A TSENet Model for Predicting Cellular Network Traffic
Abstract
:1. Introduction
2. Related Work
2.1. Wireless Sensor Networks
2.2. Network Traffic Prediction
2.3. Transformer
3. Method
3.1. The Proposed TSENet Framework
3.2. Spatial-Sequence Module
- (1)
- Grid arrangement: We sort each grid according to its correlation with other grids and select the top L largest grids. The value of L can be chosen based on experimental results. We employ the Pearson correlation coefficient to assess the correlation. The correlation between two grids A and B with equal traffic sequence lengths is calculated by the covariance of the variables and the product of their standard deviations:We concatenate the incoming data and outgoing data to form a matrix of dimensions . Subsequently, the correlation matrix is computed according to Equation. signifies the relevance between the i and j grids at the t interval.
- (2)
- Spatial sequence: As illustrated in Figure 2, the source sequence and the initial sequence serve as the principal inputs to the essential transformer. In natural language processing (NLP), the elements of the sequence involve more informative word embeddings, but the array of cellular traffic data results in the scarcity of information. We choose the two complementary input arrays to ensure the predictive performance of the transformer. The proximity matrix signifies the cellular communication states close to the target interval. The designed by encompasses real-time spatial features for the sequence with a length of L, serving as the source array, and is taken as the initial array with a length of 1, yielding the output of the SSM, . We omit positional encoding because there is no chronological order between spatial networks.
3.3. Time-Sequence Module
- (1)
- Closeness sequence: To harness additional information from the input data, is extended as the source sequence of the proximity sequence. During the enhancement procedure, we use the correlation matrix to select the topmost U correlated networks for each grid. We combine the selected data and the grid data and create a scalar with dimension , where U is a parameter determined through experimentation. This process enhances both the temporal features within the sequence elements and introduces a few space information in the original sequence, thereby enhancing the accuracy of predictions.In the closeness sequence, the averaging of the second dimension of yields an initial sequence of dimensions . We employ these averaged historical data as indicators for the traffic data levels in future time intervals. The closeness sequence produces the proximity time prediction, denoted as .
- (2)
- Periodic sequence: The periodic sequence is akin to the proximity sequence but lacks critical information. We employ as the original sequence, with serving as the initial sequence for the temporal sequence, thereby utilizing the compact time information included in to complement the period sequence. The outcome of the periodic time prediction is expressed as .
3.4. External-Factor Module
3.5. Fusion Output Module
4. Experiment
4.1. Dataset and Experimental Settings
4.2. Inner Parameters of Transformers
4.3. Analysis of Useful Temporal Features
4.4. Analysis of Useful Spatial Features
4.5. Experiment Analysis
4.6. Validation of Key Components
- (1)
- Augmentation of data: When setting Q to zero, it is equivalent to omitting data augmentation from the TSM. As discerned from Figure 5, the augmentation of data enhanced the predictive outcomes, with the minimum value of MAE observed when Q was set to 15.
- (2)
- Grid selection: Setting K to one is comparable to removing grid selection from the set-top box. As evidenced in Figure 5, grid selection markedly enhanced predictive performance. Optimal performance was achieved when selecting 20 grids.
- (3)
- Spatial features in the SSM: In order to substantiate the significance of extracting spatial features, we conducted experiments solely utilizing the TSM. The outcomes of TSENet (TSM only) presented in Table 4 underscore the efficacy of capturing spatial relationships. Additionally, we utilized a graph convolutional network (GCN) [33] in lieu of the SSM to represent spatial features in TSENet, assessing the spatial modeling efficacy of the SSM through experiments. The results in Table 4 demonstrate that incorporating the SSM yielded better performance compared to a GCN, enhancing the overall model performance.
- (4)
- Temporal fusion with the SSM: We also trained TSENet (without SSM fusion), where SSM was excluded from TSM. As illustrated in Table 4, TSENet (excluding SSM fusion) demonstrated superior performance in anomalous scenarios, confirming the spatial transformer’s effectiveness in capturing real-time spatial dependence.
