AI-Driven Capacity Planning for 5G Optical Transport Networks under Saudi Vision 2030

References

[1] Gu, R.; Yang, Z.; Ji, Y. Machine Learning for Intelligent Optical Networks: A Comprehensive Survey. Journal of Network and Computer Applications 2020, 157, 102576. https://doi.org/10.1016/j.jnca.2020.102576.

[2] Zhang, L.; Wang, J.; Chen, X.; Zhang, M. A survey on QoT prediction using machine learning in optical networks. Optical Fiber Technology, 2022, 68, 102804.

[3] Panayiotou, T.; Michalopoulou, M.; Ellinas, G. Survey on machine learning for traffic-driven service provisioning in optical networks. arXiv preprint arXiv:2209.05080, 2022.

[4] Fayad, A.; Jha, M.; Cinkler, T.; Rak, J. Planning a Cost-Effective Delay-Constrained Passive Optical Network for 5G Fronthaul. Sensors 2022, 22, 9394. https://doi.org/10.3390/s22239394.

[5] Bismi, B. S.; et al. A survey on increasing the capacity of 5G fronthaul systems using radio over fiber. Optical Fiber Technology, 2022, 69, 102845.

[6] Maryam, H.; Panayiotou, T.; Ellinas, G. Multi-step traffic prediction for multi-period planning in optical networks. arXiv preprint arXiv:2404.08314, 2024.

[7] Wlodarczyk, A.; et al. Machine-learning-assisted provisioning of time-varying traffic in spectrally-spatially flexible optical networks. Journal of Optical Communications and Networking, 2024.

[8] Du, W.; Cote, D.; Barber, C.; Liu, Y. Forecasting loss of signal in optical networks with machine learning. arXiv preprint arXiv:2201.07089, 2022.

[9] Communications, Space and Technology Commission. Saudi Internet Report 2024. Riyadh: CST, 2025.

[10] Ministry of Communications and Information Technology. Saudi Arabia's digital economy: a new era of tech growth, innovation and global impact. Riyadh: MCIT, 2025.

[11] Vision 2030. Vision 2030 Annual Report 2023. Riyadh: Government of Saudi Arabia, 2024.

[12] Vision 2030. National Transformation Program Annual Report 2024. Riyadh: Government of Saudi Arabia, 2025.

[13] stc Group. Annual Report 2024: strategy, performance and digital infrastructure. Riyadh: stc, 2025.

[14] Astaiza Hoyos, E.; et al. Towards 6G: a review of optical transport challenges for future mobile networks. Computation, 2025, 13(12), 286.

[15] Arjoune, Y.; Faruque, S. Artificial intelligence for 5G wireless systems: opportunities, challenges, and future research directions. arXiv preprint arXiv:2009.04943, 2020.

[16] Hussien, A. A.; et al. Machine learning techniques for spatiotemporal traffic prediction in 5G networks. Discover Applied Sciences, 2025.

[17] Lykakis, E.; et al. Data traffic prediction for 5G and beyond networks: methods and challenges. Electronics, 2025, 14(23), 4611.

[18] Gościen, R.; et al. Traffic prediction and explainable artificial intelligence for optimization of telecommunication networks. IFIP Networking Conference, 2024.

[19] Rubio, S.; Bogarra, S.; et al. Smart grid protection, automation and control: challenges and opportunities for digital infrastructure. Applied Sciences, 2025, 15(6), 3186.

[20] International Telecommunication Union. Measuring Digital Development: ICT Development Index and connectivity indicators. Geneva: ITU, 2024.

[21] International Energy Agency. Electricity Grids and Secure Energy Transitions. Paris: IEA, 2023.

[22] GSMA. The Mobile Economy Middle East and North Africa 2024. London: GSMA, 2024.

[23] O-RAN Alliance. O-RAN Architecture Description and RAN Intelligent Controller specifications. Bonn: O-RAN Alliance, 2023.

[24] 3GPP. Technical Specification Group Radio Access Network; NG-RAN Architecture Description. TS 38.401, Release 17. Sophia Antipolis: 3GPP, 2022.

[25] 3GPP. Technical Specification Group Services and System Aspects; System architecture for the 5G System. TS 23.501, Release 17. Sophia Antipolis: 3GPP, 2022.

[26] Open Networking Foundation. SDN-enabled broadband access and transport network automation reports. Menlo Park: ONF, 2021.

[27] IEEE Communications Society. Network automation and machine learning for next-generation optical transport systems. IEEE Communications Surveys and Tutorials, 2021.

[28] Khan, M. U. Fundamentals of next-generation network planning for 5G and beyond. arXiv preprint arXiv:2508.13469, 2025.

[29] Routray, S. K.; et al. Statistical analysis and modeling for optical networks. Electronics, 2025, 14(15), 2950.

[30] Iovanna, P.; et al. Flexible transport networks for future C-RAN. Journal of Optical Communications and Networking, 2025, 17(11), E129-E140.

@article{1722173,
      author = {Muhammad Tahir Imran},
      title = {AI-Driven Capacity Planning for 5G Optical Transport Networks under Saudi Vision 2030},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {2},
      pages = {283-294},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722173.pdf},
      abstract = {As part of Vision 2030, Saudi Arabia is fast-tracking digital transformation, expanding 5G connectivity, cloud services, smart cities, industrial automation and data-intensive applications. These developments put pressure on optical transport networks as mobile fronthaul, midhaul, backhaul and data-center interconnection require scalable capacity, low latency and resilient routing. In this review, we focus on the role of artificial intelligence in the capacity planning of 5G optical transport networks through the integration of traffic forecasting, quality-of-transmission estimation, topology awareness, CAPEX optimization and executive governance. We conducted a structured narrative review of machine learning in optical networks, traffic-driven service provisioning, 5G fronthaul design and Saudi digital infrastructure, for the period 2020-2025. In this paper we propose a layered planning framework that ingests telemetry, inventory, service demand and external development signals and transforms them into staged capacity decisions. The review concludes that AI should not supplant engineering judgement, but enhance planning evidence, shorten reaction time, improve investment timing and support Vision 2030 readiness across metro, intercity, edge and critical infrastructure corridors.},
      keywords = {AI Capacity Planning, 5G Optical Transport, Saudi Vision 2030, Traffic Forecasting, CAPEX Optimization, Optical Networks, Telecom Operators.},
      month = {August},
      doi = {https://doi.org/10.64388/IREV10I2-1722173}
  }