533689.
Jia, T., Li, Y., Yang, Y., Huang, G., Wu, Z. (2022). Augmenting log-based anomaly detection models to reduce false anomalies with human feedback. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, PP. 3081–3089. DOI:10.1145/3534678.3539393.
Jia, T., Wu, Y., Hou, C., Li, Y. (2021). LogFlash: Real-time streaming anomaly detection and diagnosis from system logs for large-scale software systems. Proceedings of the IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE), PP. 80–90. DOI:10.1109/ISSRE52982.2021.00021.
Jia, T., Yang, L., Chen, P., Li, Y., Meng, F., Xu, J. (2017). Logsed: Anomaly diagnosis through mining time-weighted control flow graph in logs. Proceedings of the IEEE 10th International Conference on Cloud Computing (CLOUD), PP. 447–455. DOI:10.1109/CLOUD.2017.60.
Kim, J., Savchenko, V., Shin, K., Sorokin, K., Jeon, H., Pankratenko, G., Markov, S., Kim, C.-J. (2020). Automatic abnormal log detection by analyzing log history for providing debugging insight. Proceedings of the 42nd International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP), PP. 71–80. DOI:10.1145/3377813.3381363.
Lin, Q., Zhang, H., Lou, J., Zhang, Y., Chen, X. (2016). Log clustering based problem identification for online service systems. Proceedings of the 38th International Conference on Software Engineering Companion, PP. 102–111. DOI:10.1145/2889160.2889232.
Huo, Y., Li, Y., Su, Y., He, P., Xie, Z., Lyu, M.R. (2023). AutoLog: A log sequence synthesis framework for anomaly detection, arXiv:2308.09324.
Landauer, M., Skopik, F., Wurzenberger, M. (2023). A critical review of common log data sets used for evaluation of sequence-based anomaly detection techniques, arXiv:2309.02854.
Wang, C., Huang, X., Qiao, J., Jiang, T., Rui, L., Zhang, J., Kang, R., Feinauer, J., McGrail, K.A., Wang, P., et al. (2020). Apache IoTDB: Time-series database for internet of things. Proceedings of the VLDB Endowment, Vol. 13. PP. 2901–2904. DOI:10.14778/3415478.3415504.
Zhang, L., Jia, T., Jia, M., Li, Y., Yang, Y., Wu, Z. (2024). Multivariate log-based anomaly detection for distributed database. Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, PP. 12. DOI:10.1145/3637528.3671725.
Oraculix. Monitoring Oracle performance with AppDynamics, 2013. [Online]. Retrieved from: https://oraculix.com/2013/02/25/monitoring-oracle-performance-with-appdynamics/.
Oracle. Instance tuning using performance views. Database Performance Tuning Guide, 2023. [Online]. Retrieved from: https://docs.oracle.com/en/database/oracle/oracle-database/23/tgdba/instance-tuning-using-performance-views.html.
Lam, H.T., Thiebaut, J.M., Sinn, M., Chen, B., Mai, T., Alkan, O. (2017). One button machine for automating feature engineering in relational databases, arXiv:1706.00327. DOI:10.48550/arXiv.1706.00327.
Wilkinson, M.D., Dumontier, M., Aalbersberg, I.J., Appleton, G., Axton, M., Baak, A., Blomberg, N., Boiten, J.-W., da Silva Santos, L.B., Bourne, P.E., et al. (2016). The FAIR Guiding Principles for scientific data management and stewardship. Scientific Data, Vol. 3. Article 160018. DOI:10.1038/sdata.2016.18.
Buchanan, E., Crain, S., Cunningham, A., Johnson, H., Stash, H., Papadatou-Pastou, M., Isager, P., Carlsson, R., Aczel, B. (2019). Getting started creating data dictionaries: How to create a shareable dataset. OSF Preprints, DOI:10.31219/osf.io/vd4y3.
