Wi-Fi rate adaptation is a challenging problem due to the complex and dynamic nature of wireless channels. Existing solutions often rely on heuristics or machine learning techniques. In this work, we propose a novel rate adaptation algorithm, WiFi-CUTS, which employs a cascaded unimodal Thompson sampling (CUTS) multi-armed bandit (MAB) approach to optimize the transmission rate for IEEE 802.11ac links. We develop and implement WiFi-CUTS in numerical simulations and real-world testbed experiments, demonstrating its effectiveness in achieving higher throughput than other multi-armed bandit (MAB) algorithms and the default rate adaptation algorithm in the Linux kernel, Minstrel-HT. Our shielding box experiment results show that WiFi-CUTS achieves a throughput gain of at least 7%, on average 15% and up to 37% over Minstrel-HT in our testbed experiments for medium and high signal-to-noise ratio (SNR) channels. Our over-the-air experiments show a throughput gain of at least 18.2% over Minstrel-HT. Moreover, the proposed CUTS-based algorithms achieve at least a 56% higher throughput than Minstrel-HT in the initial 0.7 s, due to their faster convergence speed. Both indicate that CUTS-based approaches can effectively address the growing demands of next-generation Wi-Fi networks and provide significant improvements over Minstrel-HT.

The emerging low-altitude economy leverages airspace below 1000 meters for intensive commercial and social aerial activities, where integrated sensing and communication (ISAC) service in 6G network for aircraft is critical to ensuring safe and efficient operations. However, aircraft often operate under constrained wireless resources, particularly in areas with limited or no network coverage. In such settings, exhaustive sensing and data communication among neighboring nodes lead to uncoordinated competition and prohibitive overhead. This paper investigates the ISAC service modeling and scheduling in aerial-vehicle-to-everything (Aerial-V2X) networks, which provides continuous high-accuracy sensing without compromising communication throughput under constrained resource budgets. First, we design a reconfigurable ISAC waveform tailored for aircraft, enabling flexible resource partitioning for both cellular communication (aerial vehicle-to-infrastructure, A-V2I) and cooperative sensing (aerial vehicle-to-vehicle, A-V2V). Second, we formulate a joint sensing-communication service model under this waveform and cast the optimization problem in a partially observable Markov decision process (POMDP). Third, a multi-agent deep reinforcement learning (MADRL) approach is developed to perform decentralized scheduling of sensing actions for each aircraft, minimizing time-frequency resource consumption. Experiments and trace-driven evaluations demonstrate that the proposed method can reduce sensing overhead by up to 70% compared to benchmark policies, while maintaining satisfactory communication and sensing performance.

Smaller cells have been the most important contributor to throughput improvement since the birth of cellular networks. They are likely to evolve further in the shift to cell-free massive MIMO (CF mMIMO), where multiple closely placed access points (APs) collaborate to serve users. This scheme is particularly suitable for millimeter wave (mmWave) communication, which enables very high data rates with its large bandwidth, but encounters severe challenges of high path loss and blockage. The CF mMIMO network is a good countermeasure to these two challenges by utilizing overlapping signals from different APs and macro-diversity. In this work, we demonstrate that mmWave CF mMIMO network optimization is largely an AP-user assignment problem. To solve this large-scale, nondifferentiable problem, we propose an unsupervised machine learning (ML) approach, which looks for the optimal solution autonomously without labels. A customized graph neural network architecture tailored to the problem properties is proposed, which enables distributed optimization without a central unit, allows for a varying number of users, and hierarchical permutation-equivariance of APs and users. A teacher-student model is applied to prune the graph, where the teacher model uses a fully connected graph for maximum performance, and the student model uses a pruned graph to reproduce the teacher's behavior with less communication in fronthaul. Moreover, a special training method is designed, which relaxes the combinatorial problem to a continuous one. In this way, we can apply gradient-based neural network training. An entropy-inspired penalty is introduced to make the relaxed problem equivalent to the original one. The analytical augmented Lagrangian method is combined with ML for the constrained optimization. Simulation results show that the proposed approach outperforms baselines in both performance and computation time. In addition, with a properly pruned graph, the proposed approach performs inference in a distributed manner with sparse message passing between APs, realizing a low signaling overhead in fronthaul, and a performance close to the fully connected graph.

