This paper aims to enhance the performance of Vehicular Platooning (VP) systems integrated with Wireless Federated Learning (WFL). In highly dynamic environments, vehicular platoons experience frequent communication changes and resource constraints, which significantly affect information exchange and learning model synchronization. To address these challenges, we first formulate WFL in VP as a joint optimization problem that simultaneously considers Age of Information (AoI) and Federated Learning Model Drift (FLMD) to ensure timely and accurate control. Through theoretical analysis, we examine the impact of FLMD on convergence performance and develop a two-stage Resource-Aware Control framEwork (RACE). The first stage employs a Lagrangian dual decomposition method for resource configuration, while the second stage implements a multi-agent deep reinforcement learning approach for vehicle selection. The approach integrates Multi-Head Self-Attention and Long Short-Term Memory networks to capture spatiotemporal correlations in communication states. Experimental results demonstrate that, compared to baseline methods, the proposed framework improves AoI optimization by up to 45%, accelerates learning convergence, and adapts more effectively to dynamic VP environments on the AI4MARS dataset.

Reconfigurable Intelligent Surface (RIS)-assisted uncrewed Aerial Vehicle (UAV) communications have been realized as essential to space-air-group system integration in the 6 G technology landscape. Trajectory planning plays a crucial role in RIS-assisted UAV communications to face the challenges of UAV’s limited power capacities and dynamic wireless channels. Existing solutions assume complete channel state information, focus on single-rotor UAVs, and rely heavily on time-consuming training processes for machine learning; thus, they lack applicability to deal with highly dynamic real-world scenarios. To fill these research gaps, we aim to characterize RIS-assisted UAV communications and design responsive and accurate UAV trajectory planning algorithms in this paper. We first develop a communication model with incomplete information and an energy consumption model for quadrotor UAVs. We then formulate UAV trajectory planning as an optimization problem to minimize UAV’s energy consumption while maintaining communication throughput. To solve this problem, we design an acceleration framework,FedX, for reinforcement learning (RL) solvers and present two fast trajectory planning algorithms, FedSAC and FedPPO, as instantiations of theFedXframework. Our evaluation results indicate that the proposed framework is effective and efficient–more than 3 times faster with 5 agents and 7 times faster with 10 agents than standard RL algorithms, making it suitable for using RL solvers within wireless networks and mobile computing environments. We also discuss and identify the pros and cons of our proposed framework.

This paper presents a transformer-driven resource allocation strategy to optimize channel assignment and power allocation in multi-carrier non-orthogonal multiple access (NOMA) downlink systems, aiming to maximize the sum data rate. Our approach configures the system to support two users per channel. We employ an attention-based deep learning model, specifically an encoder-only transformer, to process the channel-gain-to-noise ratio matrix and derive the optimal channel-assignment matrix. The transformer model includes a tailored loss function that addresses the requirements of the output channel-assignment matrix, precisely steering the optimization to meet the system demands. Simulation results demonstrate the superior performance of our method, confirming its effectiveness in enhancing wireless communication optimization through the integration of deep learning techniques.

Molecule design is the process of discovering potential compound candidates for drug discovery. Deep learning technique shows significant advantages in data mining and can be used for molecule design. However, most drug discovery projects are limited to low-data situations, and it is difficult to train deep learning neural networks. This paper proposes a novel drug design system that is based on deep learning. It adopts one-shot learning and reinforcement learning, and it can operate under low-data conditions. Once trained, the system can generate new molecules with the desired properties.

Establishing trustworthy relationships among the objects greatly improves the effectiveness of node interaction in the social Internet of Things (IoT). It helps nodes overcome perceptions of uncertainty and risk. However, there are limitations in the existing trust models. In this paper, a comprehensive model of trust is proposed that is tailored to the social IoT. The model includes ingredients such as trustor, trustee, goal, trustworthiness evaluation, decision, action, result, and context. Building on this trust model, we clarify the concepts of trust in the social IoT in five aspects such as: (1) mutuality of trustor and trustee; (2) inferential transfer of trust; (3) transitivity of trust; (4) trustworthiness update; and (5) trustworthiness affected by dynamic environment. With network connectivities that are from real-world social networks, simulations are conducted to evaluate the performance of the social IoT operated with the proposed trust model. An experimental IoT network is used to further validate the proposed trust model.

