Deep learning (DL) has been widely studied for assisting applications of modern wireless communications. One of the applications is automatic modulation classification (AMC). However, DL models are found to be vulnerable to adversarial machine learning (AML) threats. One of the most persistent and stealthy threats is the backdoor (Trojan) attack. Nevertheless, most studied threats originate from other AI domains, such as computer vision (CV). Therefore, in this paper, a physical backdoor attack targeting the wireless signal before transmission is studied. The adversary is considered to be using explainable AI (XAI) to guide the placement of the trigger in the most vulnerable parts of the signal. Then, a class prototype combined with principal components is used to generate the trigger. The studied threat was found to be efficient in breaching multiple DL-based AMC models. The attack achieves high success rates for a wide range of SNR values and a small poisoning ratio.

With the advancement of Artificial Intelligence (AI) and Explainable AI (XAI), Deep Learning (DL) algorithms become increasingly vulnerable to adversarial machine learning (AML) threats. One of the widely used DL-based applications in wireless communication is the Automatic Modulation Classification (AMC). In this paper, we investigate XAI methods for designing AML attacks in DL-based AMC systems. Specifically, we discuss four AML tactics, namely, untargeted causative, targeted evasion, untargeted evasion, and targeted backdoor attacks. We present new specific explanation methods used to launch these attacks, which are customized versions of Saliency Map, Integrated Gradient, the SHapley Additive exPlanations (SHAP), and the enhanced Gradient-weighted Class Activation Mapping (Grad-CAM++) techniques. These explanations identify the most contributory data points to the DL-based AMC classifier. It allows an attacker to perturb these identified data samples using the Fast Gradient Sign Method (FGSM). We compare these new XAI-guided attacks with traditional state-of-the-art attacks on DL-based AMC. Our research shows that the XAI-guided threats outperform (negatively) the traditional ones in terms of Robust Accuracy (RA) metric, Attack Success Rate (ASR), and Fooling Rate (FR), but they exhibit higher computational complexity. However, XAI-guided AML attacks require fewer perturbed signals, which justifies the exhibited computational cost.

Federated-Learning (FL) based Spectrum Sensing (SS) method is considered for the application in future cognitive radio communication systems due to its supreme performance in changing radio environments as compared to classic cooperative or non-cooperative SS. It also avoids transferring large training datasets with high-resolution localization data. The FL algorithm is the subject of poisoning attacks that can be random or coordinated. In this paper, we first evaluate the impact of such attacks on the FL-based SS performance. Next, we propose a zero-trust method based on continuous monitoring and classification of the sensors’ models to detect attacked models. These models are then eliminated from the global model construction in FL. Our method issemi-blind, i.e., it does not require an apriori knowledge of who are the genuine actors participating in FL. Simulation results of the system under various attacks (random or coordinated, moderate or very aggressive, deliberately increasing or decreasing the spectrum occupancy) show that our method decreases the SS probability of false alarms by 89 % and increases the SS probability of detection by 16 % in case of the most severe targeted attacks in the most critical SNR ranges.

The concept of open radio access networks (RAN) creates numerous opportunities for developing new technology and economy branches. At the same time, a flexible and modular approach in the disaggregated RAN entails the need for careful design of the overall RAN architecture and the implementation and deployment process of new applications. It is assumed that dedicated and specialized software companies may deliver the latter. A joint effort must be guaranteed among different sectors (industry, academia, and standardization bodies) to make the whole process efficient, safe, and reliable. Here, one of the critical driving forces origins from the open-source community that often stimulates the development of a specific technology. In this paper, we address the challenges that have to be faced by third-party application developers in the context of Open RAN. Based on many implemented applications (called xApps or rApps), we compare various available solutions. We pose the most critical issues that must be tackled in the near future to stimulate the progress in open RAN development further. In particular, we compare available open platforms for xApp development and testing. We present the details of implementing four selected applications describing the problems encountered. The paper is split into two logical parts - first, we identify the key ambiguities related to the development of new xApps, which address more complicated use cases like beam management. In the second part, we present the challenges associated with detailed software implementation in existing open platforms. In the first case, we show that dedicated beam mobility management xApp can reduce beam switches and keep beam failures low. However, it requires access to detailed localization information. Similarly, the signaling storm detection xApp provides expected performance under the assumption that there is access to detailed information on, e.g., time advance resolution parameter. We conclude here that several aspects still need to be well-defined to allow smooth software implementation; these include the rules for data reporting in time, parameters available in service models, and localization features. Concerning the second logical part, related to low-level implementation, we compare the numerical results of the traffic steering and quality-of-service-based resource allocation xApps and draw conclusions related to implementation and testing. In particular, we point out problems associated with the simulator, the software, and conflicts inside. Finally, we identify the key challenges which should be treated as incentives for joint academia-industry cooperation in the field of Open RAN. Thus, the paper presents the lesson learned during the first years of xApp development.

