Machine (deep) learning enabled accurate traffic modeling and prediction is an indispensable part for future big data-driven intelligent cellular networks, since it can help autonomic network control and management as well as service provisioning. Along this line, this paper proposes a novel deep learning architecture, namely Spatial-Temporal Cross-domain neural Network (STCNet), to effectively capture the complex patterns hidden in cellular data. By adopting convolutional long short-term memory network as its subcomponent, STCNet has a strong ability in modeling spatial-temporal dependencies. Besides, three kinds of cross-domain datasets are actively collected and modeled by STCNet to capture the external factors that affect traffic generation. As diversity and similarity coexist among cellular traffic from different city functional zones, a clustering algorithm is put forward to segment city areas into different groups and consequently, a successive inter-cluster transfer learning strategy is designed to enhance knowledge reuse. In addition, the knowledge transferring among different kinds of cellular traffic is also explored with the proposed STCNet model. The effectiveness of STCNet is validated through real world cellular traffic datasets using three kinds of evaluation metrics. Experimental results demonstrate that STCNet outperforms the state-of-the-art algorithms. In particular, the transfer learning based on STCNet brings about 4%~13% extra performance improvements.

With accurate traffic prediction, future cellular networks can make self-management and embrace intelligent and efficient automation. This letter devotes itself to citywide cellular traffic prediction and propose a deep learning approach to model the nonlinear dynamics of wireless traffic. By treating traffic data as images, both the spatial and temporal dependence of cell traffic are well captured utilizing densely connected convolutional neural networks. A parametric matrix based fusion scheme is further put forward to learn influence degrees of the spatial and temporal dependence. Experimental results show that the prediction performance in terms of root mean square error (RMSE) can be significantly improved compared with those existing algorithms. The prediction accuracy is also validated by using the datasets of Telecom Italia.

Wireless traffic prediction is essential for cellular networks to realize intelligent network operations, such as load-aware resource management and predictive control. Existing prediction approaches usually adopt centralized training architectures and require the transferring of huge amounts of traffic data, which may raise delay and privacy concerns for certain scenarios. In this work, we propose a novel wireless traffic prediction framework named Dual Attention-Based Federated Learning (FedDA), by which a high-quality prediction model is trained collaboratively by multiple edge clients. To simultaneously capture the various wireless traffic patterns and keep raw data locally, FedDA first groups the clients into different clusters by using a small augmentation dataset. Then, a quasi-global model is trained and shared among clients as prior knowledge, aiming to solve the statistical heterogeneity challenge confronted with federated learning. To construct the global model, a dual attention scheme is further proposed by aggregating the intra-and inter-cluster models, instead of simply averaging the weights of local models. We conduct extensive experiments on two real-world wireless traffic datasets and results show that FedDA outperforms state-of-the-art methods. The average mean squared error performance gains on the two datasets are up to 10% and 30%, respectively.

This paper focuses on securing confidential communication in multiple intelligent reflecting surfaces (IRS) assisted terahertz (THz) systems, where a potential eavesdropper can intercept either the base station (BS)-IRS link or the IRS-user link. Notably, the secure transmission may be intercepted and blocked by the eavesdropper due to the blockage-prone nature in THz bands. To characterize the blocking effects of the eavesdropper, the blocking-based path loss is first investigated. With the imperfect eavesdropper channel state information (ECSI), the worst-case secrecy rate (WCSR) is derived, and a joint optimization problem of hybrid beamforming at the BS and reflecting beamforming at the IRS is formulated. For the BS-IRS link eavesdropping, the zero-forcing (ZF) principle-based hybrid beamforming and the closed-form phase shifts of multiple IRSs are respectively proposed. For the IRS-user link eavesdropping, an iterative algorithm is proposed to tackle the non-convex optimization problem with a given information leakage threshold. Finally, a robust secure transmission strategy for multi-eavesdropper systems is further investigated. Simulation results demonstrate that compared with blockage-unaware scenarios, our proposed scheme can resist the adverse effects of the blockage-prone nature of THz waves on information security, and significantly boost secrecy performance.

Wireless traffic prediction plays a vital role in managing high dynamic and low latency communication networks, especially in 6G wireless networks. Regarding data and computing resources constraints in edge devices, federated wireless traffic prediction has attracted considerable interest. However, federated learning is limited to dealing with heterogeneous scenarios and unbalanced data availability. Along this line, we propose an efficient federated meta-learning approach to learn a sensitive global model with knowledge collected from different regions. The global model can efficiently adapt to the heterogeneous local scenarios by processing only one or a few steps of fine-tuning on the local data sets. Additionally, distance-based weighted model aggregation is designed to capture the dependencies among different regions for better spatial-temporal prediction. We evaluate the performance of the proposed scheme by comparing it with the conventional federated learning approaches and other commonly used benchmarks for traffic prediction. The extensive simulation results reveal that the proposed scheme outperforms the benchmarks.

Recurrent neural network (RNN) based models are widely adopted to capture temporal dependencies in the state-of-the-art approaches for cellular traffic prediction. However, RNN is inefficient and incapable of capturing long-range temporal dependencies of traffic data. Besides, its inherent sequential nature makes it time consuming in capture the temporal dependencies. To better capture the long-term temporal dependency and reduce the consumed time in traffic data prediction, we propose a time-wise attention aided convolutional neural network (TWACNet) structure for cellular traffic prediction. In the proposed TWACNet, the time-wise attention mechanism is adopted to capture long-range temporal dependencies of the cellular traffic data and the convolutional neural network (CNN) is adopted to capture the spatial correlation. The performance of TWACNet in traffic prediction is tested in real-world cellular traffic datasets. Experimental results demonstrate that our proposed approach can considerably outperform those existing prediction methods in terms of root mean square errors (RMSE) and training time.