Algoritmos supervisados para la predicción de fallos en la red LAN de la UPSE
DOI:
https://doi.org/10.26423/03cdzf27Palabras clave:
Aprendizaje automático, análisis predictivo, Gestión de redes, Redes universitarias, SNMPResumen
En redes universitarias como la de la Universidad Estatal Península de Santa Elena, la gestión LAN sigue siendo reactiva, sin historial ni alertas tempranas. Este estudio propone aplicar algoritmos supervisados de aprendizaje automático, seleccionados con base en evidencia científica, para construir y evaluar un modelo predictivo de fallos a partir de telemetría SNMP obtenida mediante Zabbix. Se utilizó una metodología combinada de Investigación en Ciencias del Diseño (DSR) y CRISP–DM, con ventanas de 60 minutos sobre 7571 ejemplos (729 fallos y 6 842 normales). Se compararon dos modelos: Random Forest, entrenado con características estadísticas, y una red neuronal convolucional unidimensional, aplicada sobre secuencias multivariadas. Random Forest alcanzó una exactitud del 96,88 %, mientras que la red neuronal logró un recall del 73,10 %. Los resultados demuestran su complementariedad y evidencian que la combinación de ambos modelos favorece una gestión proactiva de la red institucional, reduciendo los tiempos de respuesta ante incidencias.
Descargas
Referencias
1. SHIRATSUCHI, H., K. HORIUCHI y T. MATSUZAKI. Studies on development of web-based integrated learning and education support system. ICIC Express Letters, Part B: Applications [online]. 2020, vol. 11, n.° 2, pág. 197–205. Disponible en: https://doi.org/10.24507/icicelb.11.02.197.
2. DA SILVA ROCHA, É., L. DA SILVA, G.L. SANTOS, D. BEZERRA, A. MOREIRA, G. GONÇALVES, M.V. MARQUEZINI, A. MEHTA, M. WILDEMAN, J. KELNER, D. SADOK y P.T. ENDO. Aggregating data center measurements for availability analysis. Software: Practice and Experience [online]. 2021, vol. 51, n.° 5, pág. 868–892. Disponible en: https://doi.org/https://doi.org/10.1002/spe.2934. DOI: https://doi.org/10.1002/spe.2934
3. FATHIMA, A. y G.S. DEVI. Enhancing university network management and security: a real-time monitoring, visualization & cyber attack detection approach using Paessler PRTG and Sophos Firewall. International Journal of System Assurance Engineering and Management [online]. 2024. Disponible en: https://doi.org/10.1007/s13198-024-02448-y. DOI: https://doi.org/10.1007/s13198-024-02448-y
4. ALHARI, M.I. y M. LUBIS. Quality of Service (QoS) Wifi Network Study Case: Telkom University Dormitory Hall. En: 2023 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology (IAICT). 2023, pág. 345–349. Disponible en: https://doi.org/10.1109/IAICT59002.2023.10205625. DOI: https://doi.org/10.1109/IAICT59002.2023.10205625
5. ESPINEL VILLALOBOS, R.I., E. ARDILA TRIANA, H. ZARATE CEBALLOS y J.E. ORTIZ TRIVIÑO. Design and implementation of network monitoring system for campus infrastructure using software agents. Ingenieria e Investigacion [online]. 2022, vol. 42, n.° 1. Disponible en: https://doi.org/10.15446/ing.investig.v42n1.87564. DOI: https://doi.org/10.15446/ing.investig.v42n1.87564
6. SETYANTORO, D., V. AFIFAH, R.A. HASIBUAN, N. APRILIA y N.P. SARI. The Wireless Computer Network Management Security Analysis. JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) [online]. 2022, vol. 7, n.° 2, pág. 105–110. Disponible en: https://doi.org/10.33480/jitk.v7i2.2786. DOI: https://doi.org/10.33480/jitk.v7i2.2786
