Reconfigurable intelligent surface (RIS) plays an essential role in alleviating severe path loss in millimeter wave communication systems. Its performance hinges on the precise modeling of high-dimensional cascaded channels. However, traditional modeling approaches require extensive experience in radio propagation, resulting in complex and inefficient processes. To overcome these limitations, we transform the RIS channel modeling into a channel distribution transport mapping problem and introduce a generative model based on rectified flow. Our approach integrates distance information into a diffusion transformer (DiT) architecture through cross-attention mechanisms, resulting in a conditional DiT capable of synthesizing target channels from distance inputs. We further optimize the rectified flow into a single-step generator via reflow techniques. Building on this framework, we design a generative digital twin (DT) channel model that serves as a high fidelity data generator for downstream tasks. The proposed model acts as a virtual replica of the propagation environment, enabling efficient channel data synthesis for training communication algorithms such as channel state information feedback and channel estimation. Simulation results show that our approach generates channels with minimal distribution discrepancy compared to real channels (a maximum mean discrepancy < 0.01), outperforming existing generative methods. Furthermore, the reflow-driven DT channel model achieves the shortest generation time among all evaluated benchmarks.

Cell-free massive multi-input-multi-output (CF-mMIMO) provides significant improvement owing to the distributed architecture. However, it suffers from the constraints including information constraints, and computation resources constraints. In this paper, we propose 4 ranks of available information in CF-mMIMO and aim to find a distributed precoding exploiting randomly accessible side information, which is one-step without iterations and robust against the unreliable fronthaul between distributed central processing units. Quadratic team learning (QTL) is devised which is derived from team theory to handle the distributed underdetermined quadratic programming. The extensive 1440 experiments validate the superiority of QTL and we believe QTL is a definitely excellent choice for CF-mMIMO distributed precoding. To the best of our knowledge, this is the first work utilizing team theory to help the design of artificial intelligence architecture for wireless communications. To prompt the development of QTL, we have open-sourced the implementation code on https://github.com/hzy238221seu/QTL4CF-Precoding.git.

Cell-free massive MIMO (CF-mMIMO) represents the pinnacle of distributed antenna systems, offering superior service to all users. However, the distributed nature of access points leads to fragmented information processing, limiting performance in practical deployments. Additionally, existing studies often overlook the impact of limited fronthaul capacity, which introduces noise and degrades the reliability of shared information. In this work, we implement a practical CF-mMIMO prototype under fifth generation new radio standards and propose a diffusion-based uplink scheme that outperforms conventional distributed cell-free systems without cooperation. Our approach adapts to arbitrary fronthaul topologies by leveraging the law of large numbers. We further analyze the linear effects of fronthaul noise and the correlation of uploaded data, demonstrating that the diffusion uplink excels in Rician fading environments while maintaining robust performance in Rayleigh fading. To the best of our knowledge, this is the first work to employ a diffusion model for mitigating fronthaul non-idealities, enabling distributed cooperative uplink in a real-world CF-mMIMO system.

Extremely large-scale MIMO (XL-MIMO) is regarded as a pivotal enabler for achieving ultra-high spectral efficiency in 6G communications. Near-field channel models, which integrate both line-of-sight (LoS) and non-line-of-sight (NLoS) components, provide accurate characterizations of near-field XL-MIMO channels. However, existing channel estimation schemes encounter severe performance bottlenecks due to the high-dimensional nature of near-field XL-MIMO channels and their structured angular sparsity compared to far-field MIMO systems. To address these challenges, we propose a variance exploding stochastic differential equation (VE-SDE) generator based on an improved diffusion transformer (IDiT) network. The VE-SDE progressively maps the complex XL-MIMO channel distribution to a tractable prior distribution by gradually injecting noise. We utilize the patchify technique to decompose the perturbed angular domain channels into token sequences, which are then processed with diffusion transformer (DiT) blocks, substantially reducing floating-point operations (FLOPs). Additionally, a sparse self-attention mechanism is employed to enhance structured sparsity characterization learning, thereby improving estimation accuracy. Theoretical analysis and numerical experiments show that the VE-SDE generator exhibits strong generalizability and robustness across diverse channel distributions without requiring retraining. Simulation results reveal that the proposed method outperforms state-of-the-art estimation approaches, achieving high-fidelity channel estimation with only 20% pilot density.

