Implementing an AI-Powered Maintenance Framework for Enhancing Reliability in Small and Medium IT Infrastructures

References

[1] Adebiyi, F. M., Akinola, A. S., Santoro, A., &Mastrolitti, S. (2017). Chemical analysis of resin fraction of Nigerian bitumen for organic and trace metal compositions. Petroleum Science and Technology, 35(13), 1370-1380.

[2] Adebiyi, F. M., Thoss, V., & Akinola, A. S. (2014). Comparative studies of the elements that are associated with petroleum hydrocarbon formation in Nigerian crude oil and bitumen using ICP-OES. Journal of sustainable energy engineering, 2(1), 10-18.

[3] Ahmad, R., & Kamaruddin, S. (2018). Maintenance strategy optimization in SMEs. Journal of Industrial Engineering International, 14(2), 381–394.

[4] Ahmed, M., Mahmood, A., & Hu, J. (2016). A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 60, 19–31.

[5] Ahmed, M., Mahmood, A., & Hu, J. (2016). A survey of network data preprocessing in cybersecurity analytics. IEEE Communications Surveys & Tutorials, 18(1), 605–630.

[6] Akinola, A. S., Adebiyi, F. M., Santoro, A., &Mastrolitti, S. (2018). Study of resin fraction of Nigerian crude oil using spectroscopic/spectrometric analytical techniques. Petroleum Science and Technology, 36(6), 429-436.

[7] Al Mourad, M. B. (2016). ITSM process integration in hybrid enterprise systems. Procedia Computer Science, 94, 149–156.

[8] Alam, M., & Saini, H. (2015). Cloud computing for SMEs: Infrastructure, security, and adoption issues. International Journal of Engineering Research, 4(8), 421–428.

[9] Albakry, S., & Benkhelifa, E. (2016). Downtime causality in distributed systems. Journal of Systems and Software, 117, 35–48.

[10] Amir, M., & Hassan, R. (2016). A layered architectural model for predictive IT maintenance. International Journal of Computer Science Issues, 13(2), 45–53.

[11] BABATUNDE, O. A., ADERIBIGBE, S. A., JAJA, I. C., BABATUNDE, O. O., ADEWOYE, K. R., DUROWADE, K. A., & ADETOKUNBO, S. (2014). Sexual activities and practice of abortion among public secondary school students in Ilorin, Kwara State, Nigeria. International Journal of Science, Environment and Technology, 3(4), 1472-1479.

[12] Bari, A., Jiang, J., & Saad, W. (2018). Challenges in edge computing resource allocation. IEEE Communications Surveys & Tutorials, 20(4), 2886–2907.

[13] Basto, F., & Pereira, A. (2014). Component-based frameworks for autonomous monitoring systems. Procedia Technology, 17, 63–70.

[14] Bojarski, M., et al. (2016). End to end learning for self-driving cars. arXiv.

[15] Bousdekis, A., Magoutas, B., Apostolou, D., & Mentzas, G. (2015). Review of predictive maintenance decision-support systems. IFAC-PapersOnLine, 48(3), 171–177.

[16] Bouwman, H., Nikou, S., & de Reuver, M. (2018). SME productivity impacts of digital infrastructure. Telecommunications Policy, 42(9), 681–695.

[17] Brun, A., &Saetre, T. (2018). Financial evaluation of digital transformation investments. Journal of Industrial Engineering and Management, 11(1), 13–34.

[18] Bukhari, T.T., Oladimeji, O., Etim, E.D. & Ajayi, J.O., 2018. A Conceptual Framework for Designing Resilient Multi-Cloud Networks Ensuring Security, Scalability, and Reliability Across Infrastructures. IRE Journals, 1(8), pp.164-173. DOI: 10.34256/irevol1818

[19] Campos, J., & Pratas, N. (2015). Condition-based maintenance in SMEs through data-driven machine learning. Procedia Manufacturing, 11, 1491–1498.

[20] Cândido, C., & Pinto, A. (2017). Failure modes in legacy IT infrastructures. Journal of Information Technology, 32(4), 355–368.

