{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T13:55:51Z","timestamp":1761746151293,"version":"build-2065373602"},"reference-count":39,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T00:00:00Z","timestamp":1759795200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Catalonia Government through the Agency for Management of University and Research Grants","award":["SGR-2021-00598"],"award-info":[{"award-number":["SGR-2021-00598"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Network"],"abstract":"<jats:p>Elastic optical networks (EONs) must allocate resources dynamically to accommodate heterogeneous, high-bandwidth demands. However, the continuous setup and teardown of connections with different bit rates can fragment the spectrum and lead to blocking. The blocking predictors enable proactive defragmentation and resource reallocation within network controllers. In this paper, we propose two novel deep learning models (based on CNN\u2013BiLSTM and CNN\u2013LSTM) to predict blocking in EONs by combining spatial feature extraction from spectrum snapshots using 2D convolutional layers with temporal sequence modeling. This hybrid spatio-temporal design learns how local fragmentation patterns evolve over time, allowing it to detect impending blocking scenarios more accurately than conventional methods. We evaluate our model on the simulated NSFNET topology and compare it against multiple baselines, namely 1D CNN, 2D CNN, k-nearest neighbors (KNN), and support vector machines (SVMs). The results show that the proposed CNN\u2013BiLSTM\/LSTM models consistently achieve higher performance. The CNN\u2013BiLSTM model achieved the highest accuracy in blocking prediction, while the CNN\u2013LSTM model shows slightly lower accuracy; however, it has much lower complexity and a faster learning time.<\/jats:p>","DOI":"10.3390\/network5040044","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T10:48:07Z","timestamp":1759834087000},"page":"44","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Hybrid Spatio-Temporal CNN\u2013LSTM\/BiLSTM Models for Blocking Prediction in Elastic Optical Networks"],"prefix":"10.3390","volume":"5","author":[{"given":"Farzaneh","family":"Nourmohammadi","sequence":"first","affiliation":[{"name":"Department of Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya, 08034 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaume","family":"Comellas","sequence":"additional","affiliation":[{"name":"Department of Signal Theory and Communications, Universitat Polit\u00e8cnica de Catalunya, 08034 Barcelona, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4500-9098","authenticated-orcid":false,"given":"Uzay","family":"Kaymak","sequence":"additional","affiliation":[{"name":"Jheronimus Academy of Data Science, Eindhoven University of Technology, 5600 MB Eindhoven, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,10,7]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Nourmohammadi, F., Parmar, C., Wings, E., and Comellas, J. (2024). Using convolutional neural networks for blocking prediction in elastic optical networks. Appl. Sci., 14.","key":"ref_1","DOI":"10.3390\/app14052003"},{"doi-asserted-by":"crossref","unstructured":"Li, C., Huang, Y.C., and Mu, L. (2023, January 4\u20137). Inter-Core Crosstalk Aware Deep Reinforcement Learning Based Resource Allocation in Multicore Elastic Optical Networks. Proceedings of the 2023 Asia Communications and Photonics Conference\/2023 International Photonics and Optoelectronics Meetings (ACP\/POEM), Wuhan, China.","key":"ref_2","DOI":"10.1109\/ACP\/POEM59049.2023.10368728"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"104133","DOI":"10.1016\/j.yofte.2025.104133","article-title":"DRL-based fragmentation-and impairment-aware resource allocation algorithm in C + L band elastic optical networks","volume":"90","author":"Yan","year":"2025","journal-title":"Opt. Fiber Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1109\/COMST.2017.2769102","article-title":"Fragmentation problems and management approaches in elastic optical networks: A survey","volume":"20","author":"Chatterjee","year":"2017","journal-title":"IEEE Commun. Surv. Tutor."