A radio-frequency (RF) energy harvester collects the radiated energy from nearby wireless information transmitters. Multiple wireless transmitters concentrate their radiation on the RF energy harvester while satisfying the basic requirement of the information links. To achieve this, a deep learning method is proposed for the multiuser transmission. A deep neural network (DNN) is implemented in each wireless transmitter. The DNNs are trained offline with simulated channels and applied online to generate transmit covariance matrices that meet the communication requirement and approach the maximum sum received power at the RF energy harvester.

A multi-antenna wireless transmitter communicates with its information receiver while beaming the radiated power to multiple nearby radio-frequency energy harvesters. The transmitter knows the channel to the information receiver but not the ones to the energy harvesters. By designing its transmit covariance matrix, the transmitter maximizes the minimum harvested power among the multiple energy harvesters while maintaining the information rate toward the receiver. To achieve this, we introduce a simplified channel vector from the transmitter toward the energy harvester. It can be estimated through particular transmissions and very limited feedback from the energy harvester to the transmitter. Once the transmitter obtains the simplified channel vectors, it can find the optimal transmit power allocation. To avoid high computational complexity, we propose a method to find the optimal power allocation with a deep neural network instead of solving a convex optimization problem. The simplified channel vectors are the input to the deep neural network. The neural network is trained offline with a large number of simulated data. Simulation results validate the method and show its superior performance compared with the convex optimization approach.

Devices with the capability of radio-frequency energy harvesting can collect the radiated energy from adjacent wireless energy transmitters. If the multi-antenna transmitter knows the vector channel to the energy harvester, it can design an optimal transmit covariance matrix that satisfies the energy harvesting requirement. However, it is impractical for the energy harvester to estimate the channel. In this paper, we propose a method to design the wireless transmission with a neural network. The transmitter uses a set of special beam patterns and the energy harvester measures the received power and feeds the power values back to the transmitters. The neural network then takes in the power values and outputs the transmit covariance matrix that can meet the energy harvesting requirement. The neural network is trained offline with a large number of simulated data. Simulation results validate the proposed method and show better performance than other wireless energy transmission methods.

Energy efficiency is an important design criterion for wireless communications. As parallel frequency channels are used for multiuser transmission, different channel bandwidth and power can be applied to transmit signals to different users. Channel bandwidth assignment and transmit power allocation are optimized to maximize the sum information rate with the total bandwidth budget, the total transmit power budget, and the user-specific rate requirements. Moreover, with variable total transmit power, the energy efficiency is measured as the maximum sum rate per unit of power used. In this paper, with fixed or flexible bandwidths of the user frequency channels, effective methods are developed to find the total transmit power along with the resource (bandwidth and power) allocation for maximum energy efficiency. This resource allocation ensures that, while each user's minimum rate requirement is satisfied, all of the excess resource of spectrum and transmit power is dedicated to the one user with the best channel quality. Simulation and experimental results validate the optimal solution of total transmit power along with resource allocation that supports the energy-efficient multiuser transmission.

A social approach can be exploited for the Internet of Things (IoT) to manage a large number of connected objects. These objects operate as autonomous agents to request and provide information and services to users. Establishing trustworthy relationships among the objects greatly improves the effectiveness of node interaction in the social IoT and helps nodes overcome perceptions of uncertainty and risk. However, there are limitations in the existing trust models. In this paper, a comprehensive model of trust is proposed that is tailored to the social IoT. The model includes ingredients such as trustor, trustee, goal, trustworthiness evaluation, decision, action, result, and context. Building on this trust model, we clarify the concepts of trust in the social IoT in five aspects such as: 1) mutuality of trustor and trustee; 2) inferential transfer of trust; 3) transitivity of trust; 4) trustworthiness update; and 5) trustworthiness affected by dynamic environment. With network connectivities that are from real-world social networks, a series of simulations are conducted to evaluate the performance of the social IoT operated with the proposed trust model. An experimental IoT network is used to further validate the proposed trust model.