[21] Carvalho, T., Soares, F., & Araujo, R. (2017). Real-time monitoring using hybrid machine learning pipelines. Expert Systems with Applications, 83, 1–11.

[22] Carvalho, T., Soares, F., Vita, R., Francisco, R., & Basto, J. (2018). A comparative study of predictive vs. preventive maintenance. Journal of Industrial Information Integration, 11, 1–9.

[23] Chukwunonso, F., & Ogu, E. (2018). ICT capacity development challenges in Africa. Journal of ICT Research and Applications, 12(2), 120–131.

[24] Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent units. NIPS.

[25] Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL-HLT.

[26] Durowade, K. A., Adetokunbo, S., &Ibirongbe, D. E. (2016). Healthcare delivery in a frail economy: Challenges and way forward. Savannah Journal of Medical Research and Practice, 5(1), 1-8.

[27] Durowade, K. A., Babatunde, O. A., Omokanye, L. O., Elegbede, O. E., Ayodele, L. M., Adewoye, K. R., ... & Olaniyan, T. O. (2017). Early sexual debut: prevalence and risk factors among secondary school students in Ido-ekiti, Ekiti state, South-West Nigeria. African health sciences, 17(3), 614-622.

[28] Durowade, K. A., Omokanye, L. O., Elegbede, O. E., Adetokunbo, S., Olomofe, C. O., Ajiboye, A. D., ... & Sanni, T. A. (2017). Barriers to contraceptive uptake among women of reproductive age in a semi-urban community of Ekiti State, Southwest Nigeria. Ethiopian journal of health sciences, 27(2), 121-128.

[29] Durowade, K. A., Salaudeen, A. G., Akande, T. M., Musa, O. I., Bolarinwa, O. A., Olokoba, L. B., ... & Adetokunbo, S. (2018). Traditional eye medication: A rural-urban comparison of use and association with glaucoma among adults in Ilorin-west Local Government Area, North-Central Nigeria. Journal of Community Medicine and Primary Health Care, 30(1), 86-98.

[30] El-Khatib, K. (2014). IT service degradation and business continuity failures. Journal of Business Continuity & Emergency Planning, 7(2), 150–162.

[31] Erigha, E. D., Ayo, F. E., Dada, O. O., & Folorunso, O. (2017). INTRUSION DETECTION SYSTEM BASED ON SUPPORT VECTOR MACHINES AND THE TWO-PHASE BAT ALGORITHM. Journal of Information System Security, 13(3).

[32] Feng, C., & Li, Z. (2018). Intrusion detection and governance frameworks using AI models. IEEE Access, 6, 3067–3078.

[33] François-Lavet, V., Henderson, P., Islam, R., et al. (2018). An introduction to deep reinforcement learning. Foundations and Trends in Machine Learning, 11(3–4), 219–354.

[34] Gao, J., & Zhu, Y. (2014). Data fusion and preprocessing models for reliability-centered monitoring. Computers in Industry, 65(2), 216–227.

[35] Gholami, M., & Daneshmand, M. (2016). Managing heterogeneous IT assets in small enterprises. Journal of Network and Computer Applications, 72, 145–158.

[36] Guo, L., Lei, Y., & Li, N. (2016). A deep convolutional framework for equipment health diagnostics. Mechanical Systems and Signal Processing, 72, 99–118.

[37] Gupta, A., & Mishra, R. (2016). The productivity cost of IT downtime in small enterprises. International Journal of Productivity and Performance Management, 65(3), 377–395.

[38] Hashemian, N., & Bean, A. (2015). Best practices for implementing predictive analytics in SME maintenance. Journal of Quality in Maintenance Engineering, 21(3), 306–318.

[39] Hawari, R., &Hejase, H. (2015). Talent shortages in IT operations for SMEs. Journal of Management Research, 7(3), 1–20.

[40] He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. CVPR.

[41] He, Q., Peng, X., & Chen, J. (2018). Architecture design for intelligent maintenance systems in smart enterprises. IEEE Access, 6, 9709–9721.