Non-orthogonal multiple access (NOMA) is a promising multiple access technique. Its performance depends strongly on the wireless channel property, which can be enhanced by reconfigurable intelligent surfaces (RISs). In this paper, we jointly optimize base station (BS) precoding and RIS configuration with unsupervised machine learning (ML), which looks for the optimal solution autonomously. In particular, we propose a dedicated neural network (NN) architecture RISnet inspired by domain knowledge in communication. Compared to state-of-the-art, the proposed approach combines analytical optimal BS precoding and ML-enabled RIS, has a high scalability to control more than 1000 RIS elements, has a low requirement for channel state information (CSI) in input, and addresses the mutual coupling between RIS elements. Beyond the considered problem, this work is an early contribution to domain knowledge enabled ML, which exploit the domain expertise of communication systems to design better approaches than general ML methods.

Cell-free massive multiple-input multiple-output symbiotic radio (CF-mMIMO-SR) is a promising technology to address the requirements of high-rate and spectrum-efficient communication for the Internet of Things (IoT). However, in the conventional CF-mMIMO-SR system aided by backscatter devices (BDs), the backscatter link is impacted by double fading without any supplementary compensation, resulting in significantly low spectral efficiency (SE) on the backscatter link. To address this issue, we propose the usage of reconfigurable intelligent surfaces (RISs) instead of BD for symbol-level reflection on the backscatter link, leading to a novel RIS-aided CF-mMIMO-SR (RIS-CF-SR) system. In this paper, we conduct a comprehensive analysis of the RIS-CF-SR system considering different levels of cooperation among the access points (APs). Specifically, we analyze the uplink SEs of four different implementations with arbitrary linear processing on both the direct and backscatter links. Moreover, we investigate different signal cancellation schemes based on full or local channel state information (CSI) to improve the SE of the backscatter link. Through the simulation results, we find that RISs can significantly improve the SE of the backscatter link due to the large number of reflection elements, whereas additional appropriate signal processing schemes are required for the direct link. More specifically, from Level 1 to Level 3, RIS-CF-SR does not have significant advantage in SE over BD-CF-SR on the direct link. At Level 4, RIS-CF-SR can outperform BD-CF-SR on the direct link with the MMSE combining scheme.

space-division multiple access (SDMA) plays an important role in modern wireless communications. Its performance depends on the channel properties, which can be improved by reconfigurable intelligent surfaces (RISs). In this work, we jointly optimize SDMA precoding at the base station (BS) and RIS configuration. We tackle difficulties of mutual coupling between RIS elements, scalability to more than 1000 RIS elements, and high requirement for channel estimation. We first derive an RIS-assisted channel model considering mutual coupling, then propose an unsupervised machine learning (ML) approach to optimize the RIS with a dedicated neural network (NN) architectureRISnet, which has good scalability, desired permutation-invariance, and a low requirement for channel estimation. Moreover, we leverage existing high-performance analytical precoding scheme to propose a hybrid solution of ML-enabled RIS configuration and analytical precoding at BS. More generally, this work is an early contribution to combine ML technique and domain knowledge in communication for NN architecture design. Compared to generic ML, the problem-specific ML can achieve higher performance, lower complexity and permutation-invariance.

Millimeter wave (mmWave) cell-free massive MIMO (CF mMIMO) is a promising solution for future wireless communications. However, its optimization is non-trivial due to the challenging channel characteristics. We show that mmWave CF mMIMO optimization is largely an assignment problem between access points (APs) and users due to the high path loss of mmWave channels, the limited output power of the amplifier, and the almost orthogonal channels between users given a large number of AP antennas. The combinatorial nature of the assignment problem, the requirement for scalability, and the distributed implementation of CF mMIMO make this problem difficult. In this work, we propose an unsupervised machine learning (ML) enabled solution. In particular, a graph neural network (GNN) customized for scalability and distributed implementation is introduced. Moreover, the customized GNN architecture is hierarchically permutation-equivariant (HPE), i.e., if the APs or users of an AP are permuted, the output assignment is automatically permuted in the same way. To address this combinatorial problem, we relax it to a continuous problem, and introduce an information entropy-inspired penalty term. The training objective is then formulated using the augmented Lagrangian method (ALM). The test results show that the realized sum-rate outperforms that of the generalized serial dictatorship (GSD) algorithm and is very close to an upper bound in a small network scenario, while the upper bound is impossible to obtain in a large network scenario.