7. HELALI, S. Monitoring Systems and Networks. En: Systems and Network Infrastructure Integration: Design, Implementation, Safety and Supervision. Wiley, 2020, pág. 157–171. Disponible en: https://doi.org/10.1002/9781119779964.ch9. DOI: https://doi.org/10.1002/9781119779964.ch9
8. MAU, D.O. Integrated Intelligent Agent for SNMP-Based Network Management System. En: Industrial Networks and Intelligent Systems. Cham: Springer Nature Switzerland, 2023, pág. 19–33. DOI: https://doi.org/10.1007/978-3-031-47359-3_2
9. STOYKOVA, S. y N. SHAKEV. Artificial Intelligence for Management Information Systems: Opportunities, Challenges, and Future Directions. Algorithms [online]. 2023, vol. 16, n.° 8. Disponible en: https://doi.org/10.3390/a16080357. DOI: https://doi.org/10.3390/a16080357
10. MOOSA, M.A., A.K. VANGUJAR y D.P. MAHAJAN. Detection and Analysis of DDoS Attack Using a Collaborative Network Monitoring Stack. En: 16th International Conference on Security of Information and Networks, SIN 2023. 2023. Disponible en: https://doi.org/10.1109/SIN60469.2023.10474700. DOI: https://doi.org/10.1109/SIN60469.2023.10474700
11. MOHAMMED, B., M. KIRAN y B. ENDERS. NetGraf: An End-to-End Learning Network Monitoring Service. En: 2021 IEEE Workshop on Innovating the Network for Data-Intensive Science (INDIS). 2021, pág. 12–22. Disponible en: https://doi.org/10.1109/INDIS54524.2021.00007. DOI: https://doi.org/10.1109/INDIS54524.2021.00007
12. AL-NAYMAT, G., M. AL-KASASSBEH y E. AL-HAWARI. Using machine learning methods for detecting network anomalies within SNMP-MIB dataset. International Journal of Wireless and Mobile Computing [online]. 2018, vol. 15, n.° 1, pág. 67 – 76. Disponible en: https://doi.org/10.1504/IJWMC.2018.094644. DOI: https://doi.org/10.1504/IJWMC.2018.094644
13. SAYED, M.S. El, N.-A. LE-KHAC, M.A. AZER y A.D. JURCUT. A Flow-Based Anomaly Detection Approach With Feature Selection Method Against DDoS Attacks in SDNs. IEEE Transactions on Cognitive Communications and Networking [online]. 2022, vol. 8, n.° 4, pág. 1862–1880. Disponible en: https://doi.org/10.1109/TCCN.2022.3186331. DOI: https://doi.org/10.1109/TCCN.2022.3186331
14. PAES, D.S.F., C.H.V. DE MORAES y B.G. BATISTA. Analysis of supervised machine-learning techniques in computer networks attack detection. Computer Communications [online]. 2025, vol. 240, pág. 108203. Disponible en: https://doi.org/https://doi.org/10.1016/j.comcom.2025.108203. DOI: https://doi.org/10.1016/j.comcom.2025.108203
15. ZHAO, S., M. CHANDRASHEKAR, Y. LEE y D. MEDHI. Real-time network anomaly detection system using machine learning. En: 2015 11th International Conference on the Design of Reliable Communication Networks, DRCN 2015. Institute of Electrical and Electronics Engineers Inc., 2015, pág. 267–270. Disponible en: https://doi.org/10.1109/DRCN.2015.7149025. DOI: https://doi.org/10.1109/DRCN.2015.7149025
16. SAFARI, A., H. SOROURI, A. RAHIMI y A. OSHNOEI. A Systematic Review of Energy Efficiency Metrics for Optimizing Cloud Data Center Operations and Management. Electronics [online]. 2025, vol. 14, n.° 11. Disponible en: https://doi.org/10.3390/electronics14112214. DOI: https://doi.org/10.3390/electronics14112214