In this paper, we present a novel approach to spectrum sensing (SS) and spectrum future occupancy prediction (SP) in a multipath, frequency-selective fading radio environment. In conventional methods, fading effects in the link between a primary user (PU) and the sensor may impede the detection of the PU transmission. Additionally, in the presence of multiple PUs and links characterized by different signal-to-noise (SNR) ratios, reliable SS and SP become even more difficult. In this paper, we look at the methods to resolve these problems. Our proposed algorithm employs machine learning (ML) methods to uncover time and frequency patterns in the occupied spectrum and occurring frequency-selective fading effects. It exploits two convolutional neural networks (CNNs). One is for Spectrum Sensing (SS) and Sensing Prediction (SP), and the other estimates fading level of a signal in a given moment. Both CNN's decisions are combined into one joint decision with improved reliability. The fading estimation provides information on the level of channel distortion that impacts the quality of SS and SP performance. The obtained results are promising and prove the usefulness of the ML-based fading-level estimation in SS and SP.

Fog networks offer computing resources of varying capacities at different distances from end users. A Fog Node (FN) closer to the network edge may have less powerful computing resources compared to the cloud, but the processing of computational tasks in FN limits long-distance transmission. How should the tasks be distributed between fog and cloud nodes? We formulate a universal non-convex Mixed-Integer Nonlinear Programming (MINLP) problem minimizing task transmission- and processing-related energy with delay constraints to answer this question. It is transformed with Successive Convex Approximation (SCA) and decomposed using the primal and dual decomposition techniques. Two practical algorithms called Energy-EFFicient Resource Allocation (EEFFRA) and Low-Complexity (LC)-EEFFRA are proposed and their effectiveness is tested for various network and traffic scenarios. Using EEFFRA/LC-EEFFRA can significantly decrease the number of computational requests with unmet delay requirements when compared with baseline solutions (from 48% to 24% for 10 MB requests). Utilizing Dynamic Voltage and Frequency Scaling (DVFS) minimizes energy consumption (by one-third) while satisfying delay requirements.

In this paper, we investigate joint subcarrier (SC) allocation, pairing and power loading for optimized energy efficiency (EE) in multiuser, multicell, multicarrier downlink decode-and-forward (DF) relay interference networks with computational awareness, i.e., taking computations-related energy into account. In order to maximize EE of the network, the transmission mode is adapted to instantaneous channel conditions. For the benefit of spectral-efficiency, both direct- and relayed transmission is allowed to use the same SCs simultaneously. Linearly rate-dependent power consumption of signal processing is considered. The formulated optimization problem is the nonconvex fractional mixed binary-integer programming problem, which has NP-hard complexity. Hence, we approximate the problem by the series of equivalent convex problems applying convex relaxation techniques such as a Successive Convex Approximation (SCA). Based on these transformations, we develop an iterative algorithm exploiting the Dinkelbach method to tackle the nonlinear fractional programming problem which maximizes EE of the system. Moreover, in our considerations, the total transmission power constraint and the minimum required rate constraints have been included. Simulation results demonstrate the effectiveness of our solution for future relay networks.