[42] Henderson, T., & Venkatraman, S. (2018). Integrating AI tools into ITSM workflows. Journal of Service Management, 29(4), 620–642.

[43] Heng, A., Zhang, S., Tan, A. C., & Mathew, J. (2015). Rotating machine predictive maintenance performance evaluation metrics. Mechanical Systems and Signal Processing, 64–65, 217–239.

[44] Hollis, A., & Wheeler, P. (2015). Cost-benefit modeling for AI deployment in SMEs. International Journal of Production Economics, 169, 421–430.

[45] Hosseini, M., Arshad, A., & Shafiee, M. (2018). Cloud computing and reliability analysis. Reliability Engineering & System Safety, 178, 1–9.

[46] Hussain, M., & Hoque, R. (2015). Predictive vs. reactive maintenance in SMEs. International Journal of Engineering Research, 6(6), 12–20.

[47] Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017). Bag of tricks for efficient text classification. EACL.

[48] Kim, H., & Park, S. (2016). Shortcomings of preventive maintenance in small data centers. IEEE Access, 4, 7720–7732.

[49] Kim, Y. (2014). Convolutional neural networks for sentence classification. EMNLP.

[50] Kwon, D., Yang, J., & Kim, K. (2017). Quantifying IT infrastructure reliability using MTBF- and MTTR-driven models. Computers & Industrial Engineering, 113, 720–730.

[51] Lary, D., & Elshazly, H. (2018). Monitoring patterns of system outages using machine learning. Journal of Big Data, 5(1), 1–19.

[52] Lee, J., Bagheri, B., & Kao, H. (2015). A cyber-physical systems architecture for Industry 4.0-based manufacturing systems. Manufacturing Letters, 3, 18–23.

[53] Lee, J., Bagheri, B., & Kao, H. A. (2015). A cyber-physical systems approach to predictive analytics. Manufacturing Letters, 3, 18–23.

[54] Li, X., Ding, H., & Huang, S. (2017). Autonomous scheduling algorithms for IT systems. Journal of Systems and Software, 132, 68–82.

[55] Li, Y. (2017). Deep reinforcement learning: An overview. arXiv preprint arXiv:1701.07274.

[56] Lozada, F., & Buitrago, E. (2014). Interoperability frameworks for enterprise service management. Computers & Industrial Engineering, 77, 1–10.

[57] Manyika, J., Chui, M., Bughin, J., & McCarthy, B. (2017). The ROI of artificial intelligence in small enterprises. McKinsey Global Institute Report.

[58] Menson, W. N. A., Olawepo, J. O., Bruno, T., Gbadamosi, S. O., Nalda, N. F., Anyebe, V., ... &Ezeanolue, E. E. (2018). Reliability of self-reported Mobile phone ownership in rural north-Central Nigeria: cross-sectional study. JMIR mHealth and uHealth, 6(3), e8760.

[59] Mishra, M., & Mahapatra, R. (2016). Data acquisition strategies for distributed computing environments. IEEE Transactions on Instrumentation and Measurement, 65(11), 2452–2462.

[60] Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2015). Human-level control through deep reinforcement learning. Nature, 518, 529–533.

[61] Mobley, R. K. (2014). Maintenance fundamentals. Elsevier.

[62] Nash, S. (2017). Operational performance decline due to weak maintenance. Journal of Operations and Supply Chain Management, 10(1), 1–12.

[63] Nayak, P., &Pattnaik, S. (2015). Disruptions in SME networks: Root-cause patterns. International Journal of Computer Applications, 128(10), 20–27.

[64] Nsa, B., Anyebe, V., Dimkpa, C., Aboki, D., Egbule, D., Useni, S., &Eneogu, R. (2018). Impact of active case finding of tuberculosis among prisoners using the WOW truck in North Central Nigeria. The International Journal of Tuberculosis and Lung Disease, 22(11), S444.

[65] Olamoyegun, M., David, A., Akinlade, A., Gbadegesin, B., Aransiola, C., Olopade, R., ... & Adetokunbo, S. (2015, October). Assessment of the relationship between obesity indices and lipid parameters among Nigerians with hypertension. In Endocrine Abstracts (Vol. 38). Bioscientifica.

