As a critical component of sixth-generation (6G) wireless networks, ultra-reliable and low-latency communication (URLLC) is expected to support real-time and reliable information exchange in low-altitude environments. However, achieving URLLC often incurs significant resource overhead, including increased bandwidth consumption, higher transmit power, and denser access point (AP) deployment, which pose significant challenges to both spectral efficiency (SE) and energy efficiency (EE). Besides, existing iterative optimization algorithms are computationally intensive and struggle to meet the latency requirements of URLLC. To address these challenges, we propose a hybrid aerial-terrestrial cell-free massive MIMO (CF-mMIMO) network to support diverse services, along with a channel prediction network and a deep mixture of experts (MoE) network for uplink optimization. First, we design a channel prediction network (CP-Net) to mitigate channel aging caused by high-mobility user equipment (UE). CP-Net employs three Transformer-based sub-networks for aged channel state information (CSI) prediction, while a channel quality-aware loss function is introduced to improve the prediction accuracy of weak links. Based on the predicted CSI, we develop a deep MoE network (MoE-Net) for power allocation comprising three expert models targeting different objectives. Then, we introduce a weighted gating network (WT-Net) to learn an efficient adaptive combination of expert outputs. The proposed framework better captures heterogeneous UE requirements and improves communication performance under URLLC constraints. Numerical results demonstrate the effectiveness of the proposed method.

With the rapid advancement of unmanned aerial vehicle (UAV) technology, UAV cell free massive multiple-input multiple-output (CF-mMIMO) systems demonstrate significant potential for enhancing wireless communication performance. However, optimizing energy efficiency (EE) to meet the growing demands of communication has become a critical research challenge. This paper explores resource allocation in the UAV CF-mMIMO uplink under ultra reliable and low latency communication (URLLC) constraints to improve EE. We first conduct a systematic analysis in the system model to identify key factors impacting EE. Accounting for these factors, an optimization problem is then formulated. To solve this problem, we employ a self-supervised deep neural network (SSDNN) composed of two submodules: One is to extract channel characteristics of all users equipment (UEs), and the other is to optimally allocate power for both UAVs and ground user equipments (GUEs) via a resource allocation layer. Numerical results show that our proposed method achieves higher EE compared to approaches that do not consider GUE interference.

Termites present a significant environmental risk by compromising the structural integrity of trees, dams, and various other critical infrastructures. However, their small size makes accurate detection challenging, particularly in complex environments. To address this issue, this paper proposes a novel detection model, You Only Look Once with HiLo-ECPCA Refined Attention (YOLO-HERA), based on the YOLOv8s framework. The proposed model integrates HiLo and ECPCA attention mechanisms to enhance the detection of small targets in cluttered environments. The HiLo module effectively combines high-frequency details with low-frequency contextual information, while the ECPCA mechanism optimizes feature extraction through adaptive channel and spatial attention. The YOLO-HERA model is incorporated into a comprehensive termite monitoring system comprising an embedded terminal, server, and frontend display for real-time detection, data transmission, and visualization. Experimental evaluations demonstrate that YOLO-HERA achieves superior performance compared to previous YOLO versions and other detection algorithms, offering a robust solution for practical termite detection applications.

Tracking micro-unmanned aerial vehicles (micro-UAVs) in low signal-to-noise ratio (SNR) environments poses significant challenges due to their weak radar cross-section (RCS) and the inherent limitations of traditional Detect-Before-Track (DBT) radar algorithms. This paper proposes a novel Track-Before-Detect (TBD) approach based on a Markov Chain Monte Carlo-Enhanced Particle Filter (MCMC-EPF), leveraging 4D Frequency Modulated Continuous Wave (FMCW) MIMO radar. By directly processing unthresholded multi-frame 4D-FFT radar data, the method achieves joint detection and tracking, effectively preserving weak target information that is typically lost in DBT methods. Experimental results on real radar data demonstrate that the proposed algorithm achieves robust and accurate UAV tracking, maintaining a root-mean-square error (RMSE) within 1 meter and an average relative tracking error below 2.5% under low SNR conditions. These results highlight the method’s potential for reliable UAV surveillance in challenging operational environments.

