Open Access

Interpretable AI-Based Architecture for Early Prediction of Solid-State Drive Failures

https://doi.org/10.55640/ijaair-v03i09-02

PDF

Kasun D. Perera ¹ , Nadeesha R. Fernando ¹ ,

⁴ Department of Artificial Intelligence, Colombo Institute of Technology, Colombo, Sri Lanka

⁴ Department of Computer Science, Kandy University of Technology, Kandy, Sri Lanka

Abstract

Solid-state drives (SSDs) have become fundamental components of contemporary computing infrastructures, yet their failure behavior remains difficult to predict because degradation can emerge from interacting software, workload, device, and operational factors. Conventional predictive systems may achieve useful classification performance while providing limited insight into why a drive is considered at risk. This paper proposes an interpretable artificial intelligence architecture for early SSD-failure prediction that integrates data preparation, feature engineering, machine-learning prediction, and explanation layers based on Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP). The architectural rationale is grounded in the provided literature on intelligent software systems, automated learning, system failures, information reuse, and interpretable SSD prediction. The proposed design treats interpretability not as a post-processing feature but as a functional component of the prediction pipeline. A methodological framework is developed around telemetry acquisition, temporal feature construction, risk estimation, explanation generation, and decision support. Analytical findings indicate that the architecture can improve transparency by identifying influential health indicators and distinguishing global failure drivers from instance-specific causes. The study further argues that interpretability can support maintenance prioritization, model validation, and human confidence, although explanations remain dependent on model quality, feature representation, and data distribution. The resulting framework provides a structured foundation for developing reliable and auditable SSD failure prediction systems.

Keywords

Solid-State Drive, SSD Failure Prediction, Explainable AI, LIME

References

M. T. Ahvanooey, Q. Li, M. Wu, and S. Wang, “A survey of genetic programming and its applications,” KSII Trans. Int. Inf. Syst., vol. 13, no. 4, pp. 1765–1794, Apr. 2019.

M. Bruch, M. Monperrus, and M. Mezini, “Learning from examples to improve code completion systems,” in Proc. 7th Joint Meeting Eur. Softw. Eng. Conf. ACM SIGSOFT Symp. Found. Softw. Eng., Amsterdam, The Netherlands, Aug. 2009, pp. 213–222.

A. Correia, J. Iyoda, and A. Mota, “Combining model finder and genetic programming into a general purpose automatic program synthesizer,” Inf. Process. Lett., vol. 154, Feb. 2020, Art. no. 105866.

B. Dagenais and H. Ossher, “Automatically locating framework extension examples,” in Proc. 16th ACM SIGSOFT Int. Symp. Found. Softw. Eng., Atlanta, GA, USA, Nov. 2008, pp. 203–213.

K. E. Emam and A. G. Koru, “A replicated survey of IT software project failures,” IEEE Softw., vol. 25, no. 5, pp. 84–90, Sep. 2008.

D. F. Ferreira, “Sisvar: A computer statistical analysis system,” Ciência e Agrotecnologia, vol. 35, no. 6, pp. 1039–1042, Dec. 2011.

B. Fitzgerald, “Software crisis 2.0,” Computer, vol. 45, no. 4, pp. 89–91, Apr. 2012.

M. Mooty, A. Faulring, J. Stylos, and B. A. Myers, “Calcite: Completing code completion for constructors using crowds,” in Proc. IEEE Symp. Vis. Lang. Human-Centric Comput., Spain, Sep. 2010, pp. 15–22.

A. S. Rappaport and V. L. Hinder, “Market impact of integrated software development environments,” in Proc. 33rd IEEE Comput. Soc. Int. Conf., San Francisco, CA, USA, Feb. 1988, pp. 250–253.

M. Reid and Y. Levy, “Integrating trust and computer self-efficacy with TAM: An empirical assessment of customers' acceptance of banking information systems (BIS) in Jamaica,” J. Internet Banking Commerce, vol. 12, no. 3, pp. 1–18, Dec. 2008.

P. Sebastian, L. Johannes, and M. Mira, “Intelligent code completion with Bayesian networks,” ACM Trans. Softw. Eng. Methodol, vol. 25, no. 3, pp. 1–31, Dec. 2015.

T. Suresh and X. Tao, “Parseweb: A programmer assistant for reusing open source code on the Web,” in Proc. 22nd IEEE/ACM Int. Conf. Automated Softw. Eng., Atlanta, GA, USA, Nov. 2007, pp. 204–213.

A. Svyatkovskiy, Y. Zhao, S. Fu, and N. Sundaresan, “Pythia: AI-assisted code completion system,” in Proc. 25th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining, Anchorage, AK, USA, Jul. 2019, pp. 2727–2735.

Y. Ye and G. Fischer, “Supporting reuse by delivering task-relevant and personalized information,” in Proc. 24th Int. Conf. Softw. Eng., Orlando, FL, USA, 2002, pp. 513–523.

M. V. Zelkowitz, “Perspectives in software engineering,” ACM Comput. Surv., vol. 10, no. 2, pp. 197–216, Jun. 1978.

Kumar, S. K. (2026). Explainable AI for SSD Failure Prediction: Using LIME and SHAP for Transparency. Journal of Engineering Research and Sciences, 5(4), 1–16. https://doi.org/10.55708/js0504001

Most read articles by the same author(s)

<< < 4 5 6 7 8 9 10 11 > >>

International Journal of Advanced Artificial Intelligence Research

Interpretable AI-Based Architecture for Early Prediction of Solid-State Drive Failures

Abstract

Keywords

References

Most read articles by the same author(s)

Similar Articles