Using LSTM Network for Predicting Radio Mobile Networks’ Behaviors
Sử dụng mạng LSTM để dự báo hành vi mạng thông tin vô tuyến di động
Abstract
Breakthroughs in artificial intelligence, machine learning and deep learning with great recent achievements have been strongly impacting the mobile communication industry. The traditional method of mobile network management and operation has been shifting toward automation and proactive monitoring. Forecasting radio mobile networks’ behaviors in coexisting multi-layer technology mobile networks for improving resource allocation efficiency and optimizing network’s key performance indicators becomes a critical task. The use of a Long-Short Term Memory (LSTM) network for predicting radio networks’ behaviors based on real statistical data from operational support systems is suggested in this research. The promising results show the potential of our approach. The prediction results can help mobile network operators leverage networks’ operating performance.
References
Yang Jin, Miguel Dajer, AI-enabled Mobile Networks, Huawei ICT, China (2019)
Ericsson Page, https://www.ericsson.com/en/reports-and-papers/white-papers/artificial-intelligence-in-next-generation-connected-systems. Last accessed 4 Jan 2023
I. Ahmad et al, "Machine Learning Meets Communication Networks: Current Trends and Future Challenges", IEEE Access ,8, 223418–223460 (2020)
C. Casetti, "The 5G Ecosystem Forges Ahead as Remote Services Take Center Stage [Mobile Radio].", IEEE Vehicular Technology Magazine, 16(1), 7–13 (2021)
A. F. M. Shahen Shah, "A Survey From 1G to 5G Including the Advent of 6G: Architectures, Multiple Access
Techniques, and Emerging Technologies", 2022 IEEE 12th Annual Computing and Communication Workshop and Conference (CCWC), pp. 1117–1123. IEEE, USA (2022)
Qualcomm Page, https://www.qualcomm.com/media/documents/files/whitepaper-making-5g-nr-a-reality.pdf.
Last accessed 10 Dec 2022
Cuong Pham-Quoc, Tuan Tang-Anh, "Predicting mobile network’s behaviors using Linear Neural Networks",2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), pp. 75–79. IEEE, Vietnam (2021)
J. Huang, E. Kurniawan and S. Sun, "Cellular KPI Anomaly Detection with GAN and Time Series Decomposition," ICC 2022 - IEEE International Conference on Communications, Seoul, Korea, Republic of, 2022, pp. 4074-4079, doi: 10.1109/ICC45855.2022.9838810.
S. Maruyama, Y. Nishikawa, T. Onishi and E. Takahashi, "Identifying Root Cause of 5G Radio Quality Deterioration Using Machine Learning," 2022 23rd Asia-Pacific Network Operations and Management Symposium (APNOMS), Takamatsu, Japan, 2022, pp. 1-6, doi: 10.23919/APNOMS56106.2022.9919922.
Ralf Kreher, Karsten Gaenger, LTE Signaling: Troubleshooting and Performance Measurement,. 2nd ed, IEEE-Wiley Telecom, USA (2015)
B. Nath Saha, A. Senapati, "Long Short Term Memory (LSTM) based Deep Learning for Sentiment Analysis of English and Spanish Data",2020 International Conference on Computational Performance Evaluation (ComPE), pp.442–446. IEEE, India (2020)
Diederik Kingma, P. Jimmy Lei Ba, "Adam: A Method for Stochastic Optimization", ICLR Conference, pp. 1–13. USA (2015)
Yixiang Wang, Jiqiang Liu, Jelena Misic, Vojislav Misic, B. Shaohua Lv, Xiaolin Chang, "Accessing Optimizer Impact on DNN Model Sensitivity to Adversarial Examples", IEEE Access ,7, 152766–152776 (2019)
H. Ide, T. Kurita, "Improvement of learning for CNN with ReLU activation by sparse regularization", In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2684–2691. IEEE, USA (2017)
Andrew Ng, Machine Learning Yearning: Technical Strategy for AI Engineers In the Era of Deep Learning, Deep Learning AI, USA (2018)
Amit Sharma, "Nokia Get Together NetAct ML demos", Conference on Mobile Network Optimization, USA (2017)
Tomovic, S., Pejanovic-Djurisic, M., Radusinovic, I, "SDN Based Mobile Networks: Concepts and Benefits", Wireless Pers Commun, 77(4), 1629–1644 (2014)
C. Pham-Quoc, H. Nguyen-Le, C. Tang-Tan, T. Tang-Anh, "Reinforcing mobile network planning with forecasted input data obtained by a machine learning approach", 2020 IEEE Eighth International Conference on Communications and Electronics (ICCE), pp. 561–565. IEEE, Vietnam (2021)