{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:42:45Z","timestamp":1760150565102,"version":"build-2065373602"},"reference-count":27,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2023,12,10]],"date-time":"2023-12-10T00:00:00Z","timestamp":1702166400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of China","award":["U21B2003"],"award-info":[{"award-number":["U21B2003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>In light of the high bit error rate in satellite network links, the traditional transmission control protocol (TCP) fails to distinguish between congestion and wireless losses, and existing loss differentiation methods lack heterogeneous ensemble learning models, especially feature selection for loss differentiation, individual classifier selection methods, effective ensemble strategies, etc. A loss differentiation method based on heterogeneous ensemble learning (LDM-HEL) for low-Earth-orbit (LEO) satellite networks is proposed. This method utilizes the Relief and mutual information algorithms for selecting loss differentiation features and employs the least-squares support vector machine, decision tree, logistic regression, and K-nearest neighbor as individual learners. An ensemble strategy is designed using the stochastic gradient descent method to optimize the weights of individual learners. Simulation results demonstrate that the proposed LDM-HEL achieves higher accuracy rate, recall rate, and F1-score in the simulation scenario, and significantly improves throughput performance when applied to TCP. Compared with the integrated model LDM-satellite, the above indexes can be improved by 4.37%, 4.55%, 4.87%, and 9.28%, respectively.<\/jats:p>","DOI":"10.3390\/e25121642","type":"journal-article","created":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T03:25:31Z","timestamp":1702265131000},"page":"1642","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Loss Differentiation Method Based on Heterogeneous Ensemble Learning Model for Low Earth Orbit Satellite Networks"],"prefix":"10.3390","volume":"25","author":[{"given":"Debin","family":"Wei","sequence":"first","affiliation":[{"name":"Communication and Network Laboratory, College of Information Engineering, Dalian University, Dalian 116622, China"},{"name":"School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanqi","family":"Guo","sequence":"additional","affiliation":[{"name":"Communication and Network Laboratory, College of Information Engineering, Dalian University, Dalian 116622, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Automation, Nanjing University of Science and Technology, Nanjing 210094, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Xu","sequence":"additional","affiliation":[{"name":"Communication and Network Laboratory, College of Information Engineering, Dalian University, Dalian 116622, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,12,10]]},"reference":[{"key":"ref_1","first-page":"53","article-title":"The future of broadband connectivity: Terrestrial networks vs. satellite constellations","volume":"5","author":"Adinoyi","year":"2022","journal-title":"Int. J. Commun. Netw. Syst. Sci."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"3063","DOI":"10.1007\/s00521-021-06156-7","article-title":"Optimizing the end-to-end transmission scheme for hybrid satellite and multihop networks","volume":"35","author":"Zong","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/TAES.2013.6494376","article-title":"TFRC-Satellite: A TFRC variant with a loss differentiation algorithm for satellite networks","volume":"49","author":"Sun","year":"2013","journal-title":"IEEE Trans. Aerosp. Electron. Syst."},{"key":"ref_4","unstructured":"Biaz, S., and Vaidya, N.H. (1999, January 24\u201327). Discriminating congestion losses from wireless losses using inter-arrival times at the receiver. Proceedings of the 1999 IEEE Symposium on Application-Specific Systems and Software Engineering and Technology (ASSET), Richardson, TX, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1109\/TNET.2003.818187","article-title":"End-to-end differentiation of congestion and wireless losses","volume":"11","author":"Cen","year":"2003","journal-title":"IEEE ACM Trans. Netw."},{"key":"ref_6","unstructured":"Tobe, Y., Tamura, Y., Molano, A., Ghosh, S., and Tokuda, H. (2000, January 8\u201310). Achieving moderate fairness for UDP flows by path-status classification. Proceedings of the 25th Annual IEEE Conference on Local Computer Networks, Tampa, FL, USA."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Mascolo, S., Casetti, C., Gerla, M., Sanadidi, M.Y., and Wang, R. (2001, January 16\u201321). TCP westwood: Bandwidth estimation for enhanced transport over wireless links. Proceedings of the 7th Annual International Conference on Mobile Computing and Networking, Rome, Italy.","DOI":"10.1145\/381677.381704"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9692","DOI":"10.1109\/TITS.2021.3106018","article-title":"Cross-regional transmission control for satellite network-assisted vehicular ad hoc networks","volume":"23","author":"Zong","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_9","first-page":"2684","article-title":"A packet loss differentiation algorithm for 4G-LTE network","volume":"52","author":"Du","year":"2015","journal-title":"J. Comput. Res. Dev."