Active Reconfigurable Intelligent Surfaces (RIS)s are a promising technology for 6G wireless networks. This paper investigates a novel hybrid deep reinforcement learning (DRL) framework for resource allocation in a multi-user uplink system assisted by multiple active RISs. The objective is to maximize the minimum user rate by jointly optimizing user transmit powers, active RIS configurations, and base station (BS) beamforming. We derive a closed-form solution for optimal beamforming and employ DRL algorithms—soft actor-critic (SAC), deep deterministic policy gradient (DDPG), and twin delayed DDPG (TD3)–to solve this high-dimensional, non-convex optimization problem. Simulation results demonstrate that SAC achieves superior performance with a high learning rate leading to faster convergence and lower computational cost compared to DDPG and TD3. Furthermore, the closed-form of optimal beamforming enhances the minimum rate effectively.

In the future communications, cell-free networks are considered very promising, owing to their robustness against inter-cell interference which degrades the user signal-to-interference-plus-noise-ratio (SINR). For an efficient network to achieve an enhanced capacity at a minimized power consumption, reconfigurable intelligent surfaces (RIS) are promoted as a key candidate 6G technology. In this paper, a joint precoding RIS aided cell-free Multiple-Input-Multiple-Output (MIMO) network is considered, where a weighted sum rate (WSR) maximization problem is formulated and decoupled into subproblems. A feasible solution is then obtained using fractional programming (FP). Finally, the performance of passive RIS and active RIS is then compared.

Large Intelligent Surfaces are essential components in upcoming 6G networks due to their impressive capabilities and energy efficiency. To enhance network coverage, we introduce relays that can overcome distance and obstacle limitations. The focus is on integrating Large Intelligent Surfaces with amplify-and-forward relay techniques to facilitate communication between a base station and a full-duplex user, even in the presence of co-channel interference from device-to-device pairs nearby. To optimize data transmission, closed-form expression is derived that calculates the optimal power required to achieve maximum data rates while considering challenges like self-interference and co-channel interference from device-to-device communications. Also, quadratic transform for the non-convex problem is derived analytically to be able to solve the problem using CVX as well. Additionally, a neural network approach is proposed that accurately predicts the minimum power needed to achieve the maximum data rates. This neural network model proves to be a promising alternative with much less complexity.

Large Intelligent Surfaces are key technologies for the upcoming 6G networks for their high capabilities and low power consumption. To further extend the coverage, relays can be employed to overcome distances and obstacle limitations. In this paper, we integrate the large intelligent surfaces technology with the decode-and-forward relay to aid the communication of a base station with a full-duplex user in the presence of device-to-device communicating devices. A closed form expression for the optimum power to achieve maximum data rate is derived in the presence of self-interference and co-channel interference from the device-to-device communications. A neural network approach is proposed, that accurately predicts the minimum power required to achieve maximum data rates. Results show that the neural network is a promising alternative to avoid complex calculations.

This paper investigates interference cancellation in an Uplink Multi-User (MU) Multiple Input Multiple Output (MIMO) system with imperfect Channel State Information (CSI), in which a Full Duplex (FD) Decode and Forward (DF) relay is used. Least Squares (LS) approach is considered to estimate the channels. In order to decode the symbols at the relay, the received MU interference is cancelled by applying Block Diagonalization (BD) based processors. Moreover, an equivalent relay is used to suppress the relay's self-interference signal. Afterwards, Minimum Mean Squared Error (MMSE) technique is adopted for the information extraction at the relay. A similar procedure is applied at the Base Station (BS) for MU interference cancellation and information extraction. Simulation results provide the appropriate number of users, antennas and pilot powers for each setup in order to achieve a relatively high sum rate.

In this paper, power allocation problem for cooperative THz MIMO-NOMA system is studied to maximize the minimum achievable rate of the available users. The cooperative system consists of a base station (Bs) that communicates directly with a nearby user, while a relay node (RN) is used to help the Bs to communicate with the far user. The RN operates in HD and FD modes using DF protocol. The Bs is equipped with multiple antennas, while both the relay and the user nodes are equipped with single antenna. The optimization problem for power allocation is solved analytically and validated numerically.

In this paper, we propose a model of a full duplex (FD) massive MIMO AF relay assisting D2D and cellular users simultaneously in presence of cross-tier interference and imperfect channel state information (CSI). Zero-forcing reception (ZFR)/zero-forcing transmission (ZFT) processing technique is used in the relay. The asymptotic spectral efficiency (SE) under four power scaling schemes is derived and validated by numerical results. Results show that the loop interference due to the FD nature of the relay can be eliminated by scaling down the transmitted power of the sources and the relay.

Heterogeneous network (HetNets) and Device-to-device (D2D) communication are two promising techniques to be introduced in future generation networks to meet the requirements of explosive data traffic. D2D is a promising technique to communicate between user equipment underlying a cellular network by re-using cellular resources within the cell. Although, this can help in offloading the main cellular network, however one of the major challenges is to to control the interference generated by reusing the same resources. In this paper, the problem of interference management for underlay D2D users is studied in a two-tier heterogeneous macro-small cell network assuming imperfect channel state information (CSI). The network consists of one macro-cell with its macro-cell base station (MBS) and one small-cell cellular user equipment (SUE) linked to a small-cell base station (SCBS). The network has N D2D pairs belonging to the macro-cell tier outside the range of the small-cell. The N D2D pairs use the same resources of the SUE to increase the spectral efficiency of the network. The optimal power of D2D users that maximize the signal-to-interference-and-noise (SINR) ratio is derived in presence of imperfect CSI maintaining the signal to interference-plus-noise ratio (SINR) of the SUE greater than certain threshold to guarantee by quality-of-service (QoS).