Methods | MAE | NRMSE | |
---|---|---|---|
TSENet (TSM only) | 10.3499 | 0.54258 | 0.82695 |
TSENet (with GCN) | 10.9125 | 0.57528 | 0.80473 |
TSENet (w/o SSM in fusion) | 9.9268 | 0.53369 | 0.83329 |
TSENet | 9.758 | 0.51858 | 0.84302 |
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Orfanus, D.; Eliassen, F.; de Freitas, E.P. Self-organizing relay network supporting remotely deployed sensor nodes in military operations. In Proceedings of the 2014 6th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT), St. Petersburg, Russia, 6–8 October 2014; pp. 326–333. [Google Scholar]
- Giménez, P.; Molina, B.; Calvo-Gallego, J.; Esteve, M.; Palau, C.E. I3WSN: Industrial intelligent wireless sensor networks for indoor environments. Comput. Ind. 2014, 65, 187–199. [Google Scholar] [CrossRef]
- Li, X.; Li, D.; Wan, J.; Vasilakos, A.V.; Lai, C.F.; Wang, S. A review of industrial wireless networks in the context of Industry 4.0. Wirel. Netw. 2017, 23, 23–41. [Google Scholar] [CrossRef]
- Gomes, R.D.; Queiroz, D.V.; Lima Filho, A.C.; Fonseca, I.E.; Alencar, M.S. Real-time link quality estimation for industrial wireless sensor networks using dedicated nodes. Hoc Netw. 2017, 59, 116–133. [Google Scholar] [CrossRef]
- Yu, L.; Li, M.; Jin, W.; Guo, Y.; Wang, Q.; Yan, F.; Li, P. STEP: A spatio-temporal fine-granular user traffic prediction system for cellular networks. IEEE Trans. Mob. Comput. 2020, 20, 3453–3466. [Google Scholar] [CrossRef]
- Santos, G.L.; Rosati, P.; Lynn, T.; Kelner, J.; Sadok, D.; Endo, P.T. Predicting short-term mobile Internet traffic from Internet activity using recurrent neural networks. Int. J. Netw. Manag. 2022, 32, e2191. [Google Scholar] [CrossRef]
- Hardegen, C.; Pfülb, B.; Rieger, S.; Gepperth, A. Predicting network flow characteristics using deep learning and real-world network traffic. IEEE Trans. Netw. Serv. Manag. 2020, 17, 2662–2676. [Google Scholar] [CrossRef]
- Dodan, M.; Vien, Q.; Nguyen, T. Internet traffic prediction using recurrent neural networks. Eai Endorsed Trans. Ind. Netw. Intell. Syst. 2022, 9. [Google Scholar] [CrossRef]
- Mozo, A.; Ordozgoiti, B.; Gomez-Canaval, S. Forecasting short-term data center network traffic load with convolutional neural networks. PLoS ONE 2018, 13, e0191939. [Google Scholar] [CrossRef] [PubMed]
- Dalgkitsis, A.; Louta, M.; Karetsos, G.T. Traffic forecasting in cellular networks using the LSTM RNN. In Proceedings of the 22nd Pan-Hellenic Conference on Informatics, Athens, Greece, 29 November–1 December 2018; pp. 28–33. [Google Scholar]
- Wang, H.; Ding, J.; Li, Y.; Hui, P.; Yuan, J.; Jin, D. Characterizing the spatio-temporal inhomogeneity of mobile traffic in large-scale cellular data networks. In Proceedings of the 7th International Workshop on Hot Topics in Planet-scale mObile computing and online Social neTworking, Hangzhou, China, 22 June 2015; pp. 19–24. [Google Scholar]
- Zhao, N.; Ye, Z.; Pei, Y.; Liang, Y.C.; Niyato, D. Spatial-temporal attention-convolution network for citywide cellular traffic prediction. IEEE Commun. Lett. 2020, 24, 2532–2536. [Google Scholar] [CrossRef]