To achieve ultrareliable and low-latency communication (URLLC) and support high density of wireless connections simultaneously, the sixth-generation Industrial Internet of Things (6G-IIoT) necessitates an expansion of antenna arrays and broader bandwidths, which suffers from high energy consumption. To address this issue, this article investigates a cell-free massive multiple-input-multiple-output (CF-mMIMO) system and designs an iterative search-based two-stage energy efficiency (EE) optimization algorithm for the uplink communication of the system. The first stage prioritizes reliability to ensure that all users meet the URLLC requirements regarding latency and reliability. The second stage maximizes the EE under URLLC-satisfied conditions. Considering that iterative search algorithms incur a high computational overhead and variable number of iterations, we further propose a convolutional neural network architecture (RACNN) to approximate an optimal resource allocation strategy and to realize the real-time and stable output. This structure extracts deep correlations among users from the global channel features. It takes strategies of multitask learning and weight loss adaptation to improve the model’s convergence speed. Furthermore, we employ deep transfer learning to adjust RACNN parameters to accommodate the potential of dynamic communication scenarios, thereby reducing the demand for training samples and training time overhead. Finally, the efficacy of the proposed algorithm, RACNN, and deep transfer learning is validated through experimental simulations.

In space-air-ground integrated networks (SAGIN), receivers experience diverse interference from both the satellite and terrestrial transmitters. The heterogeneous structure of SAGIN poses challenges for traditional interference management (IM) schemes to effectively mitigate interference. To address this, a novel UAV-RIS-aided IM scheme is proposed for SAGIN, where different types of channel state information (CSI) including no CSI, instantaneous CSI, and delayed CSI, are considered. According to the types of CSI, interference alignment, beamforming, and space-time precoding are designed at the satellite and terrestrial transmitter side, and meanwhile, the UAV-RIS is introduced for the cooperating interference elimination process. Additionally, the degrees of freedom (DoF) obtained by the proposed IM scheme are discussed in depth when the number of antennas on the satellite side is insufficient. Simulation results show that the proposed IM scheme improves the system capacity in different CSI scenarios, and the performance is better than the existing IM benchmarks without UAV-RIS, but the performance improvement is at the cost of the requirement on the elements of UAV-RIS.

In this paper, we investigate a cognitive multicast communication system aided by active reconfigurable intelligent surface (active RIS). Specifically, for an underlay spectrum sharing cognitive multicast network, a cognitive radio base station (CRBS) communicates with secondary users (SUs) assisted by an active RIS. Meanwhile, the interference to primary users (PUs) is suppressed within the constraints of the transmit power of both the CRBS and active RIS, together with the restriction of the active RIS amplitude gain. We aim at the fairness problem for maximizing the minimum signal-to-interference-plus-noise-ratio (SINR) via joint beamforming design at the CRBS and the active RIS. To cope with this problem, the optimization and deep reinforcement learning (DRL) based algorithms are proposed. Specifically, the decision variables are decoupled by the alternating optimization (AO) method and then, the non-convex problem is transformed into a solvable convex form by using the successive convex approximation (SCA), Schur complement, and penalty convex-concave procedure (PCCP) methods. Furthermore, we design an AO-based algorithm for the formulated problem. Due to the characteristics of both exploration and exploitation, the DRL-based algorithms outperform the AO-based algorithm with proper parameter settings. Meanwhile, the DRL algorithm inherits the advantages of low execution complexity. The original optimization problem is first converted into a Markov decision process (MDP) form in DRL. Due to the complex objective function and various restrictions of power/amplification gain budget and quality of service (QoS), the constraints are categorized as the switching constraints for action adjustment and performance constraints for reward function setting, respectively. Subsequently, a segmented incentive-based reward function is developed to attain higher performance on SINR. We also propose two effective deep deterministic policy gradient (DDPG)-based and twin delayed deep deterministic policy gradient (TD3)-based algorithms. Finally, the simulation results demonstrate a notable enhancement in system performance upon the introduction of active RIS compared to the case with a passive RIS and the case without using an RIS. Moreover, with appropriately configured parameters, DRL algorithms outperform the AO-based algorithm, and notably, the TD3 algorithm is superior to the DDPG algorithm in optimization effectiveness.

In MIMO multi-user networks, inter-user interference (IUI) significantly affects the system performance. To handle this problem, this paper proposes the reconfigurable intelligent surface assisted cooperative interference alignment scheme (RIS-CIA). The core idea of this work is that the base station and full-duplex users jointly design space-time precoding matrices, which can reduce the dimension of the interference space on the user side. Besides, the additional interference caused by the information exchange process is split into sub-blocks by space-time precoding, then eliminated by interference nulling assisting by the passive RIS. The simulation results show that the RIS-CIA scheme with few numbers of elements obtains higher DoF than that of benchmark schemes with a huge number of elements.