Fog computing can be used to offload computationally intensive tasks from battery powered Internet of Things (IoT) devices. Although it reduces energy required for computations in an IoT device, it uses energy for communications with the fog. This paper analyzes when usage of fog computing is more energy efficient than local computing. Detailed energy consumption models are built in both scenarios with the focus set on the relation between energy consumption and distortion introduced by a Power Amplifier (PA). Numerical results show that task offloading to a fog is the most energy efficient for short, wideband links.

Dynamic spectrum sharing can provide many benefits to wireless networks operators. However, its efficiency requires sophisticated control mechanisms. The more context information is used by it, the higher performance of networks is expected. A facility for collecting this information, processing it, and controlling base stations managed by various network operators is a so‐called Radio Environment Map (REM) subsystem. This paper proposes REM‐based schemes for the allocation of base stations power levels in 4G/5G networks, while considering interference generated to a licensed network. It is assumed that both networks have different profiles of served users, e.g., area of their positions and movement, which opens opportunities for spectrum sharing. The proposed schemes have been evaluated by means of extensive system‐level simulations and compared with two widely adopted policy‐based spectrum sharing reference schemes. Simulation results show that dynamic schemes utilizing rich context information outperforms static, policy‐based spectrum sharing schemes.

In this paper, we investigate the energy-efficient resource allocation problem in the downlink of an Orthogonal Frequency Division Multiple Access (OFDMA) system with multiple users. A iterative algorithm is developed to maximize the overall energy efficiency of the downlink transmission by allocating the resource blocks (RBs) and the transmit power, which is constant for all RBs assigned to a given user. Moreover, we assume that all RBs assigned to the same user must use the same modulation and coding scheme (MCS), as in the LTE specification. In this form our optimization problem belongs to a broad class of problems called Mixed-Integer Nonlinear Fractional Problem (MINLFP), which is very difficult to solve analytically in the original form. Hence, in order to solve it, we propose the iterative algorithm with fast convergence based on the Dinkelbach method. In each iteration, the solution for the power and resource blocks allocation is derived by the numerical method using the Karush-Kuhn-Tucker (KKT) multipliers and KKT conditions, while modulation and coding scheme, for each user, is obtained by the iterative algorithm. Simulation results show that despite the computational simplicity of the proposed solution, it achieves better results than the solutions known from the literature.

In this paper, we deal with the small-scale spectrum aggregation, where a set of even very narrow and disjoint frequency bands closely located on the frequency axis can be utilized simultaneously. Contrarily to our previous work on that subject, we concentrate on the multiuser scenario in which the 5G system tries to share the spectrum interleaved by multiple narrowband signals realized in the protected cellular systems, e.g., 2G/3G systems. We first present the idea of multiuser small scale sharing based on non-contiguous multicarrier (NC-MC) techniques. In our optimization problem we rely on the detailed interference model that takes into account limitations of both transmitter and receiver frequency selectivity, and which has been practically validated. Presented results confirm that proposed solution can provide high throughput even when the 5G system operates in a dense heterogeneous network.

The article presents an analysis of correlation-based clustering procedure in cooperative spectrum sensing. The motivation is to assess if it is more beneficial in terms of energy efficiency to group nodes according to the received signal-to-noise ratio (SNR) on the link between Primary User and node or according to the distance between nodes. To this end, a merged clustering measure is introduced. Then a number of network topologies are compared via computer simulations.

Demand response management (DRM) is envisaged to play a key role in the smart grid operation, which requires reliable communications between power providers and consumers. To reduce communication cost, the cognitive radio technique is proposed to transmit the meter data from consumers to the control center. Unlike most existing studies on cognitive enabled smart grid, where only individual spectrum sensing is considered, in this paper, both cooperative spectrum sensing and harvested renewable energy are incorporated. The tradeoff between spectrum sensing cost and the DRM management gain makes the optimization of cooperation scheme a challenging research problem. To solve the problem, we analytically study the degradation of communication reliability of the renewable energy supplied consumers who attend the cooperative sensing as well as the DRM gain obtained by the communication improvement. Further, the optimization problem of selecting the number of cooperative consumers is formulated. We prove that there exists a unique optimal cooperative number under some constraints and propose an efficient searching algorithm. Numerical results are presented to validate our theoretical analysis.

