Joint access point (AP) clustering and beamforming design is an effective way to improve system performance and reduce signaling overhead for cell-free networks. However, conventional optimization methods usually solved the joint AP clustering and beamforming design by separately handling them, at the cost of high computing resources, especially when quality of service (QoS) constraint is also considered. To this end, this paper proposes a low-complexity unsupervised deep learning method to jointly optimize AP clustering and beamforming design, called as joint clustering and beamforming network (JcbNet). The JcbNet also designs a neural network to handle the QoS constraint to reduce the hyperparameters of loss function, and it introduces a learnable safety distance parameter in the loss function to reduce the violation rate of QoS constraint. In addition, the JcbNet is scalable since the dimensions of parameters and output beamforming vary with the dimension of input channel state information (CSI). The experimental results show that the JcbNet is low-complexity, and achieves a higher sum rate under a smaller number of AP clustering compared to traditional and deep learning algorithms such as weighted minimum mean square error (WMMSE), sparse WMMSE (S-WMMSE) and convolutional neural network (CNN).

User scheduling and beamforming design are two crucial yet coupled topics for multiuser wireless communication systems. They are usually addressed separately with conventional optimization methods. In this paper, cross-layer optimization problem is considered, namely, the user scheduling and beamforming are jointly discussed, subjecting to the requirement of per-user quality of service and the maximum allowable transmit power for multicell multiuser joint transmission networks. To achieve the goal, a mixed discrete-continuous variables combinational optimization problem is investigated with aiming at maximizing the sum rate of the communication system. To circumvent the original non-convex problem with dynamic solution space, we first transform it into a 0–1 integer and continuous variables optimization problem, and then obtain a tractable form with continuous variables by exploiting the characteristics of the 0–1 integer constraints. Finally, the scheduled users and the optimized beamforming vectors are simultaneously calculated by an alternating optimization algorithm. We also theoretically prove that the base stations allocate zero power to the unscheduled users. Furthermore, two heuristic optimization algorithms are proposed respectively based on brute-force search and greedy search. Numerical results validate the effectiveness of our proposed methods, and the optimization approach gets relatively balanced results compared with the other two approaches.

In multiuser communication systems, user scheduling and beamforming (US-BF) design are two fundamental problems that are usually studied separately in the existing literature. In this work, we focus on the joint US-BF design with the goal of maximizing the set cardinality of scheduled users, which is computationally challenging due to the non-convex objective function and the coupled constraints with discrete-continuous variables. To tackle these difficulties, a successive convex approximation based US-BF (SCA-USBF) optimization algorithm is firstly proposed. Then, inspired by wireless intelligent communication, a graph neural network based joint US-BF (J-USBF) learning algorithm is developed by combining the joint US and power allocation network model with the BF analytical solution. The effectiveness of SCA-USBF and J-USBF is verified by various numerical results, the latter achieves close performance and higher computational efficiency. Furthermore, the proposed J-USBF also enjoys the generalizability in dynamic wireless network scenarios.

In wireless networks, the optimization problems generally have complex constraints and are usually solved via utilizing the traditional optimization methods that have high computational complexity and need to be executed repeatedly with the change of network environments. In this paper, to overcome these shortcomings, an unsupervised deep unrolling framework based on projection gradient descent (PGD), i.e., unrolled PGD network (UPGDNet), is designed to solve a family of constrained optimization problems. The set of constraints is divided into two categories according to the coupling relations among optimization variables and the convexity of constraints. One category of constraints includes convex constraints with decoupling among optimization variables, and the other category of constraints includes non-convex or convex constraints with coupling among optimization variables. Then, the first category of constraints is directly projected onto the feasible region, while the second category of constraints is projected onto the feasible region using a neural network. Finally, an unrolled sum rate maximization network (USRMNet) is designed based on UPGDNet to solve the weighted SR maximization problem for the multiuser ultra-reliable low latency communication system. Numerical results show that USRMNet has a comparable performance with low computational complexity and an acceptable generalization ability in terms of the user distribution.

Driven by the explosive growth of Internet of Things (IoT) devices with stringent requirements on latency and reliability, ultra-reliability and low latency communication (uRLLC) has become one of the three key communication scenarios for the 5th generation (5G) and 6G communication systems. In this paper, we focus on the beamforming design problem for the downlink multiuser uRLLC system. Since the strict demand on the reliability and latency, in general, short packet transmission is a favorable way for uRLLC systems, which indicates the classical Shannon’s capacity formula is no longer applicable. With the finite blocklength transmission, the achievable rate is greatly influenced by the reliability and finite blocklength. Using the developed achievable rate formula for finite blocklength transmission, we respectively formulate the problems of interest as the weighted sum rate maximization, energy efficiency maximization, and user fairness optimization by considering the maximum allowable transmission power and minimum rate requirement. These problems considered are non-convex and are hard to obtain the global optimal solution, even for the local optimal solution. To overcome these difficulties, some important insights have been discovered by analyzing the function of achievable rate. For example, an analytical solution of the minimum rate requirement is provided with respective to the signal-to-interference-plus-noise ratio. Based on the discovered results, we provide algorithms to optimize the beamforming vectors and power allocation, which are guaranteed to converge to a local optimum solution to the formulated problems with low computational complexity. Our simulation results reveal that our proposed beamforming algorithms outperform the zero-forcing beamforming algorithm with equal power or water filling allocation widely used in the existing literatures.

In the paper, we consider the probability of applying hyper-spectral image (HSI) processing methods to panchromatic images (PIs), which is a novel yet crucial issue for further analyses. To achieve the purpose, we propose an effective approach for handling PI with HSI unmixing methods. In the approach, HSI simulating process is first implemented to obtain a synthetic HSI from PI. After that, a hyperspectral unmixing algorithm, vertex component analysis, is then applied to extract endmembers that comprise the vertices of the data simplex. Meanwhile, we calculate abundances of HSI by employing least squares method. We will see that the unmixing results, namely endmembers and abundances, can be used for target detection and other applications. Different objects such as ships and cars were successfully extracted from the backgrounds, which demonstrates the efficacy of the proposed approach.