Artificial intelligence (AI), and more specifically deep learning techniques, have demonstrated strong capabilities in processing wireless signals, enabling automatic modulation classification (AMC). However, existing AI-based AMC methods often produce unreliable predictions and lack robustness to out-of-distribution (OOD) inputs, which limits their deployment in real-world scenarios. This study aims to address the gap in simulations to real deployments by fitting predictions to OOD scenarios. We propose an uncertainty-aware AMC framework based on supervised contrastive learning (SupCon). The proposed framework aims to enhance classification reliability, particularly under OOD conditions. In this framework, a ResNet-based representation learning model that consists of a feature extractor and a projection head is first trained using a combination of SupCon loss and cross-entropy (CE) loss to produce class-discriminative embeddings. By decoupling the shared representation learning model from task-specific classifiers, the framework enables a modular and computationally efficient uncertainty estimation strategy, avoiding redundant computation during inference. The learned embeddings are then processed by a set of class-wise binary classifiers that provide both classification and sample-wise uncertainty estimates. A rejection mechanism is incorporated to improve decision reliability by discarding uncertain predictions. We evaluate the proposed framework on the RadioML 2018 dataset. Experimental results show that our approach significantly improves representation quality and classification reliability compared to conventional supervised learning. Specifically, the classification accuracy increases from 63.7% to 93.6% under in-distribution conditions, and from 30.8% to 92.5% under 50% OOD contamination, while maintaining over 85% recall on accepted predictions.

In mmWave wireless networks, signal blockages present a significant challenge due to the susceptibility to environmental moving obstructions. Recently, the availability of visual data has been leveraged to enhance blockage prediction accuracy in mmWave networks. In this work, we propose a Vision Transformer (ViT)-based approach for visual-aided blockage prediction that intelligently switches between mmWave and Sub-6 GHz frequencies to maximize network throughput and maintain reliable connectivity. Given the computational demands of processing visual data, we implement our solution within a hierarchical fog-cloud computing architecture, where fog nodes collaborate with cloud servers to efficiently manage computational tasks. This structure incorporates a generative AI-based compression technique that significantly reduces the volume of visual data transmitted between fog nodes and cloud centers. Our proposed method is tested with the real-world DeepSense 6G dataset, and according to the simulation results, it achieves a blockage prediction accuracy of$\mathbf{9 2. 7 8 \%}$while reducing bandwidth usage by 70.31 %.

Refractive metasurfaces (RMTSs) offer a promising solution to improve energy efficiency of wireless systems. To address the limitations of single-layer RMTSs, stacked intelligent metasurfaces (SIMs), which form the desired precoder and combiner in the wave domain, have been proposed. However, previous analyses have overlooked hardware non-idealities that significantly affect SIM performance. In this paper, we study the achievable sum-rate of SIM antennas in an uplink scenario, accounting for hardware constraints. We propose a system model that includes noise and hardware effects, formulate a non-convex sum-rate optimization problem, and solve it using gradient ascent and interior point methods. We compare SIMs and digital phased arrays (DPAs) under Rayleigh fading and 3GPP channels with two conditions: an equal number of$\mathbf{R F}$chains and an equal physical aperture size. Our results show SIMs outperform DPAs under equal number of RF chains but underperform DPAs with equal aperture size.

Cell-free Integrated Sensing and Communication (ISAC) aims to revolutionize 6th Generation (6G) networks. By combining distributed access points with ISAC capabilities, it boosts spectral efficiency, situational awareness, and communication reliability. Channel estimation is a critical step in cell-free ISAC systems to ensure reliable communication, but its performance is usually limited by challenges such as pilot contamination and noisy channel estimates. This paper presents a novel framework leveraging sensing information as a key input within a Conditional Denoising Diffusion Model (CDDM). In this framework, we integrate CDDM with a Multimodal Transformer (MMT) to enhance channel estimation in ISAC-enabled cell-free systems. The MMT encoder effectively captures inter-modal relationships between sensing and location data, enabling the CDDM to iteratively denoise and refine channel estimates. Simulation results demonstrate that the proposed approach achieves significant performance gains. As compared with Least Squares (LS) and Minimum Mean Squared Error (MMSE) estimators, the proposed model achieves normalized mean squared error (NMSE) improvements of 8 dB and 9 dB, respectively. Moreover, we achieve a 27.8% NMSE improvement compared to the traditional denoising diffusion model (TDDM), which does not incorporate sensing channel information. Additionally, the model exhibits higher robustness against pilot contamination and maintains high accuracy under challenging conditions, such as low signal-to-noise ratios (SNRs). According to the simulation results, the model performs well for users near sensing targets by leveraging the correlation between sensing and communication channels.

