Improving Cellular Traffic Prediction with Temporal Embeddings: A Time2Vec-LSTM Approach

Year 2025, Volume: 10 Issue: 2, 48 - 56, 08.09.2025

Hamidullah Riaz , Sıtkı Öztürk , Peri Güneş

https://doi.org/10.19072/ijet.1695391

Abstract

The network traffic prediction has to be reliable for better resource allocation and congestion management in present-day telecommunications. In this paper, a novel hybrid Time2Vec-enhanced LSTM method is presented for somewhat more accurate traffic volume forecasting. The model exploits both historical traffic behavior and temporal features enriched by Time2Vec, such as hour and day, to represent the linear or periodic dependencies embedded in cellular traffic. Unlike traditional static time encodings or raw time features, the learnable Time2Vec embeddings enable the model to better capture daily and hourly fluctuations in network traffic. The study carried out experiments with a real-world dataset that had been collected from an LTE base station located in Kandahar Province of Afghanistan, with hourly uplink, downlink, and total traffic volumes recorded for 30 days. Performance was measured in terms of the Root Mean Square Error (RMSE) and coefficient of determination (R2). The results show that the proposed Time2Vec-enhanced LSTM consistently outperforms Deep Learning (DL), statistical, and Machine Learning (ML) models across all traffic types. The learnable temporal embeddings are useful as they allow greater accuracy and better capture of trends. Ablation studies have supported that forecasting is far better with adaptive Time2Vec encoding than with models without or with a fixed-time feature, suggesting that learnable temporal features are essential for precise and robust cellular traffic prediction.

Keywords

Cellular traffic prediction , Deep learning (DL) , LSTM , Machine learning (ML) , Real-word dataset , Time2Vec

References

• [1] J. Xiao, Y. Cong, W. Zhang, and W. Weng, “A cellular traffic prediction method based on diffusion convolutional GRU and multi-head attention mechanism,” Cluster Computing, vol. 28, no. 2, p. 125, 2025.
• [2] H. Riaz, S. Öztürk, and A. Çalhan, “A Robust Handover Optimization Based on Velocity-Aware Fuzzy Logic in 5G Ultra-Dense Small Cell HetNets,” Electronics, vol. 13, no. 17, Art. no. 17, Jan. 2024, doi: 10.3390/electronics13173349.
• [3] H. Riaz, S. Öztürk, S. Aldirmaz-Colak, and A. Çalhan, “A Handover Decision Optimization Method Based on Data-Driven MLP in 5G Ultra-Dense Small Cell HetNets,” J Netw Syst Manage, vol. 33, no. 2, p. 31, Feb. 2025, doi: 10.1007/s10922-025-09903-6.
• [4] O. Aouedi, V. A. Le, K. Piamrat, and Y. Ji, “Deep Learning on Network Traffic Prediction: Recent Advances, Analysis, and Future Directions,” ACM Comput. Surv., vol. 57, no. 6, p. 151:1-151:37, Feb. 2025, doi: 10.1145/3703447.
• [5] X. Wang et al., “A Survey on Deep Learning for Cellular Traffic Prediction,” Intelligent Computing, vol. 3, p. 0054, Jan. 2024, doi: 10.34133/icomputing.0054.
• [6] H. Riaz, P. Güneş, H. Benli, and F. H. Ahmadzai, “A Comparative Analysis of Machine Learning Models for Cellular Load Prediction: Insights from Real-World Data,” Journal of Emerging Trends in Engineering Research, vol. 13, no. 4, pp. 73–81, 2025.
• [7] A. Azari, P. Papapetrou, S. Denic, and G. Peters, “Cellular traffic prediction and classification: A comparative evaluation of LSTM and ARIMA,” presented at the Discovery Science: 22nd International Conference, DS 2019, Split, Croatia, October 28–30, 2019, Proceedings 22, Springer, 2019, pp. 129–144.
• [8] S. Medhn, B. Seifu, A. Salem, and D. Hailemariam, “Mobile data traffic forecasting in UMTS networks based on SARIMA model: The case of Addis Ababa, Ethiopia,” presented at the 2017 IEEE AFRICON, IEEE, 2017, pp. 285–290.
• [9] X. Cao, Y. Zhong, Y. Zhou, J. Wang, C. Zhu, and W. Zhang, “Interactive Temporal Recurrent Convolution Network for Traffic Prediction in Data Centers,” IEEE Access, vol. 6, pp. 5276–5289, 2018, doi: 10.1109/ACCESS.2017.2787696.
• [10] C. Zhang, H. Zhang, J. Qiao, D. Yuan, and M. Zhang, “Deep Transfer Learning for Intelligent Cellular Traffic Prediction Based on Cross-Domain Big Data,” IEEE Journal on Selected Areas in Communications, vol. 37, no. 6, pp. 1389–1401, Jun. 2019, doi: 10.1109/JSAC.2019.2904363.
• [11] C. Gijón, M. Toril, S. Luna-Ramírez, M. L. Marí-Altozano, and J. M. Ruiz-Avilés, “Long-Term Data Traffic Forecasting for Network Dimensioning in LTE with Short Time Series,” Electronics, vol. 10, no. 10, Art. no. 10, Jan. 2021, doi: 10.3390/electronics10101151. [12] S. Jaffry and S. F. Hasan, “Cellular traffic prediction using recurrent neural networks,” presented at the 2020 IEEE 5th international symposium on telecommunication technologies (ISTT), IEEE, 2020, pp. 94–98.
• [13] H. Chekireb, L. Fergani, S. A. Selouani, M. R. Deramchi, and R. Rochedi, “Improving LTE network Retainability KPI prediction performance using LSTM and Data Filtering technique,” presented at the 2022 7th International Conference on Image and Signal Processing and their Applications (ISPA), IEEE, 2022, pp. 1–6.
• [14] W. Jiang, M. He, and W. Gu, “Internet Traffic Prediction with Distributed Multi-Agent Learning,” Applied System Innovation, vol. 5, no. 6, Art. no. 6, Dec. 2022, doi: 10.3390/asi5060121.
• [15] T. Xu and Y. Yan, “Cell base station traffic prediction based on GRU,” Comput. Perform. Commun. Syst, vol. 7, no. 1, pp. 66–72, 2023.
• [16] K. Gao et al., “Predicting Traffic Demand Matrix by Considering Inter-flow Correlations,” in IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), Jul. 2020, pp. 165–170. doi: 10.1109/INFOCOMWKSHPS50562.2020.9163001.
• [17] D. Aloraifan, I. Ahmad, and E. Alrashed, “Deep learning based network traffic matrix prediction,” International Journal of Intelligent Networks, vol. 2, pp. 46–56, Jan. 2021, doi: 10.1016/j.ijin.2021.06.002.
• [18] S. M. Kazemi et al., “Time2vec: Learning a vector representation of time,” arXiv preprint arXiv:1907.05321, 2019.
• [19] K. Zhou, C. Zhang, B. Xu, J. Huang, C. Li, and Y. Pei, “TE-LSTM: A Prediction Model for Temperature Based on Multivariate Time Series Data,” Remote Sensing, vol. 16, no. 19, Art. no. 19, Jan. 2024, doi: 10.3390/rs16193666.
• [20] H. Riaz, S. Öztürk, S. A. Çolak, and A. Çalhan, “Performance Analysis of Weighting Methods for Handover Decision in HetNets,” Gazi University Journal of Science, vol. 37, no. 4, pp. 1791–1810, Jan. 2024, doi: 10.35378/gujs.1373452.