Cell-free is considered a promising technology for the future network, which adopts a large number of distributed antennas to provide a uniformly good service. However, current researches under the long-term evolution standard mostly ignore the problem of asynchronous transmission brought by the different transmission delays due to the geographical distance differences, and assume that the system is perfectly synchronized. On the other, these works often do not consider a distributed method with controllable fronthaul overhead compatible with cell-free. To enable an extensive cell-free in the sixth generation, we derive an asynchronous analysis framework and propose a centralized and a distributed downlink precoding method respectively. What is more important, we have verified that cell-free suffers from inter-carrier-interference and inter-symbol-interference under the 5th generation new radio standard. To the best of our knowledge, this is the first work implementing a distributed asynchronous precoding method in an extensive cell-free, and simulation results demonstrate the effectiveness of the proposed two precoding methods, compared to naive precoding ignoring the asynchronous impact.

Cell-free is seen as one of the most important technology for the future wireless communications. In this paper, we adopt a wideband cell-free to implement low-altitude coverage to serve multiple unmanned aerial vehicles (UAVs) in the city playing the core role of low-altitude economy. For practice, distributed computation, asynchronous effects, beam split and imperfect channel state information are considered. We mainly rely on per-beam synchronization (PBS) and discuss different architecture implementations. A wideband asynchronous architecture that reuses the time delay modules exploited in wideband beam split calibration is proposed. In addition, a semi-synchronized path set (SSP-Set) is derived to eliminate asynchronous interference and a geometric scattering graphic convolutional network is used to acquire the (sub)-optimal SSP-Set. Based on these two technologies, a beam-delay alignment transmission (BDAT) scheme is obtained and we implement it with a distributed paradigm. The numerical results demonstrate the proposed BDAT can benefit from the cooperative downlink beamforming and provide a uniformly good service for UAVs.

Cell-free massive multiple-input multiple-output (MIMO) systems have emerged as a transformative architecture for sixth generation (6G) communication networks, where distributed access points (APs) collaborate to simultaneously serve all user equipments (UEs). However, in time division duplex (TDD) systems, the reciprocity of uplink channel and downlink channel is disrupted by hardware imperfections in radio frequency (RF) chains, leading to significant degradation in system performance. This paper begins with a theoretical analysis of the downlink performance under a conjugate beamforming scheme, considering scenarios with and without channel calibration. A key theoretical insight highlights the limitation of conventional least squares (LS) calibration method, which fails to achieve high calibration accuracy even with an unlimited number of pilot observations. To overcome this limitation, we propose a novel channel calibration approach based on a diffusion model, designed to successively refine the calibration vector obtained from the LS calibration method. Furthermore, to address the shortcomings of conventional denoising diffusion probabilistic model (DDPM) training architectures, we introduce an innovative bridge-based diffusion model that maps the distribution of LS calibration vectors to their perfect counterparts. The proposed diffusion neural network architecture employs a conditional generative process, integrating a message passing neural network (MPNN) to incorporate domain-specific calibration insights. Numerical results demonstrate the superior performance of our proposed calibration method compared to existing methods, with supplementary experiments and in-depth analyses confirming the efficacy of the proposed successive refinement design.

Beamforming enhances signal strength and quality by focusing energy in specific directions. This capability is particularly crucial in cell-free integrated sensing and communication (ISAC) systems, where multiple distributed access points (APs) collaborate to provide both communication and sensing services. In this work, we first derive the distribution of joint target detection probabilities across multiple receiving APs under false alarm rate constraints, and then formulate the beam selection procedure as a Markov decision process (MDP). We establish a deep reinforcement learning (DRL) framework, in which reward shaping and sinusoidal embedding are introduced to facilitate agent learning. To eliminate the high costs and associated risks of real-time agent-environment interactions, we further propose a novel digital twin (DT)-assisted offline DRL approach. Different from traditional online DRL, a conditional generative adversarial network (cGAN)-based DT module, operating as a replica of the real world, is meticulously designed to generate virtual state-action transition pairs and enrich data diversity, enabling offline adjustment of the agent’s policy. Additionally, we address the out-of-distribution issue by incorporating an extra penalty term into the loss function design. The convergency of agent-DT interaction and the upper bound of the Q-error function are theoretically derived. Numerical results demonstrate the remarkable performance of our proposed approach, which significantly reduces online interaction overhead while maintaining effective beam selection across diverse conditions including strict false alarm control, low signal-to-noise ratios, and high target velocities.