17. GUAN, J., J. LU y W. WANG. Research on Fault Monitoring Method of Information System Based on Machine Learning. En: 2023 IEEE 6th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE). 2023, pág. 1055–1059. Disponible en: https://doi.org/10.1109/AUTEEE60196.2023.10407966. DOI: https://doi.org/10.1109/AUTEEE60196.2023.10407966
18. AZAM, Z., Md.M. ISLAM y M.N. HUDA. Comparative Analysis of Intrusion Detection Systems and Machine Learning-Based Model Analysis Through Decision Tree. IEEE Access [online]. 2023, vol. 11, pág. 80348–80391. Disponible en: https://doi.org/10.1109/ACCESS.2023.3296444. DOI: https://doi.org/10.1109/ACCESS.2023.3296444
19. MYRZATAY, A., L. RZAYEVA, S. BANDINI, I. SHAYEA, B. SAOUD, I. ÇOLAK y K. KAYISLI. Predicting LAN switch failures: An integrated approach with DES and machine learning techniques (RF/LR/DT/SVM). Results in Engineering [online]. 2024, vol. 23, pág. 102356. Disponible en: https://doi.org/10.1016/J.RINENG.2024.102356. DOI: https://doi.org/10.1016/j.rineng.2024.102356
20. MAJUMDER, S., M.K. DEB BARMA y A. SAHA. ARP spoofing detection using machine learning classifiers: an experimental study. Knowl. Inf. Syst. [online]. 2024, vol. 67, n.° 1, pág. 727–766. Disponible en: https://doi.org/10.1007/s10115-024-02219-y. DOI: https://doi.org/10.1007/s10115-024-02219-y
21. HASSANAT, A.B., A.S. TARAWNEH, S.S. ABED, G.A. ALTARAWNEH, M. ALRASHIDI y M. ALGHAMDI. RDPVR: Random Data Partitioning with Voting Rule for Machine Learning from Class-Imbalanced Datasets. Electronics [online]. 2022, vol. 11, n.° 2. Disponible en: https://doi.org/10.3390/electronics11020228. DOI: https://doi.org/10.3390/electronics11020228
22. MISHRA, S., A. ALBARAKATI y S.K. SHARMA. Cyber Threat Intelligence for IoT Using Machine Learning. Processes [online]. 2022, vol. 10, n.° 12. Disponible en: https://doi.org/10.3390/pr10122673. DOI: https://doi.org/10.3390/pr10122673
23. KIRUTHIKA DEVI, B.S., K. ARAVINDHAN, P.S. KINI, G.A. REDDY y T. SUBBULAKSHMI. A Prediction Model for Flooded Packets in SNMP Networks. En: 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS). 2018, pág. 82–86. Disponible en: https://doi.org/10.1109/ICCONS.2018.8662972. DOI: https://doi.org/10.1109/ICCONS.2018.8662972
24. GARG, S., K. KAUR, N. KUMAR y J.J.P.C. RODRIGUES. Hybrid Deep-Learning-Based Anomaly Detection Scheme for Suspicious Flow Detection in SDN: A Social Multimedia Perspective. IEEE Transactions on Multimedia [online]. 2019, vol. 21, n.° 3, pág. 566–578. Disponible en: https://doi.org/10.1109/TMM.2019.2893549. DOI: https://doi.org/10.1109/TMM.2019.2893549
25. IZADI, S., M. AHMADI y A. RAJABZADEH. Network Traffic Classification Using Deep Learning Networks and Bayesian Data Fusion. Journal of Network and Systems Management [online]. 2022, vol. 30, n.° 2. Disponible en: https://doi.org/10.1007/s10922-021-09639-z. DOI: https://doi.org/10.1007/s10922-021-09639-z
26. NOETZOLD, D., A.G.D.M. ROSSETTO, V.R.Q. LEITHARDT y H.J. de M. COSTA. Enhancing Infrastructure Observability: Machine Learning for Proactive Monitoring and Anomaly Detection. Journal of Internet Services and Applications [online]. 2024, vol. 15, n.° 1, pág. 508–522. Disponible en: https://doi.org/10.5753/jisa.2024.4509. DOI: https://doi.org/10.5753/jisa.2024.4509
