{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T10:09:17Z","timestamp":1778839757365,"version":"3.51.4"},"reference-count":30,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T00:00:00Z","timestamp":1777680000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computation"],"abstract":"<jats:p>Accurate short-horizon downlink throughput prediction is essential for automation in high-density 5G deployments (e.g., stadiums and events), where user load, scheduling decisions, and interference conditions change rapidly and produce highly variable user-perceived rates. This paper benchmarks lightweight regression models for per-user throughput prediction from readily available radio access network (RAN) key performance indicators (KPIs) and studies a risk-aware extension that augments point forecasts with calibrated uncertainty and an abstention (deferral) rule. Experiments use a strictly time-ordered train\/calibration\/test protocol on the Liverpool 5G High-Density Demand (L5GHDD) dataset. The target is strongly zero-inflated (about 62% of samples at 0 Mbps) and heavy-tailed, creating regimes where average-error optimization can mask rare but operationally important bursts. In the point-prediction benchmark, the best model is a tuned two-stage support vector regressor with a mean absolute error (MAE) of 0.452 Mbps, while the strongest single-stage model attains a weighted mean absolute percentage error (WMAPE) of 56.200%. For uncertainty quantification, we compare standard split conformal prediction against two input-adaptive alternatives. Constant-width split conformal attains 88.900% marginal coverage for a nominal 90% target with an average interval width of 2.288 Mbps, but width-based deferral is degenerate because all intervals have the same size. Variable-length conformal intervals preserve near-nominal coverage (91.100%) while producing informative width variation: normalized conformal reduces the average width to 1.344 Mbps, and conformalized quantile regression reduces it to 0.641 Mbps. At a deferral threshold of 1.500 Mbps, constant-width conformal defers all samples, whereas normalized conformal still acts on 61.200% of samples with selective MAE 0.219 Mbps. These results show that input-adaptive uncertainty is necessary for meaningful selective prediction in heteroscedastic 5G throughput dynamics.<\/jats:p>","DOI":"10.3390\/computation14050105","type":"journal-article","created":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T00:15:02Z","timestamp":1777853702000},"page":"105","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Risk-Aware Downlink Throughput Prediction in High-Density 5G Networks"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-7928-4787","authenticated-orcid":false,"given":"Najem N.","family":"Sirhan","sequence":"first","affiliation":[{"name":"Computer Science Department, Faculty of Information Technology, University of Petra, Amman 11196, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0002-0397-2123","authenticated-orcid":false,"given":"Riyad","family":"Alrousan","sequence":"additional","affiliation":[{"name":"Department of Design and Visual Communication, School of Architecture and Built Environment (SABE), German Jordanian University (GJU), Amman 11180, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samar","family":"Al-Saqqa","sequence":"additional","affiliation":[{"name":"Department of Data Science and Artificial Intelligence, Faculty of Science and Information Technology, Al-Zaytoonah University of Jordan, Amman 11733, Jordan"},{"name":"Department of Information Technology, King Abdullah II School for Information Technology, The University of Jordan, Amman 11942, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Faten","family":"Hamad","sequence":"additional","affiliation":[{"name":"Information Studies Department, Sultan Qaboos University, Muscat 123, Oman"},{"name":"Information Science and Educational Technology Department, School of Educational Sciences, The University of Jordan, Amman 11942, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0000-2013-6923","authenticated-orcid":false,"given":"Zaid","family":"Khrisat","sequence":"additional","affiliation":[{"name":"Faculty of Arts and Educational Sciences, Middle East University, Amman 11831, Jordan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1065","DOI":"10.1109\/JSAC.2014.2328098","article-title":"What Will 5G Be?","volume":"32","author":"Andrews","year":"2014","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_2","unstructured":"Dahlman, E., Parkvall, S., and Sk\u00f6ld, J. (2018). 