This paper proposes a hybrid user group (HUG) scheme for simultaneous transmitting and reflecting-reconfigurable intelligent surface (STAR-RIS)-aided millimeter wave (mmWave) cell-free massive multiple-input multiple-output (CF mMIMO) systems using rate-splitting multiple access (RSMA), where users in transmission and reflection zones are optimally paired. Nearby APs serve users, and multiple STAR-RISs enhance signals under imperfect SIC. We formulate a max-min spectral efficiency (SE) problem to jointly optimize power allocation, STAR-RIS phase shifts, and user grouping, leading to a mixed-integer non-convex problem. To solve it, we relax discrete variables and decompose the problem into sub-problems, using bisection search for phase shifts and a low-complexity iterative algorithm for power allocation. Simulations show the HUG scheme improves average SE by 14.03%, 18.79%, and 33.42% compared to random grouping, conventional beamforming, and HUG with conventional RIS, respectively.

In this paper, we propose a novel energy-efficient multicast routing protocol using federated learning (FL)-based optimal route selection (FLEMR) in internet of things (IoT)-enabled mobile ad hoc networks (MANETs) with reconfigurable intelligent surfaces (RIS) and cell-free massive MIMO (CF-mMIMO). The proposed FLEMR protocol integrates cross-layer design and federated learning (FL) to improve the network and physical layers performance. Specifically, the cross-layer design combines information from the physical layer, such as mobility (speed and direction), position, remaining energy, and spectral efficiency, with information from the network layer (hop count) to maximize a cost function for optimal route selection. RISs are deployed to improve the strength of the received signals, thus enhancing overall connectivity. To further enhance energy efficiency during data transmission, we design an adaptive transmit power allocation technique that dynamically divides the transmission area into regions and zones based on receiver positions. Furthermore, we design the FL framework to solve two problems: infer the optimal weight values of the cost function to select the multicast route and decide the optimal region and zone for adaptive transmit power allocation. The simulation results show that the proposed FLEMR protocol, integrated with the cross-layer federated learning-based clustering (CFLC) protocol under the reference point group mobility (RPGM) model, establishes more robust multicast routes, demonstrating superior performance in terms of connectivity, scalability, and energy efficiency compared to benchmark protocols.

In this paper, we propose a novel federated blockchain (FedChain)-based clustering protocol to enhance network security and connectivity in flying ad hoc networks (FANETs) with cell-free massive MIMO (CF-mMIMO). By leveraging blockchain technology and federated learning (FL), the cluster can be protected against Sybil attacks, enabling secure cluster formation without increasing the number of control packets. We formulate the cost function maximization problem based on cross-layer design, which integrates physical layer information (mobility, position, channel capacity, and remaining energy) and network layer parameters (connectivity) to optimize the formation of stable clusters with minimal control overhead. Furthermore, we select the optimal cluster heads (CHs) based on the highest remaining energy and velocity-constrained criteria, ensuring long-term stability. To solve the security issue, blockchain technology is adopted to validate transactions among nodes and ensure secure formation by distinguishing legitimate users and Sybil attack nodes. Additionally, we develop a novel FL framework to predict and distinguish node status in real time without additional control packets, improving security and control overhead performance during cluster formation. Simulation results demonstrate that the proposed FedChain-based clustering protocol outperforms the lowest ID (LI), high connectivity degree (HCD), and conventional blockchain-based clustering (CBC) protocols in terms of connectivity, control overhead, and security performance. The results highlight that the FedChain-based clustering protocol provides robust security and connectivity, making it well-suited for dynamic FANET environments.