27. AHSAN, M., R. GOMES, Md.M. CHOWDHURY y K.E. NYGARD. Enhancing Machine Learning Prediction in Cybersecurity Using Dynamic Feature Selector. Journal of Cybersecurity and Privacy [online]. 2021, vol. 1, n.° 1, pág. 199–218. Disponible en: https://doi.org/10.3390/jcp1010011. DOI: https://doi.org/10.3390/jcp1010011
28. SUN, Y., H. OCHIAI y H. ESAKI. Multi-Type Anomaly Detection Based on Raw Network Traffic. En: 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). 2021, pág. 1–2. Disponible en: https://doi.org/10.1109/CCNC49032.2021.9369654. DOI: https://doi.org/10.1109/CCNC49032.2021.9369654
29. REN, L., Z. JIA, T. WANG, Y. MA y L. WANG. LM-CNN: A Cloud-Edge Collaborative Method for Adaptive Fault Diagnosis With Label Sampling Space Enlarging. IEEE Transactions on Industrial Informatics [online]. 2022, vol. 18, n.° 12, pág. 9057–9067. Disponible en: https://doi.org/10.1109/TII.2022.3180389. DOI: https://doi.org/10.1109/TII.2022.3180389
30. SURYOTRISONGKO, H., Y. MUSASHI, A. TSUNEDA y K. SUGITANI. Robust Botnet DGA Detection: Blending XAI and OSINT for Cyber Threat Intelligence Sharing. IEEE Access [online]. 2022, vol. 10, pág. 34613–34624. Disponible en: https://doi.org/10.1109/ACCESS.2022.3162588. DOI: https://doi.org/10.1109/ACCESS.2022.3162588
31. PORTELA, A.L., R.A. MENEZES, W.L. COSTA, M.M. SILVEIRA, L.F. BITTECNOURT y R.L. GOMES. Detection of IoT Devices and Network Anomalies based on Anonymized Network Traffic. En: NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium. 2023, pág. 1–6. Disponible en: https://doi.org/10.1109/NOMS56928.2023.10154276. DOI: https://doi.org/10.1109/NOMS56928.2023.10154276
32. PRIYA, S.S., M. SIVARAM, D. YUVARAJ y A. JAYANTHILADEVI. Machine Learning based DDOS Detection. En: 2020 International Conference on Emerging Smart Computing and Informatics (ESCI). 2020, pág. 234–237. Disponible en: https://doi.org/10.1109/ESCI48226.2020.9167642. DOI: https://doi.org/10.1109/ESCI48226.2020.9167642
33. MITROPOULOU, K., P. KOKKINOS, P. SOUMPLIS y E. VARVARIGOS. Anomaly Detection in Cloud Computing using Knowledge Graph Embedding and Machine Learning Mechanisms. Journal of Grid Computing [online]. 2023, vol. 22, n.° 1, pág. 6. Disponible en: https://doi.org/10.1007/s10723-023-09727-1. DOI: https://doi.org/10.1007/s10723-023-09727-1
34. FATHI-KAZEROONI, S., Y. KAYMAK y R. ROJAS-CESSA. Tracking User Application Activity by using Machine Learning Techniques on Network Traffic. En: 2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 2019, pág. 405–410. Disponible en: https://doi.org/10.1109/ICAIIC.2019.8669040. DOI: https://doi.org/10.1109/ICAIIC.2019.8669040
35. SCHUMMER, P., A. DEL RIO, J. SERRANO, D. JIMENEZ, G. SÁNCHEZ y Á. LLORENTE. Machine Learning-Based Network Anomaly Detection: Design, Implementation, and Evaluation. AI [online]. 2024, vol. 5, n.° 4, pág. 2967–2983. Disponible en: https://doi.org/10.3390/ai5040143. DOI: https://doi.org/10.3390/ai5040143
36. HOU, Y., Z. XU, L. WANG, Y. WANG y H. LI. NadGPT: Semi-Supervised Network Anomaly Detection via Auto-Regressive Auxiliary Prediction. En: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC). 2023, pág. 133–138. Disponible en: https://doi.org/10.1109/SMC53992.2023.10394639. DOI: https://doi.org/10.1109/SMC53992.2023.10394639