Passive radio-frequency (RF) energy harvesting collects the radiated energy from adjacent wireless information transmitters instead of using a dedicated wireless power source. In this paper, we investigate the scenario where a wireless transmitter communicates with its information receiver while intentionally focusing the radiated power to the RF energy harvesters. The wireless transceivers are equipped with multiple antennas, and each of the energy harvesters has one receive antenna. With an appropriate design of the transmit covariance matrix, the wireless transmitter transfers sufficient energy to the energy harvesters with a guarantee on the information rate to the communication receiver. When multiple RF energy harvesters are present, we address the trade-off between net energy harvesting rate and fairness with the dynamic of the energy harvesting network. Simulation results compare the algorithms and evaluate the performance of passive RF energy harvesting.

In a MIMO cognitive radio network, multiple secondary users sense the spatial channels and share the spectrum use with incumbent primary users. Each secondary transmitter competes with others to increase its own information rate while generating limited total interference to the primary receivers. In order to maximize the sum-rate of the cognitive radio network, the problem of secondary user transmission is modeled as a cooperative game. The strategy of each secondary user is the transmit covariance matrix, and the utility is an approximation of the information rate. The secondary users negotiate over the allocation of the interference budget and reach at a bargaining solution that maximizes the network utility. With well-designed individual utility and network utility functions, the bargaining solution is unique and Pareto optimal. An efficient distributed algorithm is developed that converges quickly to the optimal solution with moderate signaling within the network. Numerical results show the performance improvement in sum-rate of the MIMO cognitive radio network at the bargaining solution of the cooperative game compared with the Nash-equilibrium solution of the non-cooperative game.

Non-contiguous OFDM is a promising technique for cognitive radio systems. Nevertheless, the sidelobes of the OFDM-modulated tones cause the out-of-band power (OBP) which can induce large interference to the incumbent communication systems. Another major drawback of OFDM-based systems is the high peak-to-average power ratio (PAPR). In this paper, two algorithms are proposed to jointly reduce the OBP and the PAPR based on the method of alternating projections onto convex sets (POCS). Several OFDM subcarriers are reserved to accommodate the adjusting weights that reduce the OBP and the PAPR. In the first algorithm, the adjusting weights are projected onto two convex sets that are defined according to the OBP and the PAPR limits. Each POCS iteration requires a convex optimization process. In the second algorithm, the frequency-domain OFDM symbol is projected onto multiple convex sets and the adjusting weights are separated into two groups for OBP and PAPR reductions, respectively. The adjusting weights can be obtained in analytical forms so that the computational complexity is lowered. Simulation results show that, within just a few POCS iterations, the proposed algorithms can achieve good performance in the joint reduction of the OBP and the PAPR.

In a MIMO cognitive radio network, multiple secondary users sense the spatial channels and share the spectrum with incumbent primary users. Each secondary transmitter competes with others to increase its own information rate while limiting interference to the primary receivers. In this paper, we consider the interference constraint as the total interference power at the primary receiver caused by all the secondary transmissions. The problem of optimal secondary transmissions is modeled as a network utility maximization problem. The network utility function takes the weighted sum or the product of the maximum information rates achievable by the secondary users. With approximation that decouples the individual utilities of different secondary users, the network utility maximization problem becomes convex and has a unique solution. Cooperative game is adopted for the secondary transmissions in order to reach a Pareto-efficient equilibrium. A distributed algorithm is further developed that converges quickly to the Nash bargaining solution with moderate signaling within the secondary user network.

In a cognitive radio network, it is indispensable to assign common control channels for group operations of the secondary users of the spectrum. The assignment requires that multiple secondary users establish the least amount of frequency channels among them while each chooses a channel that has minimum interference to its nearby primary users. We model this problem as a strategic game and design its utility function such that the game is a potential game. A set of pure Nash equilibria are found by locating the local optima of the potential function. We develop sequential and asynchronous updates of game players' strategies using the best response dynamic. In order for the search to escape the local optimum and reach the global optimum of the potential function, we adopt simulated annealing in the sequential and asynchronous updates of the strategies. The optimal assignment of the common control channel is obtained accordingly and the convergence property is analyzed for these updating schemes.

Real-time network applications depend on schedulers to guarantee the quality of service (QoS). Conventional real-time schedulers focus on the timing constraints but are much less effective in satisfying the security requirements. In this paper, we propose an adaptive security-aware scheduling system for packet switched networks using a real-time multi-agent design model. The proposed system combines real-time scheduling with security service enhancement. The scheduling unit uses the differentiated-earliest-deadline-first (Diff-EDF) scheduler and the security enhancement scheme adopts a congestion control mechanism. The required QoS is guaranteed for different types (audio and video) of real-time data flows, while the packet security levels are adaptively enhanced according to the feedbacks from the congestion control module. Compared with the IPsec protocol, the proposed scheme reduces the number of pending packets at the destinations. In implementation, the proposed scheme can overload the priority code point and the virtual-LAN identifier fields of the IEEE 802.1Q frame format, hence eliminating the overhead of the security associations performed by the IPsec protocol.