In this article, we propose novel federated learning (FL) and blockchain-based secure multicast routing (FBSMR) protocol in flying ad hoc networks (FANETs) with cell-free massive MIMO (CF-mMIMO) and simultaneously transmitting and reflecting-reconfigurable intelligent surface (STAR-RIS) effectively avoiding collaborative attacks. The proposed FBSMR protocol integrates FL with blockchain to enhance security and prevent collaborative attacks during the routing process. Besides, by utilizing a cross-layer design, the proposed FBSMR can enhance network security and Quality-of-Service (QoS) performance. Specifically, we implement a blockchain-based approach to support secure multicast routing, which efficiently detects and isolates malicious nodes. By using these techniques, all participating nodes achieve consensus on the validity of routing paths, thereby significantly enhancing overall network security. Besides, we address the cost-minimization problem in the proposed cross-layer design by optimizing the weight values of physical layer information, data link layer information, and network layer information subject to the minimum sequence numbers, maximum end-to-end delay, and hop count constraints. To further enhance the coverage area, improve receive signal quality, and reduce the number of hops, we leverage the capabilities of STAR-RIS technology attached to the AAV (F-STAR-RIS) to refract and reflect incident waves toward desired positions, enabling significant improvements in signal quality and transmission coverage. Additionally, the FL framework is employed for real-time prediction of the secure next node, utilizing local data from each flying access point (F-AP) to predict the optimal next node, STAR-RIS configuration, and phase shift at the STAR-RIS. Simulation results demonstrate that the proposed FBSMR protocol, combined with the FedChain-based clustering protocol, establishes a more secure route against collaborative attacks and outperforms benchmark protocols in terms of connectivity, stability, and security performance.

This paper proposes an adaptive user grouping (AUG) scheme for short-packet communication (SPC) in simultaneous transmitting and reflecting (STAR)-reconfigurable intelligent surface (RIS)-assisted multiple-input multiple-output (MIMO)-non-orthogonal multiple access (NOMA) systems with SWIPT. The information users with different channel conditions are optimally grouped while the energy user harvests the energy from the base station. Besides that, multiple STAR-RISs are deployed to assist the information users in improving the quality of received signals. We formulate the spectral efficiency (SE) maximization of the considered system to optimize the linear precoding matrix, phase shift of the reflection and transmission at STAR-RIS, energy beamforming matrix, and grouping variables. The formulated problem leads to a mixed binary integer programming which is challenging to solve optimally. To tackle this problem, we first relax the integer variable to be continuous and decouple the relaxed problem into two subproblems to alternately tackle the phase shift and beamforming parts. We then propose bisection search and low-complexity iterative algorithms to solve the phase shift and beamforming subproblems with guaranteed convergence at a relative optimum of each subproblem. Towards real-time optimization, we develop a convolutional neural network (CNN) to achieve the optimal solution of the relaxed problem via a quick-inference process. Numerical results demonstrate a SE improvement of 46% in the AUG scheme over the random user grouping one and 78% over the non-user grouping under various settings. Furthermore, the developed CNN model predicts optimal phase shift variables and beamforming matrices with high accuracy compared to conventional methods but in a shorter time.

In this paper, we propose an adaptive user pairing (AUP) scheme in multi-intelligent reflecting surface (IRS)-aided massive multiple-input multiple-output (MIMO)-non-orthogonal multiple access (NOMA) networks. In the AUP scheme, two users with different channel conditions are selected for user pairing while multiple IRSs assist to improve received signal quality at users. We consider the problem of jointly optimizing the precoding matrix, the phase shift of IRSs, and the user pairing element to maximize the overall spectral efficiency (SE) subject to the maximum power budget at the base station (BS) and user-specific quality-of-service (QoS). The SE problem formulated as the maximization of non-concave functions involves a mixed-integer program, which is very challenging to solve optimally. To tackle this problem, we first relax the user pairing elements to be continuous and then transform the formulated problem into an equivalent non-convex problem with a more tractable form. We then apply the iterative algorithm (IA) with low complexity to guarantee convergence at a relative optimum. Towards real-time optimization, we propose a deep learning (DL) framework to predict the optimal solution of the precoding matrix, the phase shift of IRSs, and user pairing elements according to the user’s locations and channel gains. Compared to the conventional optimization method, the DL-based optimization framework can achieve the optimal solution within a very short time via an efficient inference process. Numerical results verify that the proposed algorithm improves the SE over state-of-the-art approaches. Moreover, the effects of essential parameters such as the total BS transmit power, the number of UEs, IRSs, and BS’s antennas on the system are discussed and evaluated to show the effectiveness of the proposed scheme in balancing resource utilization.