Multi-Step Traffic Prediction for Multi-Period Planning in Optical Networks
Abstract: A multi-period planning framework is proposed that exploits multi-step ahead traffic predictions to address service overprovisioning and improve adaptability to traffic changes, while ensuring the necessary quality-of-service (QoS) levels. An encoder-decoder deep learning model is initially leveraged for multi-step ahead prediction by analyzing real-traffic traces. This information is then exploited by multi-period planning heuristics to efficiently utilize available network resources while minimizing undesired service disruptions (caused due to lightpath re-allocations), with these heuristics outperforming a single-step ahead prediction approach.
- T. Panayiotou and G. Ellinas, “Addressing traffic prediction uncertainty in multi-period planning optical networks,” in Proc. IEEE/OSA Optical Fiber Communications Conference (OFC), 2022.
- T. Panayiotou, M. Michalopoulou, and G. Ellinas, “Survey on machine learning for traffic-driven service provisioning in optical networks,” IEEE Communications Surveys & Tutorials, vol. 25, no. 2, pp. 1412–1443, 2023.
- T. Panayiotou, K. Manousakis, S. Chatzis, and G. Ellinas, “A data-driven bandwidth allocation framework with QoS considerations for EONs,” IEEE/OSA J. Light. Technol., vol. 37, no. 9, pp. 1853–1864, 2019.
- X. Chen, R. Proietti, H. Lu, A. Castro, and S. Yoo, “Knowledge-based autonomous service provisioning in multi-domain elastic optical networks,” IEEE Commun. Mag., vol. 56, no. 8, pp. 152–158, 2018.
- M. Balanici and S. Pachnicke, “Classification and forecasting of real-time server traffic flows employing long short-term memory for hybrid E/O data center networks,” IEEE/OSA J. Opt. Commun. Netw., vol. 13, no. 5, pp. 85–93, 2021.
- S. K. Singh, C.-Y. Liu, S. J. Ben Yoo, and R. Proietti, “Machine-learning-aided dynamic reconfiguration in optical DC/HPC networks,” in Proc. IEEE Optical Network Design and Modelling (ONDM), 2022.
- H. Maryam, T. Panayiotou, and G. Ellinas, “Uncertainty quantification and consideration in ML-aided traffic-driven service provisioning,” Comp. Commun., vol. 202, pp. 13–22, 2023.
- S. Shakya, Y. Wang, X. Cao, Z. Ye, and C. Qiao, “Minimize sub-carrier reallocation in elastic optical path networks using traffic prediction,” in Proc. IEEE Global Communications Conference (GLOBECOM), 2013.
- R. Alvizu, X. Zhao, G. Maier, Y. Xu, and A. Pattavina, “Energy efficient dynamic optical routing for mobile metro-core networks under tidal traffic patterns,” IEEE/OSA J. Light. Technol., vol. 35, no. 2, pp. 325–333, 2017.
- K. Cho, B. Van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation,” arXiv:1406.1078 [cs.CL], 2014.
- S. Behera, T. Panayiotou, and G. Ellinas, “Machine learning framework for timely soft-failure detection and localization in elastic optical networks,” IEEE/OPTICA J. Opt. Commun. Netw., vol. 15, no. 10, pp. E74–E85, 2023.
- M. Jinno, B. Kozicki, H. Takara, A. Watanabe, Y. Sone, T. Tanaka, and A. Hirano, “Distance-adaptive spectrum resource allocation in spectrum-sliced elastic optical path network,” IEEE Commun. Mag., vol. 48, no. 8, pp. 138–145, 2010.
- K. Christodoulopoulos, I. Tomkos, and E. Varvarigos, “Time-varying spectrum allocation policies and blocking analysis in flexible optical networks,” IEEE J. Sel. Areas Commun., vol. 31, no. 1, pp. 13–25, 2013.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.