5G NR: The Next Generation Wireless Access Technology, Academic Press."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.comcom.2022.05.009","article-title":"A QoS-Aware and Channel-Aware Radio Resource Management Framework for Multi-Numerology Systems","volume":"191","author":"Miuccio","year":"2022","journal-title":"Comput. Commun."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2522","DOI":"10.1109\/COMST.2016.2571730","article-title":"Ultra-Dense Networks: A Survey","volume":"18","author":"Kamel","year":"2016","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Mohebi, S., Michelinakis, F., Elmokashfi, A., Gr\u00f8ndalen, O., Mahmood, K., and Zanella, A. (2021). Sectors, Beams and Environmental Impact on the Performance of Commercial 5G mmWave Cells: An Empirical Study. arXiv, Available online: https:\/\/2.zoppoz.workers.dev:443\/http\/arxiv.org\/abs\/2104.06188.","DOI":"10.1109\/ACCESS.2022.3229588"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Narayanan, A., Ramadan, E., Mehta, R., Hu, X., Liu, Q., Fezeu, R.A., Dayalan, U.K., Verma, S., Ji, P., and Li, T. (2020). Lumos5G: Mapping and Predicting Commercial mmWave 5G Throughput. IMC \u201920: Proceedings of the ACM Internet Measurement Conference, Association for Computing Machinery.","DOI":"10.1145\/3419394.3423629"},{"key":"ref_7","first-page":"1825","article-title":"Throughput Prediction Using Machine Learning in LTE and 5G Networks","volume":"22","author":"Minovski","year":"2023","journal-title":"IEEE Trans. Mob. Comput."},{"key":"ref_8","first-page":"651","article-title":"A Machine Learning Framework for Predicting Downlink Throughput in 4G-LTE\/5G Cellular Networks","volume":"16","author":"Shakir","year":"2024","journal-title":"Int. J. Inf. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhohov, R., Palaios, A., and Geuer, P. (2021). One Step Further: Tunable and Explainable Throughput Prediction Based on Large-Scale Commercial Networks. Proceedings of the 2021 IEEE 4th 5G World Forum (5GWF), IEEE.","DOI":"10.1109\/5GWF52925.2021.00082"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Biernacki, A. (2024). Throughput Prediction of 5G Network Based on Trace Similarity for Adaptive Video. Appl. Sci., 14.","DOI":"10.3390\/app14051962"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103588","DOI":"10.1016\/j.asej.2025.103588","article-title":"Accurate User Experience Estimation Through Real-Time Throughput Prediction with Machine Learning","volume":"16","author":"Eldeeb","year":"2025","journal-title":"Ain Shams Eng. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.2307\/1913643","article-title":"Regression Quantiles","volume":"46","author":"Koenker","year":"1978","journal-title":"Econometrica"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1443","DOI":"10.1016\/S0378-4266(02)00271-6","article-title":"Conditional Value-at-Risk for General Loss Distributions","volume":"26","author":"Rockafellar","year":"2002","journal-title":"J. Bank. Financ."},{"key":"ref_14","unstructured":"Duan, T., Avati, A., Ding, D.Y., Thai, K.K., Basu, S., Ng, A.Y., and Schuler, A. (2020). NGBoost: Natural Gradient Boosting for Probabilistic Prediction. Proceedings of the 37th International Conference on Machine Learning, PMLR. Proceedings of Machine Learning Research."},{"key":"ref_15","first-page":"1050","article-title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","volume":"Volume 48","author":"Gal","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"ref_16","unstructured":"Lakshminarayanan, B., Pritzel, A., and Blundell, C. (2017). Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"28","DOI":"10.14445\/23488549\/IJECE-V11I11P104","article-title":"Leveraging machine learning for predictive pathways in higher education: A case study at Al-Zaytoonah University of Jordan","volume":"11","author":"Muhairat","year":"2024","journal-title":"Int. J. Electron. Commun. Eng."},{"key":"ref_18","unstructured":"Albert-Smet, J., Frias, Z., Mendo, L., Melones, S., and Yraola, E. (2025). Characterizing 5G User Throughput via Uncertainty Modeling and Crowdsourced Measurements. arXiv."