[66] Olasehinde, O. (2018). Stock price prediction system using long short-term memory. In BlackInAI Workshop@ NeurIPS (Vol. 2018).

[67] Osabuohien, F. O. (2017). Review of the environmental impact of polymer degradation. Communication in Physical Sciences, 2(1).

[68] Pang, G., Shen, C., & van den Hengel, A. (2017). Deep learning for anomaly detection. ACM Computing Surveys, 54(2), 1–38.

[69] Pereira, A., & Romero, D. (2017). Economic impact of predictive maintenance technologies. Procedia Manufacturing, 11, 1499–1510.

[70] Rahman, M., & Ramos, I. (2016). IT workforce readiness and operational maturity. Information Systems Management, 33(4), 305–318.

[71] Rathore, M., Ahmad, A., & Paul, A. (2016). Real-time big data analytics for predictive maintenance. Journal of Supercomputing, 72(10), 3623–3646.

[72] Reddy, C., & Gupta, A. (2015). Decision-support systems for automated IT operations. Expert Systems, 32(4), 511–525.

[73] Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified real-time object detection. CVPR.

[74] Ren, L., Lv, H., Wang, S., & Zhao, F. (2017). Machine learning-based predictive maintenance vs. traditional inspection methods. IEEE Access, 5, 25010–25019.

[75] Ribeiro, I., Lopes, C., & Silva, F. (2017). Best-practice frameworks for industrial AI deployment. Procedia Manufacturing, 13, 1245–1252.

[76] Roman, R., Zhou, J., & Lopez, J. (2014). Security challenges in distributed systems. Future Generation Computer Systems, 30, 243–256.

[77] Satyanarayanan, M. (2017). The emergence of edge computing. Computer, 50(1), 30–39.

[78] Scholten, J., Eneogu, R., Ogbudebe, C., Nsa, B., Anozie, I., Anyebe, V., ... & Mitchell, E. (2018). Ending the TB epidemic: role of active TB case finding using mobile units for early diagnosis of tuberculosis in Nigeria. The international Union Against Tuberculosis and Lung Disease, 11, 22.

[79] Shah, M., & Clarke, S. (2015). ITIL-based integration strategies for service automation. Information Systems Management, 32(3), 240–254.

[80] Shah, P., & Mehta, R. (2014). Rule-based automation models for reliability-centered maintenance. Procedia Engineering, 97, 1600–1607.

[81] Shi, W., Cao, J., Zhang, Q., Li, Y., & Xu, L. (2016). Edge computing: Vision and challenges. IEEE Internet of Things Journal, 3(5), 637–646.

[82] Sicari, S., Rizzardi, A., Grieco, L. A., & Coen-Porisini, A. (2015). Security, privacy and trust in IoT. Computer Networks, 76, 146–164.

[83] Sikorska, J., Hodkiewicz, M., & Ma, L. (2015). Reliability indicators for industrial maintenance engineering. Reliability Engineering & System Safety, 142, 333–343.

[84] Silver, D., Huang, A., Maddison, C., et al. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529, 484–489.

[85] Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. ICLR.

[86] Solomon, O., Odu, O., Amu, E., Solomon, O. A., Bamidele, J. O., Emmanuel, E., &Parakoyi, B. D. (2018). Prevalence and risk factors of acute respiratory infection among under fives in rural communities of Ekiti State, Nigeria. Global Journal of Medicine and Public Health, 7(1), 1-12.

[87] Stetco, A., Breslin, J., & Sherry, L. (2015). Comparing automated maintenance pipelines with manual workflows. Procedia CIRP, 38, 250–255.

[88] Tankard, C. (2016). Data governance and security in cloud platforms. Network Security, 7, 5–12.

[89] Tavakoli, A., & Mosleh, A. (2017). Reliability modeling of IT service failures. Reliability Engineering & System Safety, 165, 56–67.

