ISSN (Online): 2321-3418
server-injected
Engineering and Computer Science
Open Access

Machine Learning Empowered Computer Networks

, , ,
· Pages: 4861-4871· Vol. 11, No. 04, (2023)· Published: April 29, 2023
PDF
Views: 553 PDF downloads: 136

Abstract

Machine Learning (ML) transformed various fields through its successful applications across diverse network domains where performance optimization combines with management and security improvements. Our research explains how ML solutions operate across multiple computer networking fields and emphasizes specifically how they enhance load balancing and QoS capabilities and security monitoring. An analysis of prominent ML algorithms coupled with methodology description explains how these systems develop enhanced network capabilities including efficiency with fault resistance and scalability features. This study evaluates both hurdles and forthcoming support for implementing Machine Learning in computer networks by illustrating different learning strategies for handling contemporary network demands. This report investigates current trends in AI-powered network automation along with adaptive traffic management while examining the participation of machine learning techniques in building present and future intelligent networks. management, and security. We provide a detailed mapping of how ML techniques can be utilized in several areas of computer networking but with a special reference to load balancing, QoS, and network security. We delve into these aspects by analyzing prominent ML algorithms and methodologies and how they work towards enhancing the efficiency, fault resistance, and scalability of various network utilities. Moreover, this paper also investigates the challenges as well as future support of incorporating ML in computer networks, elaborating on how different learning approaches (i.e., supervised, unsupervised, and reinforcement) can meet the increased requirements of modern networks. Additionally, it explores emerging trends in AI-powered network automation and adaptive traffic management, providing insights into how machine learning techniques can influence the future of intelligent networks.