This work presents a machine learning approach to optimize the energy efficiency (EE) in an interference network. This optimization problem is non-convex and it is difficult to find its global optimum. We propose an unsupervised machine learning framework to approach the global optimum. While the training of the neural network (NN) takes moderate time, applying the trained model requires very low computational complexity. In particular, we introduce a novel objective function based on the reparameterization trick, which makes it possible to prune poor local optima to converge to the global optimum. Furthermore, we design a dedicated NN architecture SINRnet for signal-to-interference-noise ratio (SINR)-related optimization problems in interference networks, which is permutation-equivariant and classifies channels according to their positions in the SINR expression. In this way, we encode our domain knowledge into the NN design. Training and testing results show that the proposed method outperforms the successive convex approximation (SCA) algorithm, achieving an EE close to the global optimum found by the branch-and-bound algorithm and with reasonable computational effort. Thus, the proposed approach finds a balance between computational complexity and performance.

The reconfigurable intelligent surface (RIS) is a promising technology that enables wireless communication systems to achieve improved performance by intelligently manipulating wireless channels. In this paper, we consider the sum-rate maximization problem in a downlink multi-user multi-input-single-output (MISO) channel via space-division multiple access (SDMA). Two major challenges of this problem are the high dimensionality due to the large number of RIS elements and the difficulty to obtain the full channel state information (CSI), which is assumed known in many algorithms proposed in the literature. Instead, we propose a hybrid machine learning approach using the weighted minimum mean squared error (WMMSE) precoder at the base station (BS) and a dedicated neural network (NN) architecture, RISnet, for RIS configuration. The RISnet has a good scalability to optimize 1296 RIS elements and requires partial CSI of only 16 RIS elements as input. We show it achieves a high performance with low requirement for channel estimation for geometric channel models obtained with ray-tracing simulation. The unsupervised learning lets the RISnet find an optimized RIS configuration by itself. Numerical results show that a trained model configures the RIS with low computational effort, considerably outperforms the baselines, and can work with discrete phase shifts.

This work presents a machine learning approach to optimize the energy efficiency (EE) in a multi-cell wireless network. This optimization problem is non-convex and its global optimum is difficult to find. In the literature, either simple but suboptimal approaches or optimal methods with high complexity are proposed. In contrast, we propose an unsupervised machine learning framework to approach the global optimum. While the neural network (NN) training takes moderate time, application with the trained model requires very low computational complexity. In particular, we introduce a novel objective function based on stochastic actions to solve the non-convex optimization problem. Besides, we design a dedicated NN architecture SINRnet for the power allocation problems in the interference channel that is permutation-equivariant. We encode our domain knowledge into the NN design and shed light into the black box of machine learning. Training and testing results show that the proposed method without supervision and with reasonable computational effort achieves an EE close to the global optimum found by the branch-and-bound algorithm and outperform the successive convex approximation (SCA) algorithm. Hence, the proposed approach balances between computational complexity and performance.

With the increasing application of internet of things (IoT), the number of wirelessly transmitting devices is on a rise. It is important that the energy efficiency (EE) is maximized to reduce interference and save energy. This work explores the possibility of power control for maximum EE in wireless interference networks using reinforcement learning (RL) techniques. We apply the soft actor-critic (SAC) algorithm based on entropy regularization that allows to escape local optima and foster exploration. This enables us to solve the energy efficient power control problem with reduced complexity. We demonstrate that the obtained solutions are close to the global optimum. In contrast to supervised machine learning (ML) techniques, we do not need any kind of labeled data in the training phase. The model free approach and the unsupervised nature of RL therefore reduce the required computational effort and has a better scalability as a consequence.

Data-driven optimization of transmitters and receivers can reveal new modulation and detection schemes and enable physical-layer communication over unknown channels. Previous work has shown that practical implementations of this approach require a feedback signal from the receiver to the transmitter. In this paper, we study the impact of quantized feedback on data-driven learning of physical-layer communication. A novel quantization method is proposed, which exploits the specific properties of the feedback signal and is suitable for non-stationary signal distributions. The method is evaluated for linear and nonlinear channels. Simulation results show that feedback quantization does not appreciably affect the learning process and can lead to similar performance as compared to the case where unquantized feedback is used for training, even with 1-bit quantization. In addition, it is shown that learning is surprisingly robust to noisy feedback where random bit flips are applied to the quantization bits.