},{"key":"ref_19","unstructured":"Bui, N., Michelinakis, F., and Widmer, J. (2014). A Model for Throughput Prediction for Mobile Users. Proceedings of the 20th European Wireless Conference, VDE."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Liu, Y., and Lee, J.Y.B. (2015). An Empirical Study of Throughput Prediction in Mobile Data Networks. Proceedings of the IEEE Global Communications Conference (GLOBECOM), IEEE.","DOI":"10.1109\/GLOCOM.2015.7417858"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Samba, A., Busnel, Y., Blanc, A., Dooze, P., and Simon, G. (2017). Instantaneous Throughput Prediction in Cellular Networks: Which Information Is Needed?. Proceedings of the IFIP\/IEEE Symposium on Integrated Network and Service Management (IM), IEEE.","DOI":"10.23919\/INM.2017.7987345"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Sirhan, N.N., and Martinez-Ramon, M. (2022). Cognitive Radio Resource Scheduling Using Multi-Agent Q-Learning for LTE. arXiv, Available online: https:\/\/2.zoppoz.workers.dev:443\/https\/arxiv.org\/abs\/2205.02765.","DOI":"10.31219\/osf.io\/d3fkt"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Raca, D., Zahran, A.H., Sreenan, C.J., Sinha, R.K., Halepovic, E., Jana, R., Gopalakrishnan, V., Bathula, B., and Varvello, M. (2019). Empowering Video Players in Cellular: Throughput Prediction from Radio Network Measurements. Proceedings of the 10th ACM Multimedia Systems Conference, Association for Computing Machinery.","DOI":"10.1145\/3304109.3306233"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/MCOM.001.1900394","article-title":"On Leveraging Machine and Deep Learning for Throughput Prediction in Cellular Networks: Design, Performance, and Challenges","volume":"58","author":"Raca","year":"2020","journal-title":"IEEE Commun. Mag."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"7089","DOI":"10.1109\/TVT.2023.3339649","article-title":"A Kalman Filter Based Low Complexity Throughput Prediction Algorithm for 5G Cellular Networks","volume":"73","author":"Biswas","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Nolan, K., Raca, D., Provan, G., and Zahran, A. (2024). MATURE: Multistage Throughput Prediction for Adaptive Video Streaming in Cellular Networks. Proceedings of the 34th Workshop on Network and Operating System Support for Digital Audio and Video, 2024, NOSSDAV \u201924, Association for Computing Machinery.","DOI":"10.1145\/3651863.3651878"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1109\/TMLCN.2023.3319282","article-title":"Calibrating AI Models for Wireless Communications via Conformal Prediction","volume":"1","author":"Cohen","year":"2023","journal-title":"IEEE Trans. Mach. Learn. Commun. Netw."},{"key":"ref_28","unstructured":"Romano, Y., Patterson, E., and Cand\u00e8s, E.J. (2019). Conformalized Quantile Regression. Proceedings of the Advances in Neural Information Processing Systems, Curran Associates Inc."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"01006","DOI":"10.1051\/matecconf\/202541101006","article-title":"Optimizing a Star-Octagonal Microstrip Patch Antenna for 5G: Design and CST Simulation Approach","volume":"411","author":"Bashayreh","year":"2025","journal-title":"MATEC Web Conf."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jaradat, Y., Jannoud, I., Masoud, M., and Elhaija, W.A. (2017). A roadmap for SDN-based network management: Al-Zaytoonah University of Jordan case. Proceedings of the 2017 18th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA), Monastir, Tunisia, 21\u201323 December 2017, IEEE.","DOI":"10.1109\/STA.2017.8314900"}],"container-title":["Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.mdpi.com\/2079-3197\/14\/5\/105\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T09:24:55Z","timestamp":1778837095000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.mdpi.com\/2079-3197\/14\/5\/105"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,2]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["computation14050105"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.3390\/computation14050105","relation":{},"ISSN":["2079-3197"],"issn-type":[{"value":"2079-3197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,2]]}}}