},{"doi-asserted-by":"crossref","unstructured":"Xie, J., Song, Y., Zhang, Y., Li, S., Zhang, M., and Wang, D. (2024, January 2\u20135). Physical Layer-Aware Route and Spectrum Allocation in Optical Networks by Multi-Objective Deep Reinforcement Learning. Proceedings of the 2024 Asia Communications and Photonics Conference (ACP) and International Conference on Information Photonics and Optical Communications (IPOC), Beijing, China.","key":"ref_5","DOI":"10.1109\/ACP\/IPOC63121.2024.10809683"},{"doi-asserted-by":"crossref","unstructured":"Comellas, J., Nourmohammadi, F., and Junyent, G. (2019, January 9\u201313). Impact of traffic delay tolerance on elastic optical networks performance. Proceedings of the 2019 21st International Conference on Transparent Optical Networks (ICTON), Angers, France.","key":"ref_6","DOI":"10.1109\/ICTON.2019.8840381"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/JLT.2024.3446762","article-title":"Deep Reinforcement Learning for QoT-Aware Routing, Modulation, and Spectrum Assignment in Elastic Optical Networks","volume":"43","author":"Asiri","year":"2024","journal-title":"J. Light. Technol."},{"doi-asserted-by":"crossref","unstructured":"Pinto-R\u00edos, J., Leiva, A., Feris, B.D., Iglesias, D., Cuevas, C., Jara, N., Olivares, R., Morales, P., B\u00f3rquez-Paredes, D., and Saavedra, G. (2024, January 14\u201318). Dynamic multicore elastic optical networks: A comparative study of performance using heuristics and artificial intelligence. Proceedings of the 2024 24th International Conference on Transparent Optical Networks (ICTON), Bari, Italy.","key":"ref_8","DOI":"10.1109\/ICTON62926.2024.10647659"},{"doi-asserted-by":"crossref","unstructured":"Choudhury, P.D., and De, T. (2019, January 9\u201313). Recent developments in Elastic Optical Networks Using Machine Learning. Proceedings of the 2019 21st International Conference on Transparent Optical Networks (ICTON), Angers, France.","key":"ref_9","DOI":"10.1109\/ICTON.2019.8840462"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"4945","DOI":"10.1109\/JLT.2022.3175865","article-title":"Deep reinforcement learning-based routing and spectrum assignment of EONs by exploiting GCN and RNN for feature extraction","volume":"40","author":"Xu","year":"2022","journal-title":"J. Light. Technol."},{"doi-asserted-by":"crossref","unstructured":"Zhu, X., Wang, J., Lai, Q., Luo, X., Ren, R., and Lu, H. (2023, January 3\u20135). Research on 5G Network Slicing Type Prediction Based on Random Forest and Deep Neural Network. Proceedings of the 2023 IEEE 8th International Conference on Big Data Analytics (ICBDA), Harbin, China.","key":"ref_11","DOI":"10.1109\/ICBDA57405.2023.10104899"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2675","DOI":"10.1109\/LCOMM.2022.3195778","article-title":"Heuristic Reward Design for Deep Reinforcement Learning-Based Routing, Modulation and Spectrum Assignment of Elastic Optical Networks","volume":"26","author":"Tang","year":"2022","journal-title":"IEEE Commun. Lett."},{"doi-asserted-by":"crossref","unstructured":"Singh, S.K., and Jukan, A. (May, January 29). Computing blocking probabilities in elastic optical networks with spectrum defragmentation. Proceedings of the IEEE INFOCOM 2019-IEEE Conference on Computer Communications, Paris, France.","key":"ref_13","DOI":"10.1109\/INFOCOM.2019.8737554"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1515\/joc-2018-0055","article-title":"Limitation of Erlang B Traffic Model in elastic optical network for blocking probability estimation","volume":"42","author":"Ujjwal","year":"2021","journal-title":"J. Opt. Commun."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"100684","DOI":"10.1016\/j.osn.2022.100684","article-title":"Routing and spectrum assignment employing long short-term memory technique for elastic optical networks","volume":"45","author":"Cheng","year":"2022","journal-title":"Opt. Switch. Netw."