Device‐to‐device (D2D) and heterogeneous networks (HetNets) are two promising technologies to be introduced in the upcoming 5G network, for improving spectral efficiency and decreasing latency. However, sharing the same spectrum resources among different tiers of HetNet raised the interference challenge. In this paper, cross‐tier interference management for underlay D2D users is studied in a heterogeneous macro‐small cell network assuming imperfect channel state information (CSI). The network consists of one macro‐cell with a centered macro‐base Station (MBS) and several small‐cell base stations (SCBS). Two types cellular users are considered; macro‐cell cellular user equipment (MUE) associated with the MBS, and small‐cell cellular user equipment (SUE) linked to SCBS. While two types of D2D users are considered; macrocell D2D (MD) located outside the range of the small cells and cross‐tier D2D user equipment (CD), where each user of the D2D pair belongs to different network tier. Closed form expressions for the D2D optimal power that aim to maximize the coverage probability and the signal‐to‐interference‐noise ratio (SINR) of both links are derived, while guaranteeing the quality of service (QoS) requirements for the cellular user. The effect of channel estimation error on the performance of both D2D and cellular users is evaluated.

A comparative study on the theoretical bit error rate (BER) is presented for hybrid relaying schemes that toggle between adaptive decode-and-forward (ADF) and amplify-and-forward (AF) protocols, for a typical three-node wireless network. Toggling between the two forwarding protocols is based on the log-likelihood ratio (LLR) or the signal-to-noise ratio (SNR) of the received signal at the relay node. Closed-form expressions for the probability of error are presented, as well as the expressions of the proposed schemes’ gains over classical ADF and AF protocols. Comparisons are carried out among the two schemes and other hybrid schemes found in the literature. Moreover, the impact of relay location on the probability of error is investigated.

An adaptive generalised selection-combining (GSC) receiver is proposed for time-varying frequency selective fading channel. The receiver adaptively selects and combines a subset of diversity branches out of the available branches and discards the others. This is performed by comparing the maximum likelihood (ML) metric of each diversity branch with a threshold. The branches that are lower than the threshold are selected and combined using maximal ratio combiner. The proposed adaptive GSC receiver dynamically adjusts the threshold value according to the time variations of the channel. Equalisation and data detection are performed after combining using ML sequence estimation implemented by Viterbi algorithm. The minimum survivor technique is employed to reduce the complexity of the receiver. An upper bound for the probability of error of the proposed receiver is derived. The performance of the proposed adaptive GSC receiver is compared with the performance of different threshold GSC receivers.

The combined effect of partial band jamming and imperfect channel estimation on the analysis of the performance of MC-FH/BFSK receiver over a Rayleigh fading channel is often neglected in the literature. In this study, this missing analysis is provided. The authors derive closed form bit error probability (BEP) expressions for studying the effect of partial band and broad-band jamming on the performance of a coherent uncoded MC-FH/BFSK receiver over a Rayleigh fading channel where the effect of channel estimation errors is not neglected. The considered model of the channel estimation errors does not assume independency between amplitude and phase estimates. Computer simulations are provided to validate the theoretical developments. It is shown that the smart partial band jammer should be present in all sub-bands of the system in order to be effective.

A method for automatic classification of composite FM/PM speech signals is proposed here. The method classifies a number of intercepted signals into FM or PM, provided that each signal is either speech FM or PM. The signals are transmitted through flat fading channels and contaminated with white Gaussian noise. A linear array consisting of several sensors is constructed to intercept these signal. The minimum description length criterion is used to estimate the number of intercepted signals. The maximum likelihood approach is used to estimate the direction of arrival of each signal, the fading channel, coefficients and the noise variance. The classification procedure is based on estimation of the phase waveform which contains the speech signal. An iterative algorithm is derived to perform this estimate for each signal and then the resulting estimate is used to develop a method to determine, for each signal, if it is FM or PM. The method is based on evaluating the power spectral density of the instantaneous frequency of the intercepted signal which is distinctive in speech FM and PM signals. Computer simulations are performed to validate the theoretical developments.

The problem of adaptive detection of signals contaminated with Middleton's class-A impulsive noise and transmitted over a fast time-varying frequency-selective fading channel is addressed. Adaptive algorithms are derived to update the estimate of the channel parameters to the detector. A theoretical performance evaluation of the detector is provided. Computer simulations are performed to validate the theoretical developments.

This paper presents a reduced-complexity maximum-likelihood sequence estimation receiver, based on the Viterbi algorithm (VA), suitable for rapidly fading mobile communication channels. The channel impulse response is expanded onto a set of basis sequences and time-invariant (TI) expansion parameters. The proposed receiver continuously estimates the TI expansion parameters directly within the metric calculation of the VA. At every time instant of the VA, the accumulated metrics of the survivor paths are compared, and the survivors whose metrics are lower than the average value of the accumulated survivor metrics are retained. The other survivors are discarded from the trellis. Then the sequences associated with the minimum survivor of the retained survivors are used to update the estimate of the TI expansion parameters. The convergence properties of the estimation algorithm are investigated, and the steady-state value of the mean square error of estimation is derived. The performance of the proposed receiver is evaluated in terms of the symbol-error probability and compared with other receivers. The effects of time offset and frequency offset on the performance of the receiver are studied.

We develop and analyze classifiers for multiple M-ary frequency-shift keying (MFSK) signals traveled over a static frequency nonselective Rayleigh fading channel. The classifier is based on approximating the likelihood function (LF) of the frequency modulated digital signals and is derived for both synchronous and asynchronous waveforms. Two cases are considered; the first one is concerned with the signals that have identical modulation type [for example, binary FSK (BFSK) or quaternary FSK (QFSK)]. The second case deals with the signals with different modulation type. We use complex envelope representation of the signals and noise to derive the LF. Simulation experiments are illustrated to validate the theoretical developments.