Accurate sensing channel estimation is fundamental to high-performance integrated sensing and communication (ISAC), as it supplies critical information for target detection and localization. Despite extensive research, most existing approaches rely on the unrealistic assumption of ideal hardware conditions. However, hardware impairments are often inevitable due to the use of cost-efficient circuit components. This highlights the necessity for robust estimation techniques that remain reliable under imperfect conditions. To this end, we propose a self-supervised model-fusion network (SMF-Net) tailored for sensing channel estimation in hardware-impaired ISAC systems. To suppress distortions induced by hardware non-idealities, we design a two-stage cascaded convolutional neural network that leverages the spectral bias of neural networks, i.e., their tendency to learn high response frequency details in shallow layers and low frequency information in deep layers, to better separate different types of distortions present in corrupted channel estimates. By analyzing domain-specific features of the distorted channel components, we introduce a hybrid-domain denoising strategy that effectively exploits spatial correlations and angular sparsity inherent in the channel model. Furthermore, the framework is trained in a self-supervised manner, obviating the need for clean channel labels. Theoretical analysis validates the effectiveness of the proposed method and demonstrates that the self-supervised training strategy can match the performance of its supervised counterpart given a sufficiently large training set. Numerical results confirm the superiority of the proposed SMF-Net across various challenging scenarios, including severe nonlinear distortions, low transmission power, and limited training data.

Cell-free is seen as an important implementation for future wireless networks, which eliminates the conventional ‘cell’ concept and enables wide deployment. However, previous works mostly ignore the asynchronous effects in such a large distributed antenna system and assume perfect synchronization which is not practical. In this paper, we proposed a user-centric alignment transmission (UCAT) to settle this problem, which has the analytical beamforming vectors in each access point (AP) being computed locally and fits user-centric cell-free well. With cooperative center processing unit power optimization and AP beamforming computation, an asynchronous downlink method is obtained, and finally, numerical results demonstrate the effectiveness of UCAT.

Deep learning (DL) techniques have been extensively utilized to tackle challenges in the field of wireless communication, overcoming the limitations of traditional methods. However, training DL algorithms often requires large amounts of data, which is difficult to obtain in increasingly complex communication environments. Reducing the amount of data required for DL training is therefore an urgent problem to be solved. In this work, we develop a denoising diffusion probabilistic model (DDPM)-based digital twin (DT) framework of integrated sensing and communication (ISAC) multiple-input-multiple-output (MIMO) channel to address the data scarcity issue commonly found in DL-based scenarios. By sampling a small amount of data, our framework captures and simulates the data distribution, building a virtual data repository that can continuously provide samples to assist in executing control instructions to physical entities, even as the user equipment (UE) and target positions change. Specifically, we formulate the data generation problem as a distribution approximation task guided by the Kullback-Leibler (KL) divergence criterion and optimize it by meticulously designing a DDPM network composed of U-Net structure, time-embedding modules, and attention mechanisms. Moreover, we enhance the framework by formulating a task-driven objective function for two applications: 1) sensing channel estimation and 2) target detection. Numerical results demonstrate the superiority of our proposed DDPM-based DT framework compared with other data augmentation techniques in improving the performance of data-driven DL-based tasks, showcasing its robustness across diverse scenarios.

This paper investigates the challenge of acquiring channel state information at the transmitter (CSIT) in cell-free massive multiple-input multiple-output (MIMO) integrated sensing and communication (ISAC) systems operating in time-division duplex (TDD) mode. Although channel state information at the receiver (CSIR) is readily obtainable and CSIT is typically assumed to be its transpose, imperfections in the radio frequency (RF) chains disrupt this reciprocity. Focusing on this issue, we establish the necessary and sufficient conditions characterizing RF chain imperfections and their impact on system performance in a simplified scenario, underscoring the criticality of channel calibration. To address this challenge, a distributed source coding (DSC)-based calibration framework is proposed, leveraging the multiplexing of the sensing task to eliminate any additional communication overhead. This framework comprises a distributed compression scheme at each slave access point (AP) and a joint aggregation scheme at the central process unit (CPU). To validate the proposed DSC-based calibration framework, we analytically derive the performance gap relative to the fully collaborated approach. Building on this, a novel data-driven DSC-based deep learning method is proposed to address channel calibration without requiring clean labels. Numerical results demonstrate significant improvement in calibration performance achieved by our proposed method compared to existing calibration methods, approaching the performance of the fully collaborated method.