37. VEMULA, M.B., K.P. KUMAR, H.R.S. THIPPARTHI y P.S. JASTI. Network Anomaly Detection Using Generative Adversarial Networks. En: 2024 First International Conference on Software, Systems and Information Technology (SSITCON). 2024, pág. 1–6. Disponible en: https://doi.org/10.1109/SSITCON62437.2024.10796515. DOI: https://doi.org/10.1109/SSITCON62437.2024.10796515
38. DUY, P.T., L.K. TIEN, N.H. KHOA, D.T.T. HIEN, A.G.-T. NGUYEN y V.-H. PHAM. DIGFuPAS: Deceive IDS with GAN and function-preserving on adversarial samples in SDN-enabled networks. Computers & Security [online]. 2021, vol. 109, pág. 102367. Disponible en: https://doi.org/https://doi.org/10.1016/j.cose.2021.102367. DOI: https://doi.org/10.1016/j.cose.2021.102367
39. STEPHAN, M., J. ZERWAS y W. KELLERER. T-MAW: Online Network Traffic Monitoring and Analysis using Weighted Stochastic Block Models. En: 2024 20th International Conference on Network and Service Management (CNSM). 2024, pág. 1–9. Disponible en: https://doi.org/10.23919/CNSM62983.2024.10814420. DOI: https://doi.org/10.23919/CNSM62983.2024.10814420
40. GUO, Y., Y. WANG, F. KHAN, A.A. AL-ATAWI, A. Al ABDULWAHID, Y. LEE y B. MARAPELLI. Traffic Management in IoT Backbone Networks Using GNN and MAB with SDN Orchestration. Sensors [online]. 2023, vol. 23, n.° 16. Disponible en: https://doi.org/10.3390/s23167091. DOI: https://doi.org/10.3390/s23167091
41. CHANGO, W., P. BUÑAY, J. ERAZO, P. AGUILAR, J. SAYAGO, A. FLORES y G. SILVA. Predicting Urban Traffic Congestion with VANET Data. Computation [online]. 2025, vol. 13, n.° 4. Disponible en: https://doi.org/10.3390/computation13040092. DOI: https://doi.org/10.3390/computation13040092
42. MURPHY, K., A. LAVIGNOTTE y C. LEPERS. Fault Prediction for Heterogeneous Telecommunication Networks Using Machine Learning: A Survey. IEEE Transactions on Network and Service Management [online]. 2024, vol. 21, n.° 2, pág. 2515–2538. Disponible en: https://doi.org/10.1109/TNSM.2023.3340351. DOI: https://doi.org/10.1109/TNSM.2023.3340351
43. EDOZIE, E., A.N. SHUAIBU, B.O. SADIQ y U.K. JOHN. Artificial intelligence advances in anomaly detection for telecom networks. Artificial Intelligence Review [online]. 2025, vol. 58, n.° 4, pág. 100. Disponible en: https://doi.org/10.1007/s10462-025-11108-x. DOI: https://doi.org/10.1007/s10462-025-11108-x
Publicado
Número
Sección
Licencia
Derechos de autor 2025 Ariel Oswaldo Fernández Loor; Alicia Andrade Vera
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial-CompartirIgual 4.0.
El titular de los derechos de autor de la obra, otorga derechos de uso a los lectores mediante la licencia Creative Commons Atribución-NoComercial-CompartirIgual 4.0 Internacional. Esto permite el acceso gratuito inmediato a la obra y permite a cualquier usuario leer, descargar, copiar, distribuir, imprimir, buscar o vincular a los textos completos de los artículos, rastrearlos para su indexación, pasarlos como datos al software o usarlos para cualquier otro propósito legal.
Cuando la obra es aprobada y aceptada para su publicación, los autores conservan los derechos de autor sin restricciones, cediendo únicamente los derechos de reproducción, distribución para su explotación en formato de papel, así como en cualquier otro soporte magnético, óptico y digital.