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"890","DOI":"10.1016\/j.icte.2023.01.008","article-title":"Triggering strategy for defragmentation process in elastic optical networks using machine learning techniques","volume":"9","author":"Enciso","year":"2023","journal-title":"ICT Express"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1412","DOI":"10.1109\/COMST.2023.3247842","article-title":"Survey on Machine Learning for Traffic-Driven Service Provisioning in Optical Networks","volume":"25","author":"Panayiotou","year":"2023","journal-title":"IEEE Commun. Surv. Tutor."},{"unstructured":"Knapi\u0144ska, A., Kanimba, R., Yesilyurt, Y., and Walkowiak, K. (2024, January 18\u201320). Application of Ensemble Regression Methods in Elastic Optical Network Optimization. Proceedings of the 5th Polish Conference on Artificial Intelligence (PP-RAI 2024), Warsaw, Poland. Available online: https:\/\/research.chalmers.se\/publication\/543844.","key":"ref_18"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"104210","DOI":"10.1016\/j.yofte.2025.104210","article-title":"Enhanced resource allocation in elastic optical network using deep learning and optimization process","volume":"93","author":"Easwaran","year":"2025","journal-title":"Opt. Fiber Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1109\/LCOMM.2022.3224213","article-title":"The research of resource allocation method based on GCN-LSTM in 5G network","volume":"27","author":"Gao","year":"2022","journal-title":"IEEE Commun. Lett."},{"key":"ref_21","first-page":"4140594","article-title":"Resource allocation in multicore elastic optical networks: A deep reinforcement learning approach","volume":"2023","author":"Leiva","year":"2023","journal-title":"Complexity"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"132856","DOI":"10.1109\/ACCESS.2024.3404866","article-title":"Neural Networks in Selected Aspects of Communications and Networking","volume":"12","author":"Borylo","year":"2024","journal-title":"IEEE Access"},{"doi-asserted-by":"crossref","unstructured":"Azzouni, A., and Pujolle, G. (2018, January 23\u201327). NeuTM: A Neural Network-Based Framework for Traffic Matrix Prediction in SDN. Proceedings of the 2018 IEEE\/IFIP Network Operations and Management Symposium (NOMS), Taipei, Taiwan.","key":"ref_23","DOI":"10.1109\/NOMS.2018.8406199"},{"doi-asserted-by":"crossref","unstructured":"Aibin, M., and Walkowiak, K. (2018, January 27\u201329). Monte Carlo Tree Search for Cross-Stratum Optimization of Survivable Inter-Data Center Elastic Optical Network. Proceedings of the 2018 10th International Workshop on Resilient Networks Design and Modeling (RNDM), Longyearbyen, Norway.","key":"ref_24","DOI":"10.1109\/RNDM.2018.8489841"},{"doi-asserted-by":"crossref","unstructured":"Poupart, P., Chen, Z., Jaini, P., Fung, F., Susanto, H., Geng, Y., Chen, L., Chen, K., and Jin, H. (2016, January 8\u201311). Online Flow Size Prediction for Improved Network Routing. Proceedings of the 2016 IEEE 24th International Conference on Network Protocols (ICNP), Singapore.","key":"ref_25","DOI":"10.1109\/ICNP.2016.7785324"},{"doi-asserted-by":"crossref","unstructured":"Nie, L., Jiang, D., Yu, S., and Song, H. (2017, January 19\u201322). Network Traffic Prediction Based on Deep Belief Network in Wireless Mesh Backbone Networks. Proceedings of the 2017 IEEE Wireless Communications and Networking Conference (WCNC), San Francisco, CA, USA.","key":"ref_26","DOI":"10.1109\/WCNC.2017.7925498"},{"doi-asserted-by":"crossref","unstructured":"Reddy, S.P., and Kumar, A.P. (2024, January 16\u201318). Optimizing Defect Detection in Elastic Optical Networks using a Deep Neural Network and Fuzzy Logic. Proceedings of the 2024 9th International Conference on Communication and Electronics Systems (ICCES), Coimbatore, India.","key":"ref_27","DOI":"10.1109\/ICCES63552.2024.10859759"},{"doi-asserted-by":"crossref","unstructured":"Maryam, H., Panayiotou, T., and Ellinas, G. (2024, January 14\u201318). Multi-Step Traffic Prediction for Multi-Period Planning in Optical Networks. Proceedings of the 2024 24th International Conference on Transparent Optical Networks (ICTON), Bari, Italy.","key":"ref_28","DOI":"10.1109\/ICTON62926.2024.10648008"},{"doi-asserted-by":"crossref","unstructured":"Vinchoff, C., Chung, N., Gordon, T., Lyford, L., and