[90] Varghese, B., &Buyya, R. (2018). Next-generation cloud computing. Future Generation Computer Systems, 79, 849–861.

[91] Wang, D., & Sun, J. (2014). Online learning models for adaptive fault detection. Neurocomputing, 138, 297–305

[92] Wang, Q., & Zhang, Y. (2017). Resource optimization challenges in distributed IT infrastructures. Future Generation Computer Systems, 78, 19–29.

[93] Wang, T., & Yu, J. (2016). Machine learning–enabled reliability assessment for industrial systems. Journal of Manufacturing Science and Engineering, 138(10), 101004.

[94] Yeboah-Boateng, E. (2014). Barriers to ICT adoption in developing-country enterprises. International Journal of Computer Applications, 88(12), 15–22.

[95] YETUNDE, R. O., ONYELUCHEYA, O. P., & DAKO, O. F. (2018). Integrating Financial Reporting Standards into Agricultural Extension Enterprises: A Case for Sustainable Rural Finance Systems.

[96] Zhang, C., Bengio, S., Hardt, M., Recht, B., &Vinyals, O. (2016). Understanding deep learning requires rethinking generalization. ICLR.

[97] Zhang, T., & Guo, X. (2018). Maintenance scheduling inefficiencies in SMEs. Journal of Industrial Engineering International, 14(1), 45–57.

[98] Zhang, X., Ding, Q., & Li, N. (2018). Intelligent fault prediction using deep learning. IEEE Transactions on Industrial Informatics, 14(7), 3215–3223.

[99] Zhang, Y., & Zhao, L. (2015). Intelligent systems architecture for real-time IT asset management. Journal of Network and Computer Applications, 58, 37–47.

[100] Zhang, Y., Yang, L., & Wang, J. (2017). Intelligent predictive maintenance for SMEs using machine learning approaches. Journal of Manufacturing Systems, 45, 109–121.

[101] Zhao, Y., Nasrullah, Z., & Li, Z. (2018). PyOD: A Python toolbox for scalable outlier detection. Journal of Machine Learning Research, 20(96), 1–7.

[102] Zheng, S., Wang, P., & Li, Y. (2018). Reinforcement learning for automated maintenance decision-making. IEEE Access, 6, 75046–75055.

@article{1713060,
      author = {Precious Osobhalenewie Okoruwa, Odunayo Mercy Babatope, Winner Mayo, Taiwo Oyewole},
      title = {Implementing an AI-Powered Maintenance Framework for Enhancing Reliability in Small and Medium IT Infrastructures},
      journal = {Iconic Research And Engineering Journals},
      year = {2018},
      volume = {2},
      number = {2},
      pages = {154-173},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1713060.pdf},
      abstract = {Small and medium enterprises (SMEs) increasingly depend on distributed IT infrastructures to support business operations, yet they often lack the resources and technical capacity for effective maintenance and timely fault resolution. Traditional reactive and preventive maintenance strategies are inadequate in environments characterized by high system heterogeneity, limited redundancy, and constrained budgets. This review examines the emerging role of artificial intelligence (AI) in optimizing maintenance frameworks for SMEs, emphasizing predictive analytics, intelligent monitoring, and automated decision-support tools. The study synthesizes recent technological developments?including machine learning-based anomaly detection, natural language processing for log analysis, and reinforcement learning for automated maintenance scheduling?to evaluate how AI-driven systems can enhance reliability, reduce downtime, and improve operational resilience. Furthermore, the paper highlights key challenges such as data scarcity, cybersecurity vulnerabilities, implementation costs, and integration complexities within hybrid on-premise and cloud-based architectures. Finally, the paper proposes a conceptual AI-powered maintenance framework tailored to SME constraints and outlines future research directions for scalable, secure, and cost-efficient IT infrastructure maintenance.},
      keywords = {AI-Powered Maintenance, SME IT Infrastructure, Predictive Analytics, Reliability Engineering, Intelligent Monitoring, Automated Fault Detection.},
      month = {August},
      doi = {https://doi.org/10.64388/IREV2I2-1713060}
  }