Cell-free massive multiple-input multiple-output (MIMO) is a promising technology to address the requirements for higher spectral efficiency and energy efficiency in 6G networks. Downlink beamforming scheme, essential for mitigating multiuser interference and enhancing overall system performance, relies on the estimated uplink channel state information (CSI) in time-division duplex (TDD) mode exploiting channel reciprocity. However, hardware impairments render the bi-directional channel non-reciprocal. This paper focuses on channel calibration for cell-free massive MIMO systems, taking into account both radio frequency (RF) mismatches and nonlinear distortions. We derive the closed-form expression for downlink achievable rate within a specific calibration scheme. To address the calibration challenge, we introduce a novel conceptual model, in which the calibration vector is determined by optimizing the performance of the reference antenna. Expanding on this concept, we propose a novel digital twin (DT)-enabled approach to overcome the limitations in the conceptual model, where the DT model is established to perform calibration task by introducing DT services of virtual reference antennas. By exploiting this method, the calibration vector is computed utilizing the proposed alternating optimization algorithm within the DT model, obviating the need for deploying reference antennas in the real cell-free system, thereby reducing costs. The communication overheads and computation complexity for updating the calibration vector is proportional to the access point (AP) number. Simulation results demonstrate the significant improvement of system performance through channel calibration and verify the higher downlink throughput of our proposed DT-enabled calibration method compared to the existing calibration methods.

The deployment of extremely large-scale antenna array (ELAA) brings higher spectral efficiency and spatial degree of freedom, but triggers issues on near-field channel estimation. Inspired by the success of deep learning (DL) in far-field channel estimation, this paper proposes a novel spatial-attention-based method to reconstruct extremely large-scale MIMO (XL-MIMO) channel. Initially, the spatial antenna correlation in near-field channels is drawn as the expectation over spatial region, different from only over spatial angle in far-field channels. The spatial antenna correlation implies that the near-field channel exhibits spatial nonstationarity, that the inter-antenna correlation vary with the antenna index and spatial regions and reveals the weakness of the widely applied convolutional neural network (CNN) with fixed receptive field. Subsequently, we develop a multi-scale spatial attention network (MsSAN) with low computational cost to enhance near-field MIMO channel estimation. In MsSAN, the channel is refined to subchannels of different scales layer by layer and each subchannel is treated as a whole and the spatial attention (SA) map is calculated by the sum of dot products of inter-subchannel so that the complexity grows linearly with channel size. Simulation results are presented to validate the proposed MsSAN with low computational cost outperforms others in terms of near-field channel reconstruction.

The deployment of extremely large-scale arrays and high-frequency signaling holds the potential to enhance communication capabilities and improve spectrum efficiency. However, channel estimation faces challenges due to the simultaneous consideration of spatial angles and distances, leading to storage constraints and energy spread. To cope with this issue, we analyze the sparsity inherent in beamspace domain representation and introduce an adaptive codebook scheme for extremely large-scale massive MIMO (XL-MIMO) channels. In this work, we transform multi-band channel estimation to sparse matrix recovery problem. Then, a novel adaptive joint sparse Bayesian learning algorithm is proposed to capture the angular-domain information and refine distance information iteratively without increasing codebook overhead for XL-MIMO channel estimation. Simulation results demonstrate our approach outperforms other algorithms based on the sampling angular-distance domain codebook with low codebook overhead.

Dual-functional radar-communication (DFRC) is a promising direction in the future integrated sensing and communication system. The joint radar and communication (JRC) beamforming scheme is recently developed in DFRC systems. To address the JRC beamforming challenge, conventional approaches predominantly rely on convex optimization methods, which severely depend on precise channel estimation and entail a high computational complexity. Motivated by this, a deep learning-based optimization approach is investigated for tackling the JRC beamforming problem. To enhance the overall performance, we design a deep alternating neural network architecture. Simulation results verify that our proposed method guarantees the required sensing performance and outperforms numerical algorithms in terms of the average data rate of communication users.