Army ground vehicles often operate in extremely severe environmental and battlefield conditions. Condition Based Maintenance (CBM) allows maintenance to be performed based on evidence of need provided by reliability modeling and/or other enabling technologies, thus reducing maintenance costs and increasing vehicle availability. A fuzzy model is developed to diagnose the axle fatigue of light trucks. The extraction of the fuzzy rules is based upon expert knowledge and a linear damage model. Training data will be used to modify the membership functions and the fuzzy If-Then rules to improve the quality of the fuzzy model for fault diagnostics. The improvement of the fuzzy model will be carried out using re-clustering operation and membership function optimization.

In MIMO cognitive radio networks, the secondary users are in cognizant of the spatial channels toward the primary users. Based on the knowledge of the interference channel toward the primary receivers and the channel toward its intended receiver, the secondary transmitter adjusts its transmission spatial spectrum in order to maximize its own information rate while limiting interference to the primary receivers. This paper considers the practical case where only the covariance of the time-varying channel matrix can be fed back to the secondary transmitter through a low-rate feedback channel. The optimal transmission is derived when either transmit power constraint or interference power constraint is imposed. Under both constraints, a suboptimal transmission scheme is proposed for the cognitive radio network. Simulation results show the average information rate per secondary user at the Nash equilibrium, which is compared with the rate in the case of perfect feedback of the channel state information.

Internet protocol security (IPsec) provides real-time IP packets with confidentiality security service, making them robust against snooping security threats. Conventionally, the security level provided by such protocol cannot be modified according to the status of the network. In this paper, we propose a security-aware scheduling algorithm for a heterogeneous packet switched network. It provides real-time packet flows with guaranteed quality of service (QoS) while adaptively controls the packet's confidentiality security service level. The proposed scheme is modeled using the object-oriented multi-agent methodology. By applying a buffer estimation technique at the network's end nodes, the algorithm provides a real-time network congestion control hence satisfying the network performance metrics. In order to minimize the overhead of network association performed by the IPsec, the algorithm overloads the priority code point fields of the IEEE 802.1Q tagged frame format. This approach helps meet both QoS and security requirements for real-time data flows.

Army ground vehicles often operate in extremely severe environmental and battlefield conditions. There are challenges for the reliability of the military ground vehicle fleet, which need to be addressed. Condition Based Maintenance (CBM) allows maintenance to be performed based on evidence of need provided by reliability modeling and/or other enabling technologies, thus reducing maintenance costs and increasing vehicle availability. The architecture of the Intelligent Vehicle Health Management System (IVHMS) for light trucks is presented. A fuzzy model is developed to diagnose the axle fatigue of the vehicle. The extraction of the fuzzy rules is based upon expert knowledge and a linear damage model. Training data will be used to modify the membership functions and the fuzzy If-Then rules to improve the quality of the fuzzy model for fault diagnostics. The improvement of the fuzzy model will be carried out using re-clustering operation and membership function optimization.

Turbo equalization that cooperates with channel prediction and iterative channel estimation is investigated for mobile broadband communications. Frames of information bits are encoded, interleaved, and mapped to symbols for transmission over time-varying radio channels. The Turbo receiver consists of a maximum a posteriori probability equalizer/demapper and a soft- input soft-output maximum a posteriori probability decoder. With initial channel estimates and sparse pilot insertion across many frames, the receiver predicts the channel of the current frame. The effect of error propagation of channel prediction is mitigated by the de-interleaver that is embedded in the Turbo receiver. The predicted and interpolated channel is refined through the channel estimator that uses the soft estimates of the symbols at each Turbo iteration. Due to the bandlimiting feature of the varying channel, the estimation errors are smoothed by the low-pass filters that follow the channel estimator. Simulation results show that incorporating Turbo equalization with channel prediction and iterative channel estimation can combat fast channel variation and improve reception performance.

