AI-powered network automation: Emerging trends and applications
DOI:
https://doi.org/10.15680/xqtv1t12Keywords:
AI-Powered Network Automation, Machine Learning for Network Security, Cloud Infrastructure Optimization, Predictive Network Analytics, Interdisciplinary Network EngineeringAbstract
This article provides a comprehensive analysis of artificial intelligence applications in network automation, examining how machine learning techniques are revolutionizing traditional network management approaches. Through systematic examination of supervised, unsupervised, and reinforcement learning methodologies, the article demonstrates the transformative impact of AI on routing optimization, anomaly detection, and adaptive network control systems. The comparative article reveals significant performance advantages of AI-driven methods over traditional approaches, including faster fault detection, improved resource utilization, and reduced operational complexity. The article explores how these technologies enable sophisticated cloud infrastructure optimization through predictive analytics, real-time scalability, and intelligent resource allocation, while simultaneously reducing environmental impact through energy consumption optimization. The article further examines AI's contribution to network security, highlighting advances in neural network-based threat detection and adaptive intrusion prevention systems that significantly reduce response times while minimizing false positives. By addressing interdisciplinary research approaches and future challenges—including ethical considerations, explainability, scalability, and integration with emerging technologies—this work provides a forward-looking perspective on the evolving landscape of intelligent network automation and its implications for network engineering professionals.
References
[1] Raouf Boutaba, Mohammad A. Salahuddin et al., "A comprehensive survey on machine learning for networking: evolution, applications and research opportunities," Journal of Internet Services and Applications, vol. 9, no. 1, pp. 1-99, 21 June 2018. https://jisajournal.springeropen.com/articles/10.1186/s13174-018-0087-2
[2] Wanrong Yang et al. "A Survey for Deep Reinforcement Learning Based Network Intrusion Detection." ArXiv, 25 Sep 2024, https://arxiv.org/abs/2410.07612
[3] Hongzi Mao, Mohammad Alizadeh, et al, "Resource Management with Deep Reinforcement Learning," in Proceedings of the 15th ACM Workshop on Hot Topics in Networks, pp. 50-56, 09 November 2016. https://dl.acm.org/doi/10.1145/3005745.3005750
[4] Samrat Kumar Dey, Md Mahbubur Rahman. "Effects of machine learning approach in flow-based anomaly detection on software-defined networking." Symmetry 12.1 (18 December 2019): 7. https://www.mdpi.com/2073-8994/12/1/7
[5] Qingchen Zhang, Laurence T. Yang, et al, "A survey on deep learning for big data," Information Fusion, vol. 42, pp. 146-157, July 2018. https://www.sciencedirect.com/science/article/abs/pii/S1566253517305328
[6] Muhammad H. B. Mahbod, et al. "Energy Saving Evaluation of an Energy Efficient Data Center Using a Model-free Reinforcement Learning Approach." Applied Energy, vol. 322, 15 September 2022, p. 119392, https://doi.org/10.1016/j.apenergy.2022.119392
[7] Giovanni Apruzzese, Michele Colajanni, et al, "On the effectiveness of machine and deep learning for cyber security," in IEEE International Conference on Cyber Conflict, pp. 371-390, 09 July 2018. https://ieeexplore.ieee.org/document/8405026
[8] Hannah Bast, Daniel Delling et al., "Route planning in transportation networks," in Algorithm Engineering, pp. 19-80, 11 November 2016. https://link.springer.com/chapter/10.1007/978-3-319-49487-6_2
[9] Nick Feamster, Jennifer Rexford, "Why (and How) Networks Should Run Themselves," in Proceedings of the Applied Networking Research Workshop, pp. 20-26, 16 July 2018.