- Zhang, C.; Zhang, H.; Yuan, D.; Zhang, M. Citywide cellular traffic prediction based on densely connected convolutional neural networks. IEEE Commun. Lett. 2018, 22, 1656–1659. [Google Scholar] [CrossRef]
- Buratti, C.; Conti, A.; Dardari, D.; Verdone, R. An overview on wireless sensor networks technology and evolution. Sensors 2009, 9, 6869–6896. [Google Scholar] [CrossRef]
- Lin, C.Y.; Tseng, Y.C.; Lai, T.H. Message-efficient in-network location management in a multi-sink wireless sensor network. In Proceedings of the IEEE International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing (SUTC’06), Taichung, Taiwan, 5–7 June 2006; Volume 1, pp. 496–506. [Google Scholar]
- Krishnasamy, L.; Dhanaraj, R.K.; Ganesh Gopal, D.; Reddy Gadekallu, T.; Aboudaif, M.K.; Abouel Nasr, E. A heuristic angular clustering framework for secured statistical data aggregation in sensor networks. Sensors 2020, 20, 4937. [Google Scholar] [CrossRef]
- Wang, L.N.; Zang, C.R.; Cheng, Y.Y. The short-term prediction of the mobile communication traffic based on the product seasonal model. SN Appl. Sci. 2020, 2, 1–9. [Google Scholar] [CrossRef]
- Brügner, H. Holt-Winters Traffic Prediction on Aggregated Flow Data. Future Internet (FI) Innov. Internet Technol. Mob. Commun. (IITM) Focal Top. Adv. Persistent Threat. 2017, 25, 25–32. [Google Scholar]
- Kim, M. Network traffic prediction based on INGARCH model. Wirel. Netw. 2020, 26, 6189–6202. [Google Scholar] [CrossRef]
- Cai, Y.; Cheng, P.; Ding, M.; Chen, Y.; Li, Y.; Vucetic, B. Spatiotemporal Gaussian process Kalman filter for mobile traffic prediction. In Proceedings of the 2020 IEEE 31st Annual International Symposium on Personal, Indoor and Mobile Radio Communications, London, UK, 31 August–3 September 2020; pp. 1–6. [Google Scholar]
- Xia, H.; Wei, X.; Gao, Y.; Lv, H. Traffic prediction based on ensemble machine learning strategies with bagging and lightgbm. In Proceedings of the 2019 IEEE International Conference on Communications Workshops (ICC Workshops), Shanghai, China, 20–24 May 2019; pp. 1–6. [Google Scholar]
- Zhang, Q.; Mozaffari, M.; Saad, W.; Bennis, M.; Debbah, M. Machine learning for predictive on-demand deployment of UAVs for wireless communications. In Proceedings of the 2018 IEEE Global Communications Conference (GLOBECOM), Abu Dhabi, United Arab Emirates, 9–13 December 2018; pp. 1–6. [Google Scholar]
- Boutaba, R.; Salahuddin, M.A.; Limam, N.; Ayoubi, S.; Shahriar, N.; Estrada-Solano, F.; Caicedo, O.M. A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities. J. Internet Serv. Appl. 2018, 9, 16. [Google Scholar] [CrossRef]
- Lohrasbinasab, I.; Shahraki, A.; Taherkordi, A.; Delia Jurcut, A. From statistical-to machine learning-based network traffic prediction. Trans. Emerg. Telecommun. Technol. 2022, 33, e4394. [Google Scholar] [CrossRef]
- Owens, F.J.; Lynn, P.A. Signal Processing of Speech, Macmillan New Electronics; Palgrave Macmillan: London, UK, 1993. [Google Scholar]