In heterogeneous networks (HetNets), although deploying numerous small base stations (SBSs) can effectively enhance spectral efficiency (SE), it is difficult to achieve seamless coverage due to their fixed locations. To handle this issue, we propose a HetNet structure assisted by unmanned aerial vehicles (UAVs), where the high mobility and flexible deployment of UAVs are leveraged. However, interference is inevitable in the proposed UAV-assisted HetNet, thus we design a comprehensive interference management (IM) scheme, selectively adopting successive interference cancellation (SIC) algorithm, space-time interference alignment (STIA) and interference steering (IS) according to the location of users and interference types. The numerical results verify that with SIC-STIA-IS scheme, the proposed UAV-assisted HetNet is advantageous in degrees of freedom (DoF) and sum rate.

In this paper, we propose a rate-splitting design and characterize the sum-degrees-of-freedom (DoF) for the K-user multiple-input-single-output (MISO) broadcast channel with mixed channel state information at the transmitter (CSIT) and order-(K − 1) messages, where mixed CSIT refers to the delayed and imperfect-current CSIT, and order-(K − 1) message refers to the message desired by K − 1 users simultaneously. In particular, for the sum-DoF lower bound, we propose a rate-splitting scheme embedding with retrospective interference alignment. In addition, we propose a matching sum-DoF upper bound via genie signalings and extremal inequality. Opposed to existing works for K = 2, our results show that the sum-DoF is saturated with CSIT quality when CSIT quality thresholds are satisfied for K > 2.

To accommodate the explosive growth of the Internet of Things (IoT), incorporating interference alignment (IA) into existing multiple access (MA) schemes is under investigation. However, when it is applied in MIMO networks to improve the system capacity, the new problem regarding information delay arises which does not meet the requirement of low-latency. Therefore, in this paper, we first propose a new metric named degree of delay (DoD) to quantify the issue of information delay. By analyzing DoD with classical transmission schemes, it can be seen that the information latency does affect the performance of the system. To cope with this issue, hybrid antenna array based partial interference elimination and retrospective interference regeneration scheme (HAA-PIE-RIR) is first proposed. It achieves optimal performance in 2-user MIMO scenarios, but suffers a performance loss in$K$-user MIMO scenarios. Then, the improved HAA-PIE-RIR scheme (HAA-IPIE-RIR), and HAA based cyclic interference elimination and RIR scheme (HAA-CIE-RIR) are proposed. The former achieves optimal performance in$K$-user MIMO scenarios, but requires heavy computational cost. The latter is a trade-off scheme considering performance and computational cost comprehensively. Overall, our proposed schemes can obtain lower DoD and higher DoF than that of traditional IA schemes.

In fifth generation networks (5G), beamforming technique is widely used to obtain higher system capacity, but it cannot eliminate inter-user interference (IUI) of networks due to excessive number of users. To handle this problem, interference alignment (IA) schemes attract great attention as they can effectively restrain IUI. However, the existing IA schemes cannot achieve antenna adaptation and the obtained degree of freedom (DoF) may be not optimal. In this paper, a novel antenna adaptation based interference elimination and regeneration (AA-IER) scheme is proposed for cooperative networks, where a relay with hybrid antenna array structure is adopted to assist the communication. The proposed transmission process is completed in two phases, including interference elimination phase (IEP) and interference regeneration phase (IRP). For the former, the IUI is eliminated and the redundant symbols are erased so that the received signal of multiple users can be decoded simultaneously. For the latter, the redundant symbols of all users are regenerated where the space resources are fully utilized. The simulation results show that AA-IER scheme obtains higher DoF than that of three benchmark schemes. Meanwhile, it requires fewer antennas of relay than HAA-CIE-RIA scheme.

As a novel method to increase channel capacity of networks, interference alignment (IA) technique has attracted wide attention in fifth-generation wireless networks (5G). However, when it is applied in interference networks, the problem regarding information delay arises which has not been well addressed yet. In this paper, we formally propose the novel concepts of degree of delay (DoD) to quantify the issue of information delay and analyze its determining factors, i.e., delay sensitive factor, queueing delay slot and size of dataset. To reduce DoD, three novel joint IA schemes are proposed for broadcast channel (BC) networks with different amounts of users, i.e., hybrid antenna array based partial interference elimination and retrospective interference regeneration scheme (HAA-PIE-RIR), HAA based improved PIE and RIR scheme (HAA-IPIE-RIR) and HAA based cyclic interference elimination and RIR scheme (HAA-CIE-RIR). Among the three, the second scheme extends the application scenarios of the first scheme from 2-user to K-user while bringing huge computational complexity burden. The third scheme relieves the burden but it leads to slight degree of freedom (DoF) loss. Overall, the proposed schemes achieve higher DoF and lower DoD than the existing IA schemes.