The widespread application of unmanned aerial vehicles (UAVs) urgently requires an effective tracking algorithm as technical support. Particle filter has been widely applied in maneuvering target tracking, however, there has been no suitable solution to the trade-off between weight degeneracy and particle diversity during the process of resampling. In this paper, we propose an improved particle filter algorithm based on systematic resampling with additional random perturbation. This method ensures that particle filter maintains particle diversity and reduces weight degeneracy under environments with different noise types, simultaneously. The simulation results demonstrate that the proposed algorithm generates more accurate filtered trajectory than generic particle filter, especially under the environment with low noise.

The terahertz (THz) communication utilizes the frequency spectrum above 300 GHz and is widely considered as a promising solution to the future high-speed short-range wireless communication beyond millimeter wave communication. While providing tens of gigahertz bandwidth, it is subjected to high-propagation path loss, inter-symbol, and inter-user interferences. The massive multiple-input-multiple-output (MIMO) can be applied to address these problems by cooperation between many access point antennas. However, the THz channel characteristics, including high-propagation path loss, frequency selectivity, and a big number of samples per channel impulse response, require carefully tailored algorithm for massive MIMO signal processing. In this paper, we propose a single carrier minimum mean square error precoding and detection algorithm for frequency selective THz channels. The MIMO signal transmission is described with the block matrices. A gain control heuristic is introduced to reduce the complexity. The sparsity property of the channel is utilized to construct sparse channel matrices and the least square QR algorithm is applied to efficiently solve the problems. Besides the uniform antenna array, the hybrid array consisting of several subarrays is considered as well. The simulation results show that the massive MIMO array can provide a satisfactory performance in terms of bit error rate.

A measurement campaign has been carried out in a reference indoor environment - a medium-size meeting room - using an ultra-wideband channel sounder operating at 3 different frequency bands: 10 GHz, 60 GHz and 300 GHz. Automatic rotational units are used at Tx and Rx side to perform a full horizontal scanning with directional antennas, in order to achieve a double-directional channel characterization. Preliminary results show that multipath is mainly affected by few single or double-bounce components, and significant contributions may come from objects other than the walls, e.g. TV monitor and entrance door. Most of the contributions are clearly identifiable at all the considered frequencies, although they appear to be stronger at 60 GHz compared to 10 GHz. The radio channel's multipath richness appears to be frequency dependent, and in particular it decreases when comparing 60 GHz to 300 GHz.

The millimeter and sub-millimeter wave communication is a promising solution to future indoor multi-gigabit wireless communications because of its huge available bandwidth. One of the key difficulties is the hu- man blockage effect since the human body can no longer be considered as being "transparent" as at lower frequencies. In this paper a study of statistical characteristics of this problem is presented. At first, broadband measurements of human blockage are provided. Afterwards, a realis- tic mobility model for indoor movements of humans is adopted and elliptic cylinders are applied to approximate human bodies in ray-launching simulations. Consequently, the distributions of Line-Of-Sight (LOS) path and blockage durations as well as blockage numbers are obtained by simulations. Finally, the system performance in presence of the distributed antennas is evaluated.

Angle of arrival (AoA) estimation is required by adaptive directive antennas in order to realize a high antenna gain, which is necessary for future indoor terahertz communications due to its extremely high path loss. This paper proposes an AoA estimation algorithm using belief propagation in a dynamic scenario, where the user equipment (UE) is moving during the data transmission, based on the space-time correlations of AoA change. The temporal correlation of AoA change is due to the limited moving speed and statistical movement pattern. Furthermore, if we have distributed antennas or hybrid massive multiple-input-multiple-output (MIMO) array, the AoA changes of different antennas reveal spatial correlation because all the AoA changes are caused by the same spatial displacement of UE. This spatial correlation is utilized in this paper to further improve the estimation accuracy by passing messages between antennas and combining the intrinsic estimate by each antenna and extrinsic information from other antennas. In order to demonstrate the algorithm performance, a distributed antenna system and a hybrid massive MIMO array (an array of multiple directive antenna arrays) are considered as application scenarios. The simulation results show that the cooperative estimation brings significant advantage in both scenarios in respect of mean effective antenna gain and level crossing rate.