Accurate cellular traffic prediction is conducive to managing communication networks, but challenging, due to dynamic temporal variations and complicated spatial correlations. In this letter, a novel Spatial-Temporal Transformer (ST-Tran) is proposed to explore spatial and temporal sequence information simultaneously. A temporal transformer block is designed to learn temporal features of every grid in a communication network by modeling its traffic flows during both recent and periodic time intervals. Meanwhile, the spatial characteristics of every grid are cooperated with the information of its related grids to generate spatial predictions in the spatial transformer block. An output block is further proposed to merge the temporal and spatial information into a final prediction. Experimental results on a large real-world dataset verify the effectiveness of the ST-Tran. The source code is available at https://github.com/liuqingyao11/ST-Tran .

Recently, unmanned aerial vehicles (UAVs) as flying wireless communication platform have attracted much attention. Benefiting from the mobility, UAV aerial base stations can be deployed quickly and flexibly, and can effectively establish Line-of-Sight communication links. However, there are many challenges in UAV communication system. The first challenge is energy constraint, where the UAV battery lifetime is in the order of fraction of an hour. The second challenge is that the coverage area of UAV aerial base station is limited and the commercial UAV is usually expensive. Thus, covering a large target region all the time with sufficient UAVs is quite challenging. To solve above challenges, in this paper, we propose energy efficient and fair 3-D UAV scheduling with energy replenishment, where UAVs move around to serve users and recharge timely to replenish energy. Inspired by the success of deep reinforcement learning, we propose a UAV Control policy based on Deep Deterministic Policy Gradient (UC-DDPG) to address the combination problem of 3-D mobility of multiple UAVs and energy replenishment scheduling, which ensures energy efficient and fair coverage of each user in a large region and maintains the persistent service. Simulation results reveal that UC-DDPG shows a good convergence and outperforms other scheduling algorithms in terms of data volume, energy efficiency and fairness.

Satellite communication (SatCom) is regarded as a key enabler for bridging connectivity and capacity gaps in sixth-generation (6G) networks. However, the proliferation of Low Earth Orbit (LEO) satellites raises significant intersystem interference risks with Geostationary Earth Orbit (GEO) systems. This paper introduces a cooperative multi-satellite multi-reconfigurable intelligent surface (RIS) transmission framework to mitigate such interference while enhancing LEO SatCom performance. Specifically, cooperative beamforming is designed under a non-coherent cell-free paradigm, considering both adaptive and max ratio (MR) precoding, as well as statistical and two-timescale channel state information (CSI), aiming to synthesize the advantages of cell-free and RIS into SatCom in a practical way. Firstly, an alternating optimization (AO)-based design leveraging statistical CSI with adaptive precoding is proposed. Then, we propose a power allocation algorithm under MR precoding with given RIS phase shifts obtained from the former, along with a direct two-stage design bypassing prior results. Additionally, we extend derived closed-form expressions and proposed algorithms to exploit two-timescale CSI. Numerical results demonstrate the impact of intersystem interference mitigation constraints, compare the performance of proposed algorithms, draw insights into the effects of transmit power, interference threshold, and Rician factors, validate SatCom performance enhancements achieved by RISs, and discuss the advantages of multi-satellite cooperation.

In this letter, we present Wi-Mose, the first 3D moving human pose estimation system using commodity WiFi. Previous WiFi-based works have achieved 2D and 3D pose estimation. These solutions either capture poses from one perspective or construct poses of people who are at a fixed point, preventing their wide adoption in daily scenarios. To reconstruct 3D poses of people who move throughout the space, we fuse the amplitude and phase of Channel State Information (CSI) into CSI image which can provide both pose and position information. Besides, we design a neural network to extract features which are only associated with poses from CSI images and then convert the features into key-point coordinates. Experimental results show that Wi-Mose can localize key-point with 29.7 mm and 37.8 mm Procrustes analysis Mean Per Joint Position Error (P-MPJPE) in the Line of Sight (LoS) and Non-Line of Sight (NLoS) scenarios, respectively, achieving higher performance than the state-of-the-art method. The results indicate that Wi-Mose can capture high-precision 3D human poses throughout the space.

Human sensing based on commodity Wi-Fi devices has become a promising technique in human tracking, gesture recognition, walking speed monitoring, in-home healthcare, etc. However, past human sensing systems usingWi-Fi capture limited information about humans. Hence in this letter, we try to make commodity Wi-Fi devices act as cameras to directly capture human poses, i.e., fine-grained human skeleton images. We use a synchronized camera to capture human skeletons as annotations for Wi-Fi signals and design a novel neural network to convert Wi-Fi signals into images. We utilize three transceivers coordinately and use amplitude and phase information of Channel State Information (CSI) jointly to improve the resolution of Wi-Fi signals. We also introduce a method to extract useful and accurate CSI corresponding to humans and construct CSI images which are input of the neural network. Experimental results show that commodity Wi-Fi devices can capture human poses almost as fine-grained as cameras.

So far the handoff management involved in Wireless Local Area Network (WLAN) has mainly fallen into the handoff mechanism and the decision algorithm. The traditional handoff mechanism generates noticeable delays during the handoff process, resulting in discontinuity of service, which is more evident in dense WLANs. Inspired by software-defined networking (SDN), prior works put forward many seamless handoff mechanisms to ensure the service continuity. With respect to the handoff decision algorithm, when to trigger handoff and which access point to reconnect to, however, are still tricky problems. In this paper, we first design a self-learning architecture applicable to the SDN-based WLAN frameworks. Along with it, we propose DCRQN, a novel handoff management scheme based on deep reinforcement learning, specifically deep Q-network. The proposed scheme enables the network to learn from actual users’ behaviors and network status from the scratch, adapting its learning in time-varying dense WLANs. Due to the temporal correlation property, the handoff decision is modeled as the Markov Decision Process (MDP). In modeled MDP, the proposed scheme depends on the real-time network statistics at time of decisions. Moreover, convolutional neural network and recurrent neural network are leveraged to extract fine-grained discriminative features. Numerical results through simulation demonstrate that DCRQN can effectively improve the data rate during the handoff process, outperforming the traditional handoff scheme.