To boost the performance of wireless communication networks, unmanned aerial vehicles (UAVs) aided communications have drawn dramatically attention due to their flexibility in establishing the line of sight (LoS) communications. However, with the blockage in the complex urban environment, and due to the movement of UAVs and mobile users, the directional paths can be occasionally blocked by trees and high-rise buildings. Intelligent reflection surfaces (IRSs) that can reflect signals to generate virtual LoS paths are capable of providing stable communications and serving wider coverage. This is the first paper that exploits a three-dimensional geometry dynamic channel model in IRS- assisted UAV-enabled communication system. Moreover, we develop a novel deep learning based channel tracking algorithm consisting of two modules: channel pre-estimation and channel tracking. A deep neural network with off-line training is designed for denoising in the pre-estimation module. Moreover, for channel tracking, a stacked bi-directional long short term memory (Stacked Bi-LSTM) is developed based on a framework that can trace back historical time sequence together with bidirectional structure over multiple stacked layers. Simulations have shown that the proposed channel tracking algorithm requires fewer epochs to convergence compared to benchmark algorithms. It also demonstrates that the proposed algorithm is superior to different benchmarks with small pilot overheads and comparable computation complexity.

Wireless-powered communication networks (WPCNs) are a promising technology supporting resource-intensive devices in the Internet of Things (IoT). However, their transmission efficiency is very limited over long distances. The newly emerged intelligent reflecting surface (IRS) can effectively mitigate the propagation-induced impairment by controlling the phase shifts of passive reflection elements. In this article, we integrate IRS into WPCNs to assist both the energy and information transmission. We aim to maximize the uplink (UL) sum rate of all IoT devices by jointly optimizing the time allocation variable, energy beam matrix at the power transmitting base station (PTBS), receive beamforming matrix at the information receiving base station, and the phase shifts of the IRS both in the UL and downlink (DL) subject to time allocation constraint, together with transmit power constraint for the PTBS and unit modulus constraints. This problem is very difficult to solve directly due to the highly coupled variables, which results in the optimization problem taking neither linear nor convex form. Hence, we decouple this problem into three subproblems by using the block coordinate descent method. The UL receive beamforing matrix and phase shift are alternatively optimized in the UL optimization subproblem with fixed time allocation and the DL variables. The DL optimization subproblem is solved by the proposed successive convex approximation algorithm. Simulation results demonstrate that the performance of integrating IRS and WPCNs outperforms traditional WPCNs. Besides, the results show that IRS is an effective method to preserve the tradeoff of energy efficiency and transmission efficiency in the IoT.

In this paper, we investigate the Unmanned Aerial Vehicles (UAVs)-assisted communications in three dimensional (3-D) environment, where one UAV is deployed to serve multiple user equipments (UEs). The locations and quality of service (QoS) requirement of the UEs are varying and the flying time of the UAV is unknown which depends on the battery of the UAVs. To address the issue, a proximal policy optimization 2 (PPO2)-based deep reinforcement learning (DRL) algorithm is proposed, which can control the UAV in an online manner. Specifically, it can allow the UAV to adjust its speed, direction and altitude so as to minimize the serving time of the UAV while satisfying the QoS requirement of the UEs. Simulation results are provided to demonstrate the effectiveness of the proposed framework.

Reconfigurable intelligent surface (RIS) has recently been regarded as a potential technique to enhance the performance of wireless communication systems by creating additional communication links. However, it is almost impossible to get the perfect channel state information (CSI) from the base station (BS) to the Internet of Things Devices (IoTDs) and the RIS-related channels. Furthermore, residual transceiver hardware impairments inevitably affect the performance of wireless communication systems. Hence, we study the robust design for an RIS-aided wireless communication system based on the imperfect CSI and hardware impairments. Minimizing the power consumption of BS is formulated by ensuring the minimum signal-to-interference-plus-noise ratio (SINR) demands of the IoTDs and the unit-modulus constraints of the RIS. Specifically, after approximating the nonconvex constraints by using the S-procedure and the successive convex approximation (SCA) methods, we adopt the block coordinate descent (BCD) technique to iteratively optimize one set of variables while keeping the other variables fixed in various channel uncertainty scenarios. Simulation results demonstrate that the influence of transceiver hardware impairments can be effectively decreased by deploying RIS even with channel uncertainty, which is more advantageous than increasing the number of BS’s antennas.

Recent breakthroughs in multimodal large language models (MLLMs) have endowed AI systems with unified perception, reasoning, and natural-language interaction across text, image, and video modalities. Meanwhile, unmanned aerial vehicle (UAV) swarms are increasingly deployed in dynamic, safety-critical missions that demand rapid situational awareness and autonomous adaptation. This paper explores potential solutions for integrating MLLMs with UAV swarms to enhance intelligence and adaptability across diverse tasks. Specifically, we first outline the fundamental architectures and functions of UAVs and MLLMs. Then, we present a comprehensive framework for an MLLM-enabled UAV swarm system and discuss the opportunities it offers. Next, we demonstrate the capabilities of the proposed framework through a forest firefighting case study that includes both simulation and real-world experiments. Finally, we discuss the challenges and future research directions for MLLM-enabled UAV swarms. An illustrative video of the experiments is available at https://youtu.be/zwnB9ZSa5A4.