This paper concentrates on addressing the challenging problem of sensing channel estimation in cell-free integrated sensing and communication (ISAC) multiple-input multiple-output (MIMO) system. This challenge arises from the complex mixture of signals from both the direct sensing channel and target reflected sensing channel. To tackle this challenge, we introduce the digital twin (DT), as a powerful tool to exploit and characterize the inherent features of the target sensing channel by sampling data from the real world and interacting with it. To be specific, the DT model, designed as a generative adversarial network (GAN), is trained to be capable of generating the desired results from the coarse observations, where the distribution of the sensing channel in a particular cell-free ISAC system is implicitly learned via the adversarial process. With this basis, we propose a novel digital-twin-enabled channel estimation (DTE-CE) approach to enhance the performance of channel estimation, where the DTE-CE network is meticulously designed by utilizing the virtual channel matrix (VCM) model to facilitate the estimation process. Simulation results show the excellent performance of the proposed approach, as well as the effectiveness of our designed DTE-CE network, in terms of sensing channel estimation with different transmitting power and numbers of targets.

Cell-free massive multiple-input multiple-output (MIMO) is known for its potential to enhance overall system performance. Thanks to the principle of channel reciprocity, it becomes possible to implement downlink beamforming by exploiting the estimated uplink channel in time-division duplex (TDD) mode. However, the assumption of perfect hardware conditions, as made in prior studies, is not reflective of practical realities. The involvement of hardware impairments disrupts this reciprocity, resulting in performance degradation. This paper investigates the impact of hardware impairments in downlink data transmission, where a novel model is established by jointly considering the radio frequency (RF) mismatches and nonlinear distortions. We first derive closed-form achievable user rate expressions and prove that the impact of RF mismatches vanishes as the number of access points (APs)$M \to \infty $in certain distributions of RF gains. Then, we study the scenarios when the number of user equipments (UEs)$K \to \infty $, as well as various degrees of hardware impairments’ severity scaling M. Finally, we introduce a channel calibration process and theoretically derive its performance, observing that in certain scenarios, the need for calibration becomes redundant as$M \to \infty $. These findings are further validated through numerical results, confirming the scaling laws derived in our study.

Distributed precoding is a meaningful topic in the cell-free massive multiple input multiple output system. This system faces challenges in performance degradation due to the absence of knowledge from other antennas and several realistic constraints brought by the distributed implementation of the communication system such as the presence of phase noise (PN). In this paper, a robust cascaded team minimum mean square error (RCT-MMSE) precoding based on a hierarchical fronthaul structure is exploited to handle distributed and robust precoding including not only PN but signaling noise, sharing cost constraints and channel aging uncertainty. Such RCT-MMSE precoding, characterized by its avoidance of iterations because we derive the analytic expressions, mitigates the need for high fronthaul level instantaneous information exchange. It also demonstrates scalability with distributed computation burden and flexible signaling overhead, which offers an advantageous performance-cost tradeoff. Simulation results demonstrate the effectiveness of RCT-MMSE to combat several practical constraints and provide a flexible distributed precoding framework compared with previous ones.

Ideally, the bi-directional channel in time division duplex (TDD) millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems exhibits reciprocity. However, the involvement of low-cost and non-ideal radio frequency (RF) chains disrupts this reciprocity. Consequently, prior to fully leveraging the advantage of channel reciprocity, it is essential to implement channel calibration. Despite numerous over-the-air calibration methods, such as Argos, the typical least square (LS) are proposed in the literature, none of their criteria directly focus on the calibration performance. To address this gap, we propose a novel deep learning based approach that aims to optimize the calibration performance and introduce device-level intelligence towards 6G networks. To be specific, two cascaded modules are designed in a model-assisted end-to-end manner. Firstly, we propose the double-CNN-based channel denoising module for joint bi-directional channel estimation by exploiting the characteristics of mmWave channel. Secondly, the deep calibration learning module is meticulously designed to obtain the calibration coefficients with the aid of assisted model. This traceable assisted model is established by leveraging the expert knowledge of calibration process, based on which the MetrNet and the CaliNet are designed. Numerical results demonstrate the superior performance of our proposed method compared to existing calibration methods. Particularly, additional simulations and analysis are conducted to verify the effectiveness of the two properly designed modules.