This paper addresses cooperative localization for mobile ad-hoc networks that benefits from the node velocity estimation. Given pair-wise range measurement and relative speed measurement between communicating nodes, the relative node positions are estimated using an extended Kalman filter. The state-space equation of the Kalman filter incorporates the node positions with their velocities. The measurement equation takes into account the log-normal distribution of the received signal power and the Gaussian distribution of the relative speed measurement error. Distributed algorithm is derived for practical use. The simulation results show the performance of the network localization with the assistance of node velocity estimation. The velocities are, however, not tracked using the Kalman filter; Separated method is proposed to estimate the node velocities.

The unmanned aerial vehicle can be an efficient and economical solution to real-time surveillance of highway traffic. This paper describes a data link that connects the camera onboard an unmanned aerial vehicle to the monitoring terminals in the office of the Michigan Department of Transportation. A video signal captured by the surveillance camera can be either displayed on the terminals in real time, or stored on ground for future off-line analysis. The video signal is relayed via available mobile communication networks. An addition server is used in practice to guarantee the consistency of data flow and high throughput of the communication channel.

This paper proposes a scheme for position estimation of randomly deployed sensor nodes in a wireless sensor network. Without GPS capability on any of the sensors, the position estimation is facilitated by beacons that move within the network. The beacons are equipped with GPS and can broadcast messages that contain the beacon identifiers and their current positions. With erroneous boundary beacon positions captured at the sensor, the sensor calculates its own position iteratively and updates the estimates upon newly acquired beacon positions. Practical implementation issues are discussed and simulation results show that the proposed iterative approach converges quickly even with beacon positions that have large errors.

Spectrum sensing is crucial for dynamic spectrum management systems. In this paper, we propose a scheme that utilizes the guard interval of OFDM symbol at the transmitter for spectrum sensing. The cyclic prefix is not inserted in the guard interval at the transmitter, whereas the circulant convolution is secured at the OFDM receiver through the proposed mechanism. Simulation results show that the scheme can be implemented with no impact on the BER under various channel conditions, and detection of incumbent DTV signal is possible in the OFDM guard interval. In addition, we develop enhancements to the circulant convolution preserving mechanism for handling the transceiver imperfections in practice.

A new approach to adaptive downlink beamforming to combat fast Rayleigh fading is presented. In this approach, the antennas at the base transceiver station form transmit beam patterns according to the prediction of downlink channels. The channel prediction is a linear prediction based on the autoregressive model, which is downsampled to extend the memory span given fixed model order. For a wideband code-division multiple-access downlink, pre-RAKE transmission is employed to achieve the multipath diversity gain. In particular, we combine pseudoinverse directions of arrival beamforming with pre-RAKE transmission to alleviate self-interference. The beamforming weights are adjusted within a downlink frame to compensate the predicted fading. We give measures of the prediction and beamforming performance and evaluate the impact of prediction errors on the downlink. Ray tracing simulations in a three-dimensional urban physical model show that the predictive downlink beamforming outperforms the conventional beamforming over Rayleigh-fading channels.

An opportunistic transmission scheduling scheme is proposed to make better use of the multiuser diversity gain in a MIMO system. The performance of a MIMO link is quantified by its information-theoretic capacity. Even though the base station has no knowledge of the transmission channel, the proposed algorithm generates a transmission randomizing matrix according to the distribution of the channel, so that it is likely that some user is near the "water-filling" configuration. The mobile users measure and feedback the channel quality. Based on this information, the base station schedules transmission to the user whose instantaneous channel capacity is the largest. Simulation results show that, over slow varying channels, or over Rician channels with a large K factor, opportunistic transmission scheduling can improve system performance in terms of channel capacity.

Multiple-input multiple-output (MIMO) wireless communication systems employ multiple transmit and multiple receive antennas to obtain significant improvement in channel capacity. However, the capacity is limited by the correlation of subchannels in non-ideal scattering environments. In this paper, we investigate MIMO systems that use antennas with dissimilar radiation patterns to introduce decorrelation, hence increasing channel capacity. We develop a ray tracing model that takes into account both the propagation channel and the transmit and receive antenna patterns. Using a computational electromagnetic simulator, we show that: (1) MIMO systems that exploit antenna pattern diversity allow for improvement over dual-polarized antenna systems; and (2) the capacity increase of such MIMO systems depends on the characteristics of the scattering environment.