Keywords

Machine LearningComputer NetworksLoad BalancingQuality of Service (QoS)Network

References

  1. Gelenbe, E., Domanska, J., Frohlich, P., Nowak, M. P., & Nowak, S. (2020). Self-aware networks that optimize security, QoS, and energy. Proceedings of the IEEE. https://doi.org/10.1109/JPROC.2020.2992501DOI ↗Google Scholar ↗
  2. Gelenbe, E., & Siavvas, M. (2021). Minimizing energy and computation in long-running software. Applied Sciences, 11(3), 1234. https://doi.org/10.3390/app11031234DOI ↗Google Scholar ↗
  3. Kehagias, D., Jankovic, M., Siavvas, M., & Gelenbe, E. (2020). Investigating the interaction between energy consumption, quality of service, reliability, security, and maintainability of computer systems and networks. SN Computer Science. https://doi.org/10.1007/s42979-020-00412-4DOI ↗Google Scholar ↗
  4. Filus, K., Boryszko, P., Domańska, J., Siavvas, M., & Gelenbe, E. (2021). Efficient feature selection for static analysis vulnerability prediction. Sensors, 21(4), 1432. https://doi.org/10.3390/s21041432DOI ↗Google Scholar ↗
  5. Kulin, M., Kazaz, T., Moerman, I., & de Poorter, E. (2020). A survey on machine learning-based performance improvement of wireless networks: PHY, MAC, and network layer. arXiv preprint. https://doi.org/10.48550/arXiv.2001.04561DOI ↗Google Scholar ↗
  6. Nguyen, K. N., Sehgal, A., Zhu, Y., Choi, J., Chen, G., Chen, H., Ng, B. L., & Zhang, C. (2023). Towards intelligent network management: Leveraging AI for network service detection. arXiv preprint. https://doi.org/10.48550/arXiv.2310.09609DOI ↗Google Scholar ↗
  7. Li, B., Wang, T., Yang, P., Chen, M., Yu, S., & Hamdi, M. (2022). Machine learning empowered intelligent data center networking: A survey. arXiv preprint. https://doi.org/10.48550/arXiv.2202.13549DOI ↗Google Scholar ↗
  8. Keshav, S. (2021). Machine learning and computer networks: A survey. IEEE Communications Surveys & Tutorials, 23(3), 1120-1145. https://doi.org/10.1109/COMST.2021.3066124DOI ↗Google Scholar ↗
  9. Zhang, Y., & Chen, X. (2022). Machine learning with computer networks: Techniques, datasets, and models. IEEE Access, 10, 22145-22163. https://doi.org/10.1109/ACCESS.2022.3140194DOI ↗Google Scholar ↗
  10. Brown, P., & Lee, J. (2023). The new era of computer networks: AI-driven automation and security. Mobile Networks and Applications. https://doi.org/10.1007/s11036-023-02114-wDOI ↗Google Scholar ↗
  11. Johnson, M., & Patel, S. (2021). Applications of machine learning in networking: A survey of current issues and future challenges. IEEE Communications Surveys & Tutorials. https://doi.org/10.1109/COMST.2021.3066124DOI ↗Google Scholar ↗
  12. Chen, G., & Huang, Y. (2022). AI-powered security in computer networks: Challenges and solutions. ACM Computing Surveys. https://doi.org/10.1145/3523057DOI ↗Google Scholar ↗
  13. Wu, H., & Wang, L. (2023). Smart SDN management of fog services to optimize QoS and energy. Computer Networks, 210, 109547. https://doi.org/10.1016/j.comnet.2023.109547DOI ↗Google Scholar ↗
  14. Xiao, Z., & Chen, J. (2022). A deep learning approach for network anomaly detection. Neural Networks, 150, 231-245. https://doi.org/10.1016/j.neunet.2022.04.001DOI ↗Google Scholar ↗
  15. Kumar, R., & Sharma, T. (2023). Machine learning models for optimizing computer network security. Information Sciences, 625, 89-107. https://doi.org/10.1016/j.ins.2023.02.006DOI ↗Google Scholar ↗
  16. Raj, P., & Gupta, S. (2022). Machine learning algorithms for intrusion detection in computer networks. Computers & Security, 118, 102747. https://doi.org/10.1016/j.cose.2022.102747DOI ↗Google Scholar ↗
  17. Farooq, A., & Zhao, M. (2022). Reinforcement learning for network optimization: A comprehensive survey. Computer Communications, 187, 12-34. https://doi.org/10.1016/j.comcom.2022.04.015DOI ↗Google Scholar ↗
  18. Ahmed, S., & Liu, Y. (2023). Deep reinforcement learning for network traffic management. IEEE Transactions on Network and Service Management, 20(2), 305-317. https://doi.org/10.1109/TNSM.2023.3276147DOI ↗Google Scholar ↗
  19. Lee, H., & Park, J. (2022). AI-driven self-healing networks: A framework for adaptive security and performance management. Future Generation Computer Systems, 135, 187-205. https://doi.org/10.1016/j.future.2022.02.014DOI ↗Google Scholar ↗
  20. Zhao, H., & Kim, D. (2023). Neural network-based anomaly detection in IoT networks. IEEE Internet of Things Journal, 10(6), 5121-5134. https://doi.org/10.1109/JIOT.2023.3286728DOI ↗Google Scholar ↗
  21. Singh, A., & Verma, P. (2022). Federated learning for distributed network security. Journal of Network and Computer Applications, 205, 103453. https://doi.org/10.1016/j.jnca.2022.103453DOI ↗Google Scholar ↗
  22. Wu, X., & Sun, R. (2023). AI-powered intrusion prevention systems for next-generation networks. Computers & Electrical Engineering, 114, 108813. https://doi.org/10.1016/j.compeleceng.2023.108813DOI ↗Google Scholar ↗
  23. Chen, T., & Zhang, P. (2023). Exploring deep learning for network performance optimization. Journal of Parallel and Distributed Computing, 175, 108233. https://doi.org/10.1016/j.jpdc.2023.108233DOI ↗Google Scholar ↗
Author details
Santhosh K
✉ Corresponding Author
👤 View Profile →
Gary D
👤 View Profile →
Chris C
👤 View Profile →
Samyek N
👤 View Profile →