Dual-functional radar-communication (DFRC) is a promising technology in future integrated sensing and communication systems. Since communication and sensing performance need to be taken into consideration for joint radar and communication (JRC) beamforming in the DFRC system, existing approaches mainly transform JRC beamforming problems into convex optimization problems and then solve them with classical convex solvers. These traditional solutions heavily rely on precise channel estimation and entail high computational complexity. In this paper, we investigate a deep learning-based optimization approach for JRC beamforming to enhance the spectral efficiency for communication users and guarantee the probability of detecting targets. To achieve better performance, we leverage the theoretical optimal structures of JRC beamforming and design an effective deep neural network architecture. To further reduce the computational burden in the training phase of neural network, we develope an improved orthogonal beamforming technique. Simulation results verify that our proposed algorithm guarantees the required sensing performance and outperforms numerical algorithms in terms of communication performance. The orthogonal beamforming technique achieves satisfactory performance with low computational complexity.

Channel estimation stands as a pivotal and challenging task for millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) communication system, especially in a time-varying scenario, where exists a massive number of channel coefficients and severe propagation loss due to the Doppler shifts. Conventional estimation schemes may fail to track the fast varying channels and not be able to fully exploit the unique characteristics of mmWave channels in their model designs. In this work, we leverage the Generative Adversarial Networks (GANs) and meticulously design a novel framework named Homogeneous Denoising Generative Adversarial Network (HDnGAN) to tackle the challenge of time-varying channel estimation for mmWave MIMO system. Our framework incorporates the distinctive traits of mmWave channels, such as temporal and spatial correlations, as well as angular sparsity, into the network architecture design. Theoretically, a special case of our proposed HDnGAN with a linear structure is demonstrated to be not inferior to the linear minimum mean squared error (LMMSE) estimator. Numerical simulations underscore the superiority of HDnGAN over existing channel estimation methods, particularly in low signal-to-noise ratio (SNR) regions. Furthermore, it exhibits robustness across varying scenarios. Notably, it remains applicable in out-of-distribution situations and in the absence of ground truth.

From practical considerations in massive multiple-input multiple-output (MIMO) systems, with the involvement of radio frequency (RF) chains, the channel reciprocity no longer holds even under time division duplex (TDD) operation. To fully leverage the advantage brought by TDD systems, channel reciprocity calibration needs to be necessarily investigated. In this paper, we propose the CNN-enhanced calibration method, which is composed of the channel estimation task and the calibration coefficient calculation task. Different from previous works, our method is based on our proposed double-CNN-based bi-directional channel estimator, which is designed specifically for the calibration problem to exploit the bi-directional channel correlation, the spatial correlation, and the angular correlation in millimeter wave (mmWave) channel. Based on this, a formulated LS calibration problem is solved. Numerical results manifest that our proposed method outperforms the existing calibration methods in the literatures.

Cell-free massive multiple-input multiple-output (MIMO) is an attractive network in 6G communications that significantly increases the spectral efficiency. Operating in time-division duplex (TDD) mode, the downlink beamforming is achieved by the estimated uplink channel, which is equal to the downlink channel due to the property of channel reciprocity. However, the involvement of different radio frequency (RF) gains in transceiver antennas renders the whole channel non-reciprocal. Therefore, it is of great necessity to calibrate the bi-directional channel. In this paper, we focus on the issue of over-the-air channel calibration in cell-free system. Taking a toy scenario as an example, we examine the performance differences between the calibration methods of ‘Direct Process’ and ‘Indirect Process’. A novel low-cost calibration method based on spanning tree model is proposed specifically for this distributed AP scenario, where a calibration tree is established to calculate calibration coefficients. Numerical results manifest that higher accuracy of our method is achieved compared to the existing calibration methods in the literatures. Our method is less sensitive to the location of master AP compared to Argos, and practical applications under the impact of phase noise show the priority of our method compared to LS method.

In this paper, we investigate the navigation for unmanned aerial vehicle (UAV)s in the secure communication system, where we design the UAV's navigation/trajectory to ensure the Quality of Service (QoS) with the Base Station (BS) in the existence of multiple unknown-location dynamical eavesdroppers and jammers. To this end, we formulate a UAV trajectory optimization problem to minimize its mission completion time with QoS and security constraints. The imperfect information, dynamic communication environment, and non-convexity make the problem intractable. For these reasons, we propose a novel solution approach, namely Model-Assisted Reinforcement Learning (MARL) algorithm, where the communication system model is embedded into Deep Reinforcement Learning (DRL) framework to ensure secure communication and shorten the learning process. Numerical results show that our proposed methodology can safeguard security and find the shortest way to finish the mission.