In this paper, the energy efficiency (EE) of an adaptive OFDM (Orthogonal Frequency-Division Multiplexing) system is analyzed taking not just the transmit power, but also the transceiver computation-power consumption into account. Such an energy-efficiency optimization problem belongs to a broader class of problems called convex-concave fractional programs, which in the case of the adaptive modulation and coding techniques is also a mixed-integer nonlinear problem (MINLP). In order to solve it, we propose the joint adaptive power and adaptive modulation and coding (AMC) algorithm with fast convergence based on Dinkelbach method, where the analytical solutions are derived by the numerical method according to the Lagrange multipliers and Karush-Kuhn-Tucker (KKT) conditions. Simulation results show that the adaptive modulation and coding techniques allow for: increased energy efficiency, increased average throughput, reduced required transmit power and reduced total power consumption. Moreover, there exists the optimal point for the transmit power maximizing the energy efficiency.

New spectrum bands together with flexible spectrum management are treated as one of the key technical enablers for achievement of the so-called key-performance indicators defined for 5G wireless networks. In this paper, we deal with the small-scale spectrum aggregation and sharing, where a set of even very narrow and disjoint frequency bands closely located on the frequency axis can be utilized simultaneously. We first discuss how such a scheme can be applied to various multicarrier systems, focusing on the non-contiguous orthogonal frequency division multiplexing and non-contiguous filter-bank multicarrier technique. We propose an interference model that takes into account the limitations of both transmitter and receiver frequency selectivity, and apply it to our 5G link-optimization framework, what differentiates our work from other standard approaches to link adaptation. We present the results of hardware experiments to validate assumed theoretical interference models. Finally, we solve the optimization problem subject to the constraints of maximum interference induced to the protected legacy systems (GSM and UMTS). Results confirm that small-scale spectrum aggregation can provide high throughput even when the 5G system operates in a dense heterogeneous network.

We consider receiver synchronization in the non-continguous orthogonal frequency division multiplexing (NC-OFDM)-based radio system in the presence of in-band interfering signal, which occupies the frequency-band between blocks of subcarriers (SCs) used by this system, i.e. in-band of NC-OFDM receiver spectrum range. This paper proposes a novel preamble-based synchronization algorithm for estimation of the time and frequency offset based on the received signal cross-correlation with the reference preamble. Contrary to the existing algorithms, it is robust against in-band interference including narrowband interference at the cost of increased complexity. Moreover, in the interference-free system, the probability of frame synchronization error is improved in comparison to all simulated algorithms.

This paper presents a new, low-complexity algorithm for time and frequency synchronization in a non-contiguous-orthogonal frequency division multiplexing (NC-OFDM) radio communication system in the presence of narrowband interference (NBI). This interference scenario is plausible for cognitive radio systems. The computational complexity of the proposed synchronization method is similar to the known Schmidl&Cox algorithm. The algorithm is partially blind, i.e., it does not require information on the NC-OFDM subcarriers used, nor on the center-frequency of the NBI. Moreover, it does not require filtering to remove the NBI. It performs best for the NBI of constant carrier frequency, but it also provides good results for the frequency-modulated interfering signal.

The synchronization at the Non-Contiguous Orthogonal Frequency Division Multiplexing (NC-OFDM) based Cognitive Radio (CR) receiver is a challenge. High-power interference from spatially- and spectrally-neighboring wireless systems may disrupt CR synchronization. In the same time, spectrum shaping techniques might be applied in the CR transmitter to reduce interference generated to other wireless systems. In this paper, we show how they can be used for time synchronization. The proposed Envelope Fluctuation Detection (EFD) method uses time- varying mean sample power of the spectrally shaped NC- OFD waveform. The EFD is more robust to narrowband interference than commonly used autocorrelation-based approach.

In this paper, we present a distributed resource allocation mechanism in cognitive radio networks, based on a new coopetition methodology, which combines advantages of nodes' competition and cooperation. We postulate that this new method allows for fully distributed resource management between cognitive radio devices. The presented framework is generic, however, we consider it for the application in OFDMA networks. Coopetition takes the best from cooperative and competitive problem formulation, and provides the opportunity to control the balance between fairness and spectral efficiency (SE) of resource allocation. Simulation results confirm that coopetition allows for efficient resource utilization, and may be used practically in wireless cognitive networks.

