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.

In this article, we propose an efficient deep-neural-network-based relay selection (DNS) scheme to evaluate and improve the end-to-end throughput in wireless-powered cognitive Internet-of-Things (IoT) networks. In this system, multiple energy harvesting (EH) relays are deployed randomly to assist data transmission from a source node to multiple users under practical nonlinearity of the EH circuits. We first design an incremental relaying protocol, where a selected user will request the help from relays if the direct transmission is not favorable. In such a protocol, we develop a deep neural network framework for relay selection and throughput prediction with high accuracy, less channel feedback amount, and short execution time. Simulation results show that the proposed DNS scheme achieves higher throughput than the conventional relay selection methods, while it considerably reduces computational complexity, suggesting a real-time configuration for IoT systems under complex scenarios. Moreover, the proposed DNS scheme achieves the root-mean-square error (RMSE) of 6.6×10-3on the considered dataset, which exhibits the lowest RMSE as compared to the state-of-the-art machine learning approaches.

In this article, we study the physical-layer security (PHY-security) improvement method for a downlink nonorthogonal multiple access (NOMA) system in the presence of an active eavesdropper. To this end, we propose a full-duplex (FD)-enabled NOMA system and a promising scheme, called the minimal transmitter selection (MTS) scheme, to support secure transmission. Specifically, the cell-center and cell-edge users act simultaneously as both receivers and jammers to degrade the eavesdropper channel condition. Additionally, the proposed MTS scheme opportunistically selects the transmitter to minimize the maximum eavesdropper channel capacity. To estimate the secrecy performance of the proposed methods, we derive an approximated closed-form expression for secrecy outage probability (SOP) and build a deep neural network (DNN) model for SOP evaluation. Numerical results reveal that the proposed NOMA system and MTS scheme improve not only the SOP but also the secrecy sum throughput. Furthermore, the estimated SOP through the DNN model is shown to be tightly close to other approaches, i.e., the Monte-Carlo method and analytical expressions. The advantages and drawbacks of the proposed transmitter selection scheme are highlighted, along with insightful discussions.

In this paper, we address the opportunistic scheduling in multitwo user NOMA system consisting of one base station, multinear user, multifar user, and one eavesdropper. To improve the secrecy performance, we propose the users selection scheme, called best‐secure‐near‐user best‐secure‐far‐user (BSNBSF) scheme. The BSNBSF scheme aims to select the best near‐far user pair, whose data transmission is the most robust against the overhearing of an eavesdropper. In order to facilitate the performance analysis of the BSNBSF scheme in terms of secrecy outage performance, we derive the exact closed‐form expression for secrecy outage probability (SOP) of the selected near user and the tight approximated closed‐form expression for SOP of the selected far user, respectively. Additionally, we propose the descent‐based search method to find the optimal values of the power allocation coefficients that can minimize the total secrecy outage probability (TSOP). The developed analyses are corroborated through Monte Carlo simulation. Comparisons with the random‐near‐user random‐far‐user (RNRF) scheme are performed and show that the proposed scheme significantly improves the secrecy performance.