Aibin, M. (2020, January 19\u201323). Traffic Prediction in Optical Networks Using Graph Convolutional Generative Adversarial Networks. Proceedings of the 2020 22nd International Conference on Transparent Optical Networks (ICTON), Bari, Italy.","key":"ref_29","DOI":"10.1109\/ICTON51198.2020.9203477"},{"doi-asserted-by":"crossref","unstructured":"Aibin, M., Chung, N., Gordon, T., Lyford, L., and Vinchoff, C. (July, January 28). On Short- and Long-Term Traffic Prediction in Optical Networks Using Machine Learning. Proceedings of the 2021 International Conference on Optical Network Design and Modeling (ONDM), Gothenburg, Sweden.","key":"ref_30","DOI":"10.23919\/ONDM51796.2021.9492437"},{"doi-asserted-by":"crossref","unstructured":"Goscien, R. (2024, January 3\u20136). Traffic Prediction- and Explainable Artificial Intelligence-Based Dynamic Routing in Software-Defined Elastic Optical Networks. Proceedings of the 2024 IFIP Networking Conference (IFIP Networking), Thessaloniki, Greece.","key":"ref_31","DOI":"10.23919\/IFIPNetworking62109.2024.10619798"},{"doi-asserted-by":"crossref","unstructured":"Li, J., Wang, F., Yao, H., Tian, F., Yin, X., and Zhang, Q. (2023, January 19\u201323). Topology-Aware-based Traffic Prediction Mechanism for Elastic Cognitive Optical Networks. Proceedings of the 2023 International Wireless Communications and Mobile Computing (IWCMC), Marrakesh, Morocco.","key":"ref_32","DOI":"10.1109\/IWCMC58020.2023.10182513"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4155","DOI":"10.1109\/JLT.2019.2923615","article-title":"DeepRMSA: A Deep Reinforcement Learning Framework for Routing, Modulation and Spectrum Assignment in Elastic Optical Networks","volume":"37","author":"Chen","year":"2019","journal-title":"J. Light. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1364\/JOCN.440590","article-title":"Efficiency and Fairness Improvement for Elastic Optical Networks Using Reinforcement Learning-Based Traffic Prediction","volume":"14","author":"Valkanis","year":"2021","journal-title":"J. Opt. Commun. Netw."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"4741","DOI":"10.1007\/s00521-020-05532-z","article-title":"A CNN-BiLSTM-AM method for stock price prediction","volume":"33","author":"Lu","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.procs.2022.01.003","article-title":"Adaptability of financial time series prediction based on BiLSTM","volume":"199","author":"Yang","year":"2022","journal-title":"Procedia Comput. Sci."},{"doi-asserted-by":"crossref","unstructured":"Nourmohammadi, F., Jumabayev, A., and Wings, E. (2021, January 21\u201323). Anomaly Detection in the Time Series Data from Fehn Pollux Ship with ECO Flettner Rotor. Proceedings of the 2021 IEEE 19th International Conference on Industrial Informatics (INDIN), Palma de Mallorca, Spain.","key":"ref_37","DOI":"10.1109\/INDIN45523.2021.9557422"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"131223","DOI":"10.1016\/j.optcom.2024.131223","article-title":"Deep learning techniques for quality of transmission estimation in optical networks","volume":"574","author":"Sahu","year":"2025","journal-title":"Opt. Commun."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1109\/JLT.2023.3235039","article-title":"Hierarchical reinforcement learning in multi-domain elastic optical networks to realize joint RMSA","volume":"41","author":"Xu","year":"2023","journal-title":"J. Light. Technol."}],"container-title":["Network"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2673-8732\/5\/4\/44\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:50:00Z","timestamp":1760035800000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2673-8732\/5\/4\/44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,7]]},"references-count":39,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["network5040044"],"URL":"https:\/\/doi.org\/10.3390\/network5040044","relation":{},"ISSN":["2673-8732"],"issn-type":[{"type":"electronic","value":"2673-8732"}],"subject":[],"published":{"date-parts":[[2025,10,7]]}}}