In the context of cognitive radio it is important to obtain high spectrum utilization while limiting interference generated to licensed systems. In this paper, new method for the determination of a dynamic spectrum mask is presented that allows for higher flexibility of the cognitive radio links, systems and future standards. The solution maximizes the throughput of the secondary non-contiguous OFDM (NC-OFDM)-based system while limiting the transmission power, interference caused to the primary system and minimum power to be allocated to each OFDM subcarrier for the successful transmission. Below, we investigate coexistence of a secondary NC-OFDM system with primary wireless microphones, although our method can be easily extended to other scenarios and systems.

The reduction of spurious emission is an important issue in future OFDM-based systems, especially in the context of cognitive radio, when the primary users must be protected from the interference. In this paper, flexible quasi-systematic precoder is presented for non-contiguous OFDM transmitter, which has the effect of relatively small distortion of the data symbols modulating the subcarriers. We discuss degrees of freedom in the precoding-matrix design. The quasi-systematicy allows for not only the reduction of the out-of-band emission, but also flexible reception with high performance, either with or without the knowledge of the coding-matrix.

Abstract In this paper, we consider the Orthogonal Frequency Division Multiple Access (OFDMA)‐based Opportunistic Radio (OR) networks, in which the nodes are able to adopt a subset of subcarriers (SCs) available in the considered network area, as well as the transmission rate and power associated with these SCs either for their uplink or downlink transmission. The idea of our top‐down approach to the efficient and rational spectrum utilization is to allow each node to first optimize the resources acquisition at OSI‐layer 2 (top), where the competition of nodes for available common resources is observed, and then to autonomously optimize the transmission parameters accounting for the radio channel conditions at the physical (down) layer. We assume that the nodes act independently based on their local channel quality information, which contains an error. In these optimization tasks, the efficiency and rationality mechanisms have been introduced in the objective (utility) functions, which reflect the throughput achieved, the network potential to serve multiple nodes, as well as pricing of resources and the power economy. Copyright © 2010 John Wiley & Sons, Ltd.

In this paper, we consider an opportunistic access to the spectrum resources in wireless networks. The resources are adopted by the network nodes in a distributed manner, i.e. based on their local channel quality information. The competition of nodes for available resources is modeled as a game. To coerce the desired behavior of the competitors having no information on the other players, pricing (taxation) of resources is applied. We formulate the problem of finding the optimal taxation rate, and propose a reduced-complexity algorithm for this optimization. Simulation results for these optimal values are also provided.

Adaptive M-ary quadrature amplitude modulation (M-QAM) with subset diversity is a way to cope with the quality of service variations in small and large-scale fading channels. We consider a pilot-assisted slow adaptive modulation (SAM) technique that adapts the constellation size and the pilots energy to slow variations of the channel due to shadowing. The SAM technique is less complex and requires a lower feedback rate with respect to fast adaptive modulation techniques. We present an analytical framework to evaluate the bit-error probability for pilot-asisted slow adaptive QAM with subset diversity and imperfect channel state information (CSI) together with a utility-based approach to SAM. It accounts for the imperfect CSI, and is related to the game-theoretic approach, in which a particular strategy (the pilots energy and the constellation signaling) is chosen as a response to the set of possible channel conditions.

In this article, we present options for energy-efficiency in adaptive bit and power loading algorithm in practical OFDM systems with imperfect Channel State Information (CSI) and pilot-aided channel estimation. We consider rate-adaptive and margin-adaptive schemes always treating energy-efficiency as the key paradigm. The studies presented aim at lowering the energy-wastage related to pilot symbols while maintaining the total transmit energy per OFDM symbol constraint. Given the energy constraints in rate-adaptive schemes, the number of pilots and their energy are chosen trading off between the Bit-Error-Rate (BER) performance and the efficiency of the spectrum usage. In margin-adaptive schemes the number of pilots and their energy are minimized to meet the required QoS parameters. We present possible options for the allocation of the available energy between pilots and data, and examine them through computer simulations in Long-Term Evolution (LTE) system scenarios.