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Cai, Y., Xiong, H., Yu, S., Chen, M., and Zhou, X. (2021, January 24\u201326). D-OLIA: The packet loss differentiation based opportunistic linked-increases algorithm for MPTCP in wireless heterogeneous network. Proceedings of the 2021 31st International Telecommunication Networks and Applications Conference (ITNAC), Sydney, Australia.","DOI":"10.1109\/ITNAC53136.2021.9652134"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"207","DOI":"10.23919\/JCC.2022.00.016","article-title":"LDM-Satellite: A new scheme for packet loss classification over LEO satellite network","volume":"19","author":"Li","year":"2022","journal-title":"China Commun."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Yan, J., Zhang, Y., and Hummel, K.A. (2022, January 2\u20135). Differentiating losses in wireless networks: A learning approach. Proceedings of the IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), New York, NY, USA.","DOI":"10.1109\/INFOCOMWKSHPS54753.2022.9798281"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1049\/ip-com:19990597","article-title":"Non-congestion packet loss detection for TCP error recovery using wireless links","volume":"146","author":"Samaraweera","year":"1999","journal-title":"IEE Proc.-Commun."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.jnca.2017.05.008","article-title":"Congestion avoidance algorithm using ARIMA(2,1,1) model-based RTT estimation and RSS in heterogeneous wired-wireless networks","volume":"93","author":"Jeyasekar","year":"2017","journal-title":"J. Netw. Comput. Appl."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1007\/s11235-011-9495-3","article-title":"RELD, RTT ECN loss differentiation to optimize the performance of transport protocols on wireless networks","volume":"52","author":"Ramadan","year":"2013","journal-title":"Telecommun. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Seddik-Ghaleb, A., Ghamri-Doudane, Y., and Senouci, S.M. (2009, January 5\u201310). TCP WELCOME: TCP variant for wireless environment, link losses, and congestion packet loss models. Proceedings of the 2009 First International Communication Systems and Networks and Workshops, Bangalore, India.","DOI":"10.1109\/COMSNETS.2009.4808863"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sarkar, N.I., Ho, P.H., Gul, S., and Zabir, S.M.S. (2022). TCP-LoRaD: A loss recovery and differentiation algorithm for improving TCP performance over MANETs in noisy channels. Electronics, 11.","DOI":"10.3390\/electronics11091479"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhao, H., Dong, Y., and Li, Y. (2009, January 22\u201325). An End-to-End loss discrimination scheme for multimedia transmission over wireless IP networks. Proceedings of the International Conference on Ad Hoc Networks, Niagara Falls, ON, Canada.","DOI":"10.1007\/978-3-642-11723-7_49"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Truchly, P., Sith, M., and Repka, R. (2019, January 21\u201322). End-to-end packet loss differentiation algorithms and their performance in heterogeneous networks. Proceedings of the 17th International Conference on Emerging eLearning Technologies and Applications, Star\u00fd Smokovec, Slovakia.","DOI":"10.1109\/ICETA48886.2019.9040082"},{"key":"ref_20","unstructured":"Liu, J., Matta, I., and Crovella, M. (2003, January 3\u20135). End-to-End inference of loss nature in a hybrid wired\/wireless environment. Proceedings of the WiOpt\u201903: Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks, Sophia Antipolis, France."},{"key":"ref_21","unstructured":"Fonseca, N., and Crovella, M. (2005, January 13\u201317). Bayesian packet loss detection for TCP. Proceedings of the IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies, Miami, FL, USA."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, Y., Lu, L., and Yu, X. (2019). Adaptive method for packet loss types in IoT: A naive Bayes distinguisher. Electronics, 8.","DOI":"10.3390\/electronics8020134"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Arif, M., Qamar, U., and Riaz, A. (2022, January 12\u201313). A machine learning-based approach for improving TCP congestion detection mechanism in IoTs. Proceedings of the International Conference on Frontiers of Information Technology, Islamabad, Pakistan.","DOI":"10.1109\/FIT57066.2022.00035"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/S1005-8885(08)60256-3","article-title":"SVM-based loss differentiation algorithm for wired-cum-wireless networks","volume":"16","author":"Deng","year":"2009","journal-title":"J. China Univ. Posts Telecommun."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Murugan, S., and Veeramanikandan, V. (2020, January 26\u201328). Performance of Packet Loss Differentiation Model by using Cuckoo Search Back-Propagation Neural Network (CSBPNN) for Mobile Ad-hoc Networks. Proceedings of the 2020 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India.","DOI":"10.1109\/ICICT48043.2020.9112555"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1937","DOI":"10.1007\/s11276-023-03254-3","article-title":"TCP-RLLD: TCP with reinforcement learning based loss differentiation for mobile ad hoc networks","volume":"29","author":"Molia","year":"2023","journal-title":"Wirel. Netw."},{"key":"ref_27","first-page":"2103","article-title":"Research advances on stochastic gradient descent algorithms","volume":"47","author":"Shi","year":"2021","journal-title":"ACTA Autom. Sin."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/12\/1642\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:36:11Z","timestamp":1760132171000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/12\/1642"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,10]]},"references-count":27,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["e25121642"],"URL":"https:\/\/doi.org\/10.3390\/e25121642","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2023,12,10]]}}}