Understanding the challenges of the call drop prediction problem in IP Multimedia Subsystem Networks
Resumo
Call drops in mobile networks using IMS (IP Multimedia Subsystem) technologies like Voice over LTE (VoLTE), Voice over New Radio (VoNR), and Voice over Wi-Fi (VoWiFi) present significant challenges to maintaining Quality of Service (QoS) and Quality of Experience (QoE). These failures often occur due to network congestion, weak signals, or issues related to software problems and complex situations. This study evaluates the effectiveness of machine learning models—Logistic Regression, Decision Tree, and XGBoost—in predicting call drops using a large dataset from Android devices, which had an imbalanced distribution of data. XGBoost achieved the highest overall accuracy but struggled with detecting rare call drops due to data imbalance. Although resampling techniques improved the detection of these call drops, they decreased overall accuracy, which remains a challenge. The proprietary nature of the dataset, which only provides information at the moment of disconnection, limits understanding of the entire call performance and the changes that occur during the call. Future work should focus on improving the data collection process and exploring deep learning techniques to capture complex patterns and improve prediction accuracy.
Palavras-chave:
Call Drop Classification, Supervised Learning, Mobile Network Failures
Referências
Al-Thaedan, S. et al. (2023). Downlink throughput prediction using machine learning models on 4g-lte networks. IEEE Access, 11:32345–32356.
Ashok, K. (2024). A deep auto imputation integrated bayes optimized transfer learning model with hybrid skill-levy search algorithm (dai-bots) for call drop prediction in mobile networks. Journal of Communication and Information Systems, 39:120–130.
Bahaa, A., Shehata, M., Gasser, S. M., and El-Mahallawy, M. S. (2022). Call failure prediction in ip multimedia subsystem (ims) networks. Applied Sciences, 12(16):8378.
Bertsimas, D. and Dunn, J. (2017). Optimal classification trees. Machine Learning, 106:1039–1082.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.
Daróczy, T. et al. (2015). Machine learning based session drop prediction in lte networks and its son aspects. IEEE Communications Letters, 19(5):822–825.
Drummond, C. and Holte, R. C. (2005). Severe class imbalance: Why better algorithms aren’t the answer. In European Conference on Machine Learning, pages 539–546. Springer.
Elbayoumy, A. D., Hussein, M., and Al-Ashry, S. F. (2018). Ott voip over lte vs. volte end-to-end qos using opnet. In The International Conference on Electrical Engineering, volume 11, pages 1–14. Military Technical College.
Erunkulu, O. O., Onwuka, E. N., Ugweje, O. C., and Ajao, L. A. (2019a). Prediction of call drops in gsm network using artificial neural network. Jurnal Teknologi Dan Sistem Komputer, 7:38–46.
Erunkulu, T. A. et al. (2019b). Prediction of call drops in gsm network using artificial neural network. International Journal of Mobile Network Design and Innovation, 10(3):150–160.
G V, A. and Kumari P., V. (2023). A novel chimp optimized linear kernel regression (colkr) model for call drop prediction in mobile networks. International Journal on Recent and Innovation Trends in Computing and Communication, 11:593–603.
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M. A., and Kagal, L. (2018). Explaining explanations: an overview of interpretability of machine learning. 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).
He, H. and Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21(9):1263–1284.
Holmbacka, S. (2018). Alarm prediction in lte networks. International Journal of Mobile Network Design and Innovation, 12(4):345–356.
Jiang, Y. (2024). Predicting loan default: a comparative analysis of multiple machine learning models. Highlights in Science, Engineering and Technology, 85:169–175.
Kibria, M. G., Nguyen, K., Villardi, G. P., Zhao, O., Ishizu, K., and Kojima, F. (2018). Big data analytics, machine learning, and artificial intelligence in next-generation wireless networks. IEEE Access, 6:32328–32338.
Krawczyk, B. (2016). Learning from imbalanced data: open challenges and future directions. Progress in artificial intelligence, 5(4):221–232.
Kumar, V., Lalotra, G. S., Sasikala, P., Rajput, D. S., Kaluri, R., Lakshmanna, K., Shorfuzzaman, M., Alsufyani, A., and Uddin, M. (2022). Addressing binary classification over class imbalanced clinical datasets using computationally intelligent techniques. In Healthcare, volume 10, page 1293. MDPI.
Lebedev, A., Westman, E., Van Westen, G., Kramberger, M., Lundervold, A., Aarsland, D., Soininen, H., Kłoszewska, I., Mecocci, P., Tsolaki, M., et al. (2014). Random forest ensembles for detection and prediction of alzheimer’s disease with a good between-cohort robustness. NeuroImage: Clinical, 6:115–125.
Lee, T.-H., Ullah, A., and Wang, R. (2020). Bootstrap aggregating and random forest. Macroeconomic forecasting in the era of big data: Theory and practice, pages 389–429.
Mishra, S. and Yadav, P. (2020). Mobility robustness optimization using ann for call drop prediction. IEEE Transactions on Vehicular Technology, 69(8):8345–8354.
Morales, J. L. and Nocedal, J. (2011). Remark on “algorithm 778: L-bfgs-b: Fortran subroutines for large-scale bound constrained optimization”. ACM Transactions on Mathematical Software (TOMS), 38(1):1–4.
Mudaliyar, R. et al. (2020). Machine learning based call drop healing in 5g. Journal of Communication and Information Systems, 35:145–155.