In this paper, a novel pragmatic bit and power allocation algorithm for Non Orthogonal Frequency Division Multiplexing (NOFDM) systems is presented. It is based on the well-known Campello approach and takes into account the lack of orthogonality between adjacent waveforms. Simulation results in a typical NOFDM wireless applicative scenario show the effectiveness of the proposed algorithms.

In this paper the game-theoretic model of the water-filling algorithm for an OFDM system is presented. The considered game model concerns the strategic choice of assigning the transmission power to each individual subcarrier in the situation of uncertainty regarding the channel state information (CSI). Strategies, utilities and payoffs are defined, and the application of the model in the time-varying radio environment is discussed. Simulation results show that by choosing the appropriate utility parameters and the CSI-error probability distribution model, a player can approach water-filling results in terms of the radio channel capacity and the transmitted power.

In this paper, multicarrier spread-spectrum radio transmission is taken into account, in which signal energy spreading is based on Walsh-Hadamard transform. The considered system operates in wireless indoor environment, in the presence of both, the additive white Gaussian noise and the impulse noise. For such a transmission, unbalanced effect of the impulse noise on distinct symbols can be expected. Below, we propose a method of decision-margin adaptation, appropriately tailored for each symbol and the spreading sequence assigned to it. This method is based on erasures of unreliable symbols and the application of Reed-Solomon codes with erasure-correction capability. Simulation results show good erasure performance and thus, the proposed method should also result in the increased BER performance of the considered transmission scheme.

An efficient low-complexity algorithm proposed earlier by the same author is considered for the application in multicarrier radio communication systems with code-division multiple access. An inverse algorithm is proposed as a method of joint detection (JD), which is capable of rejecting intersymbol and multiple-access interference at a reasonable complexity. Computational complexity calculations as well as recent performance results of the proposed method are provided. The bit-error rate performance achieved by the simulated JD algorithms and equalizer structures is comparable with the performance of other methods which exhibit higher complexity.

A new joint detection technique has been considered for application in multicarrier code division multiple access systems. Two basic approaches have been taken into account. One is based on the adaptive algorithms applied in direct sequence CDMA systems. The other one is a new adaptive technique implemented in the so called "time-domain prime". Computational complexity of this new method is discussed, and simulation results are presented.

The multicarrier CDMA technique applied in mobile radio communication systems is considered. The new fast algorithm for multi-user combining and multicarrier modulation, in a base station transmitter, is presented. It is shown, that the inverse of the proposed algorithm is a very efficient method of multicarrier demodulation and joint multi-user detection. Its applications in base and mobile station receivers is discussed. It is described, how equalization of the selective fading channel, and MAI rejection can effectively be implemented in the time-domain. It is shown, that the computational complexity of such a reception technique is very low. The detailed considerations and simulation results for the down-link transmission are presented. The similar reception method for the up-link case is also considered in detail.

The multicarrier code division multiple access (MC-CDMA) technique is considered. Various spreading sequences have been taken into account, analyzed and compared with respect to their application in MC-CDMA systems. The analysis of the peak to average power ratio of the selected spreading codes is presented. The sensitivity of the MC-CDMA systems, using these codes, to the frequency offsets is analyzed. An interesting point of the analysis presented in the paper, is the computational complexity of MC-CDMA transmitter/receiver implementation.

The data driven frequency-domain echo canceller (EC) for a multicarrier modulation system is considered. An EC in such a system has to deal with both the interchannel and intersymbol interference occurring in the echo signal. For this reason, the main disadvantage of the data driven EC structure is the large computational complexity. Here, the solution of the computational complexity problem is presented. It is based on assumption that in practice, interchannel interference has a limited range. The number of operations per symbol as a measure of the EC computational complexity is given. Simulation results present echo attenuation in the frequency-domain EC, operating in the orthogonally multiplexed quadrature amplitude-shift keying system. Modifications of the proposed EC structure and its computational complexity in the systems with pulse shaping are discussed.