- Baxevanis, A.; Bader, G.; Wishart, D. Bioinformatics; John Wiley & Sons: Hoboken, NJ, USA, 2020. [Google Scholar]
- Wen, Y.; Xu, P.; Li, Z.; Xu, W.; Wang, X. RPConvformer: A novel Transformer-based deep neural networks for traffic flow prediction. Expert Syst. Appl. 2023, 218, 119587. [Google Scholar] [CrossRef]
- Zhang, C.; Patras, P. Long-term mobile traffic forecasting using deep spatio-temporal neural networks. In Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing, Los Angeles, CA, USA, 26–29 June 2018; pp. 231–240. [Google Scholar]
- Qi, W.; Yao, J.; Li, J.; Wu, W. Performer: A Resource Demand Forecasting Method for Data Centers. In Proceedings of the International Conference on Green, Pervasive, and Cloud Computing, Chengdu, China, 2–4 December 2022; Springer: Berlin/Heidelberg, Germany, 2022; pp. 204–214. [Google Scholar]
- Zhang, C.; Dang, S.; Shihada, B.; Alouini, M.S. Dual attention-based federated learning for wireless traffic prediction. In Proceedings of the IEEE INFOCOM 2021—IEEE Conference on Computer Communications, Vancouver, BC, Canada, 10–13 May 2021; pp. 1–10. [Google Scholar]
- Rao, Z.; Xu, Y.; Pan, S.; Guo, J.; Yan, Y.; Wang, Z. Cellular Traffic Prediction: A Deep Learning Method Considering Dynamic Nonlocal Spatial Correlation, Self-Attention, and Correlation of Spatiotemporal Feature Fusion. IEEE Trans. Netw. Serv. Manag. 2022, 20, 426–440. [Google Scholar] [CrossRef]
- Feng, J.; Chen, X.; Gao, R.; Zeng, M.; Li, Y. Deeptp: An end-to-end neural network for mobile cellular traffic prediction. IEEE Netw. 2018, 32, 108–115. [Google Scholar] [CrossRef]
- Kipf, T.N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907. [Google Scholar]
Transformer | d | h | Source Sequence | Initial Sequence | ||
---|---|---|---|---|---|---|
Spatial | 64 | 8 | Augmented | Average of | ||
Closeness | 256 | 8 | ||||
Period | 128 | 8 |
Combination | MAE | NRMSE | |
---|---|---|---|
(hourly) | 11.3955 | 0.55332 | 0.81508 |
(hourly) | 10.5194 | 0.57136 | 0.81226 |
10.4823 | 0.55282 | 0.81539 | |
(weekly) | 17.6349 | 0.86621 | 0.57041 |
17.6375 | 0.77772 | 0.63955 | |
17.4319 | 0.74192 | 0.67187 |
Methods | MAE | NRMSE | |
---|---|---|---|
ARIMA | 21.19 | 0.8364 | 0.3574 |
LSTM | 15.341 | 0.7613 | 0.7275 |
DenseNet | 13.243 | 0.6241 | 0.7830 |
TWACNet | 11.22 | 0.6198 | 0.8021 |
HSTNet | 10.930 | 0.5549 | 0.8295 |
STCNet | 10.898 | 0.5766 | 0.8271 |
TSENet (Ours) | 9.758 | 0.51858 | 0.84302 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, J.; Shen, L.; Fan, W. A TSENet Model for Predicting Cellular Network Traffic. Sensors 2024, 24, 1713. https://doi.org/10.3390/s24061713
Wang J, Shen L, Fan W. A TSENet Model for Predicting Cellular Network Traffic. Sensors. 2024; 24(6):1713. https://doi.org/10.3390/s24061713
Chicago/Turabian StyleWang, Jianbin, Lei Shen, and Weiming Fan. 2024. "A TSENet Model for Predicting Cellular Network Traffic" Sensors 24, no. 6: 1713. https://doi.org/10.3390/s24061713
APA StyleWang, J., Shen, L., & Fan, W. (2024). A TSENet Model for Predicting Cellular Network Traffic. Sensors, 24(6), 1713. https://doi.org/10.3390/s24061713