Abstract
Next-generation wireless network aims to support low-latency, high-speed data transmission services by incorporating artificial intelligence (AI) technologies. To fulfill this promise, AI-based network traffic prediction is essential for pre-allocating resources, such as bandwidth and computing power. This can help reduce network congestion and improve the quality of service (QoS) for users. Most studies achieve future traffic prediction by exploiting deep learning and reinforcement learning, to mine spatio-temporal correlated variables. Nevertheless, the prediction results obtained only by the spatio-temporal correlated variables cannot reflect real traffic changes. This phenomenon prevents the true prediction variables from being inferred, making the prediction algorithm perform poorly. Inspired by causal science, we propose a novel network traffic prediction method based on self-supervised spatio-temporal causal discovery (SSTCD). We first introduce the Granger causal discovery algorithm to build a causal graph among prediction variables and obtain spatio-temporal causality in the observed data, which reflects the real reasons affecting traffic changes. Next, a graph neural network (GNN) is adopted to incorporate causality for traffic prediction. Furthermore, we propose a self-supervised method to implement causal discovery to to address the challenge of lacking ground-truth causal graphs in the observed data. Experimental results demonstrate the effectiveness of the SSTCD method.
Similar content being viewed by others
References
Siriwardhana Y, Porambage P, Liyanage M, et al. A survey on mobile augmented reality with 5G mobile edge computing: architectures, applications, and technical aspects. IEEE Commun Surv Tut, 2021, 23: 1160–1192
Du J, Yu F R, Lu G, et al. MEC-assisted immersive VR video streaming over terahertz wireless networks: a deep reinforcement learning approach. IEEE Int Things J, 2020, 7: 9517–9529
Liberatore M J, Wagner W P. Virtual, mixed, and augmented reality: a systematic review for immersive systems research. Virtual Reality, 2021, 25: 773–799
Fang T, Yuan F, Ao L, et al. Joint task offloading, D2D pairing, and resource allocation in device-enhanced MEC: a potential game approach. IEEE Int Things J, 2022, 9: 3226–3237
Portilla-Figueras A, Llopis-Sánchez S, Jiménez-Fernández S, et al. Examining 5G technology-based applications for military communications. In: Proceedings of the European Symposium on Research in Computer Security, 2022. 449–465
Chu P, Zhang J A, Wang X X, et al. Semi-persistent V2X resource allocation with traffic prediction in two-tier cellular networks. In: Proceedings of the 89th Vehicular Technology Conference (VTC2019-Spring), 2019. 1–6
Zhou X, Zhang Y, Li Z, et al. Large-scale cellular traffic prediction based on graph convolutional networks with transfer learning. Neural Comput Appl, 2022, 34: 5549–5559
Zheng T H, Li B C. Poisoning attacks on deep learning based wireless traffic prediction. In: Proceedings of the IEEE Conference on Computer Communications, 2022. 660–669
Wang Y Q, Jiang D D, Huo L W, et al. A new traffic prediction algorithm to software defined networking. Mobile Netw Appl, 2021, 26: 716–725
Nie L S, Ning Z L, Obaidat M S, et al. A reinforcement learning-based network traffic prediction mechanism in intelligent internet of things. IEEE Trans Ind Inf, 2021, 17: 2169–2180
Li M, Wang Y W, Wang Z W, et al. A deep learning method based on an attention mechanism for wireless network traffic prediction. Ad Hoc Netw, 2020, 107: 102258
Xu H Y, Huang Y D, Duan Z H, et al. Multivariate time series forecasting based on causal inference with transfer entropy and graph neural network. 2020. ArXiv:2005.01185
Pearl J. Causal inference. In: Proceedings of Workshop on Causality: Objectives and Assessment at NIPS, 2010. 39–58
Nogueira A R, Pugnana A, Ruggieri S, et al. Methods and tools for causal discovery and causal inference. WIREs Data Min Knowl, 2022, 12