Qu, J. (2020). Temporal-spatial collaborative prediction for lte-r communication quality based on deep learning. Wireless Networks, 26:1925–1936.
Sucahyo, C. B., Rizqini, F. Q., Naufal, A., Yandratama, H., Shiddiqy, J. A., Utama, A. B. P., Putri, N. S. F., and Wibawa, A. P. (2024). Performance analysis of random forest on quartile classification journal. Applied Engineering and Technology, 3(1):1–15.
Ashok, K. (2024). A deep auto imputation integrated bayes optimized transfer learning model with hybrid skill-levy search algorithm (dai-bots) for call drop prediction in mobile networks. Journal of Communication and Information Systems, 39:120–130.
Bahaa, A., Shehata, M., Gasser, S. M., and El-Mahallawy, M. S. (2022). Call failure prediction in ip multimedia subsystem (ims) networks. Applied Sciences, 12(16):8378.
Bertsimas, D. and Dunn, J. (2017). Optimal classification trees. Machine Learning, 106:1039–1082.
Chawla, N. V., Bowyer, K. W., Hall, L. O., and Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794.
Daróczy, T. et al. (2015). Machine learning based session drop prediction in lte networks and its son aspects. IEEE Communications Letters, 19(5):822–825.
Drummond, C. and Holte, R. C. (2005). Severe class imbalance: Why better algorithms aren’t the answer. In European Conference on Machine Learning, pages 539–546. Springer.
Elbayoumy, A. D., Hussein, M., and Al-Ashry, S. F. (2018). Ott voip over lte vs. volte end-to-end qos using opnet. In The International Conference on Electrical Engineering, volume 11, pages 1–14. Military Technical College.
Erunkulu, O. O., Onwuka, E. N., Ugweje, O. C., and Ajao, L. A. (2019a). Prediction of call drops in gsm network using artificial neural network. Jurnal Teknologi Dan Sistem Komputer, 7:38–46.
Erunkulu, T. A. et al. (2019b). Prediction of call drops in gsm network using artificial neural network. International Journal of Mobile Network Design and Innovation, 10(3):150–160.
G V, A. and Kumari P., V. (2023). A novel chimp optimized linear kernel regression (colkr) model for call drop prediction in mobile networks. International Journal on Recent and Innovation Trends in Computing and Communication, 11:593–603.
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M. A., and Kagal, L. (2018). Explaining explanations: an overview of interpretability of machine learning. 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA).
He, H. and Garcia, E. A. (2009). Learning from imbalanced data. IEEE Transactions on knowledge and data engineering, 21(9):1263–1284.
Holmbacka, S. (2018). Alarm prediction in lte networks. International Journal of Mobile Network Design and Innovation, 12(4):345–356.
Jiang, Y. (2024). Predicting loan default: a comparative analysis of multiple machine learning models. Highlights in Science, Engineering and Technology, 85:169–175.
Kibria, M. G., Nguyen, K., Villardi, G. P., Zhao, O., Ishizu, K., and Kojima, F. (2018). Big data analytics, machine learning, and artificial intelligence in next-generation wireless networks. IEEE Access, 6:32328–32338.
Krawczyk, B. (2016). Learning from imbalanced data: open challenges and future directions. Progress in artificial intelligence, 5(4):221–232.
Kumar, V., Lalotra, G. S., Sasikala, P., Rajput, D. S., Kaluri, R., Lakshmanna, K., Shorfuzzaman, M., Alsufyani, A., and Uddin, M. (2022). Addressing binary classification over class imbalanced clinical datasets using computationally intelligent techniques. In Healthcare, volume 10, page 1293. MDPI.
Lebedev, A., Westman, E., Van Westen, G., Kramberger, M., Lundervold, A., Aarsland, D., Soininen, H., Kłoszewska, I., Mecocci, P., Tsolaki, M., et al. (2014). Random forest ensembles for detection and prediction of alzheimer’s disease with a good between-cohort robustness. NeuroImage: Clinical, 6:115–125.
Lee, T.-H., Ullah, A., and Wang, R. (2020). Bootstrap aggregating and random forest. Macroeconomic forecasting in the era of big data: Theory and practice, pages 389–429.
Mishra, S. and Yadav, P. (2020). Mobility robustness optimization using ann for call drop prediction. IEEE Transactions on Vehicular Technology, 69(8):8345–8354.
Morales, J. L. and Nocedal, J. (2011). Remark on “algorithm 778: L-bfgs-b: Fortran subroutines for large-scale bound constrained optimization”. ACM Transactions on Mathematical Software (TOMS), 38(1):1–4.
Mudaliyar, R. et al. (2020). Machine learning based call drop healing in 5g. Journal of Communication and Information Systems, 35:145–155.
Qu, J. (2020). Temporal-spatial collaborative prediction for lte-r communication quality based on deep learning. Wireless Networks, 26:1925–1936.
Sucahyo, C. B., Rizqini, F. Q., Naufal, A., Yandratama, H., Shiddiqy, J. A., Utama, A. B. P., Putri, N. S. F., and Wibawa, A. P. (2024). Performance analysis of random forest on quartile classification journal. Applied Engineering and Technology, 3(1):1–15.
Publicado
17/11/2024
Como Citar
MATIAS, Pedro Victor Dos Santos; MIRANDA FILHO, Ricardo; DE FREITAS, Rosiane.
Understanding the challenges of the call drop prediction problem in IP Multimedia Subsystem Networks. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 21. , 2024, Belém/PA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 263-274.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2024.245284.