Granger C W. Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 1969, 37: 424–438
Box G E, Jenkins G M, Reinsel G C, et al. Time Series Analysis: Forecasting and Control. Hoboken: John Wiley & Sons, 2015
Zivot E, Wang J H. Vector autoregressive models for multivariate time series. In: Modeling Financial Time Series with S-PLUS®. Berlin: Springer, 2006. 385–429
Wang J, Tang J, Xu Z Y, et al. Spatiotemporal modeling and prediction in cellular networks: a big data enabled deep learning approach. In: Proceedings of the IEEE Conference on Computer Communications, 2017. 1–9
Li Z Y, Fu Y C, Zhao P C, et al. A dynamic spatiotemporal prediction method for urban network traffic. In: Proceedings of the 96th Vehicular Technology Conference (VTC2022-Fall), 2022. 1–5
Wang K, Li K L, Zhou L Q, et al. Multiple convolutional neural networks for multivariate time series prediction. Neurocomputing, 2019, 360: 107–119
Zhang C T, Zhang H X, Qiao J P, et al. Deep transfer learning for intelligent cellular traffic prediction based on cross-domain big data. IEEE J Sel Areas Commun, 2019, 37: 1389–1401
Zhang C T, Dang S P, Shihada B, et al. Dual attention-based federated learning for wireless traffic prediction. In: Proceedings of the IEEE Conference on Computer Communications, 2021. 1–10
Cheng L, Guo R C, Moraffah R, et al. Evaluation methods and measures for causal learning algorithms. IEEE Trans Artif Intell, 2022, 3: 924–943
Luo Y N, Peng J, Ma J Z. When causal inference meets deep learning. Nat Mach Intell, 2020, 2: 426–427
Nauta M, Bucur D, Seifert C. Causal discovery with attention-based convolutional neural networks. MAKE, 2019, 1: 312–340
Löwe S, Madras D, Zemel R, et al. Amortized causal discovery: learning to infer causal graphs from time-series data. In: Proceedings of the Conference on Causal Learning and Reasoning, 2022. 509–525
Wang Y X, Cao F Y, Yu K, et al. Local causal discovery in multiple manipulated datasets. IEEE Trans Neural Netw Learn Syst, 2023, 34: 7235–7247
Monti R P, Zhang K, Hyvärinen A. Causal discovery with general non-linear relationships using non-linear ICA. In: Proceedings of the Uncertainty in Artificial Intelligence, 2020. 186–195
Yu L X, Li M, Jin W Q, et al. STEP: a spatio-temporal fine-granular user traffic prediction system for cellular networks. IEEE Trans Mobile Comput, 2021, 20: 3453–3466
Tank A, Covert I, Foti N, et al. Neural Granger causality. IEEE Trans Pattern Anal Mach Intell, 2022, 44: 4267–279
Barlacchi G, De Nadai M, Larcher R, et al. A multi-source dataset of urban life in the city of Milan and the Province of Trentino. Sci Data, 2015, 2: 150055
Sun H Y, Liu H X, Xiao H, et al. Short term traffic forecasting using the local linear regression model. SN Appl Sci, 2002, 2: 1159
Sapankevych N, Sankar R. Time series prediction using support vector machines: a survey. IEEE Comput Intell Mag, 2009, 4: 24–38
Qiu C, Zhang Y Y, Feng Z Y, et al. Spatio-temporal wireless traffic prediction with recurrent neural network. IEEE Wireless Commun Lett, 2018, 7: 554–557
Wang X, Zhao J, Zhu L, et al. Adaptive multi-receptive field spatial-temporal graph convolutional network for traffic forecasting. In: Proceedings of the IEEE Global Communications Conference (GLOBECOM), 2021. 1–7
Yao Y, Gu B, Su Z, et al. MVSTGN: a multi-view spatial-temporal graph network for cellular traffic prediction. IEEE Trans Mobile Comput, 2023, 22: 2837–2849
Acknowledgements
This work was supported by Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy (Grant No. GML-KF-22-01), National Natural Science Foundation of China (Grant Nos. 62201419, 62372357), Key Research and Development Program of Shaanxi (Grant No. 2022ZDLGY05-08), and ISN State Key Laboratory.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, D., Liu, Y. & Song, B. A credible traffic prediction method based on self-supervised causal discovery. Sci. China Inf. Sci. 67, 152303 (2024). https://doi.org/10.1007/s11432-023-3899-1
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11432-023-3899-1