Reconfigurable intelligent surfaces (RIS) have emerged as a promising technology for enhancing wireless communication by dynamically controlling signal propagation in the environment. However, their efficient deployment relies on accurate channel state information (CSI), which leads to high channel estimation overhead due to their passive nature and the large number of reflective elements. In this work, we solve this challenge by proposing a novel framework that leverages a pre-trained open-source foundation model (FM) named large wireless model (LWM) to process wireless channels and generate versatile and contextualized channel embeddings. These embeddings are then used for the joint optimization of the BS beamforming and RIS configurations. To be more specific, for joint optimization, we design a deep reinforcement learning (DRL) model to automatically select the BS beamforming vector and RIS phase-shift matrix, aiming to maximize the spectral efficiency (SE). This work shows that a pre-trained FM for radio signal understanding can be fine-tuned and integrated with DRL for effective decision-making in wireless networks. It highlights the potential of modality-specific FMs in real-world network optimization. According to the simulation results, the proposed method outperforms the DRL-based approach and beam sweeping-based approach, achieving 9.89% and 43.66% higher SE, respectively.

Mobile traffic prediction is an important enabler for optimizing resource allocation and improving energy efficiency in mobile wireless networks. Building on the advanced contextual understanding and generative capabilities of large language models (LLMs), this work introduces a context-aware wireless traffic prediction framework powered by LLMs. To further enhance prediction accuracy, we leverage in-context learning (ICL) and develop a novel two-step demonstration selection strategy, optimizing the performance of LLM-based predictions. The initial step involves selecting ICL demonstrations using the effectiveness rule, followed by a second step that determines whether the chosen demonstrations should be utilized, based on the informativeness rule. We also provide an analytical framework for both informativeness and effectiveness rules. The effectiveness of the proposed framework is demonstrated with a real-world fifth-generation (5G) dataset with different application scenarios. According to the numerical results, the proposed framework shows lower mean squared error and higherR2-Scores compared to the zero-shot prediction method and other demonstration selection methods, such as constant ICL demonstration selection and distance-only-based ICL demonstration selection.

Integrated sensing and communications is a key enabler for the 6G wireless communication systems. The multiple sensing modalities will allow the base station to have a more accurate representation of the environment, leading to context-aware communications. Some widely equipped sensors such as cameras and RADAR sensors can provide some environmental perceptions. However, they are not enough to generate precise environmental representations, especially in adverse weather conditions. On the other hand, the LiDAR sensors provide more accurate representations, however, their widespread adoption is hindered by their high cost. This paper proposes a novel approach to enhance the wireless communication systems by synthesizing LiDAR point clouds from images and RADAR data. Specifically, it uses a multimodal transformer architecture and pre-trained encoding models to enable an accurate LiDAR generation. The proposed framework is evaluated on the DeepSense 6G dataset, which is a real-world dataset curated for context-aware wireless applications. Our results demonstrate the efficacy of the proposed approach in accurately generating LiDAR point clouds. We achieve a modified mean squared error of 10.39 with {256, 128, 64, 64} convolutional filters in the LiDAR decoder, as compared to 38.58 achieved for the all-zeroes benchmark. Visual examination of the images indicates that our model can successfully capture the majority of structures present in the LiDAR point cloud for diverse environments. By integrating LiDAR synthesis with existing sensing modalities, our method can enhance the performance of various wireless applications, including beam and blockage prediction.

Large language models (LLMs), especially generative pre-trained transformers (GPTs), have recently demonstrated outstanding ability in information comprehension and problem-solving. This has motivated many studies in applying LLMs to wireless communication networks. In this paper, we propose a pre-trained LLM-empowered framework to perform fully automatic network intrusion detection. Three in-context learning methods are designed and compared to enhance the performance of LLMs. With experiments on a real network intrusion detection dataset, in-context learning proves to be highly beneficial in improving the task processing performance in a way that no further training or fine-tuning of LLMs is required. We show that for GPT-4, testing accuracy and F1-Score can be improved by 90%. Moreover, pre-trained LLMs demonstrate big potential in performing wireless communication-related tasks. Specifically, the proposed framework can reach an accuracy and F1-Score of over 95% on different types of attacks with GPT-4 using only 10 in-context learning examples.

This paper studies the impact of intra- and inter-cell mobility on mmWave networks with a specific focus on beam switching. The paper utilises a geometric model to partition the coverage area of a mmWave gNB cell into radial and angular sectors, thus accounting for the coverage footprints of planar antenna arrays with azimuth-tilt beam orientations (i.e., horizontal and vertical orientations). Using this model, intra-cell beam switching rate is derived analytically. We extrapolate the analysis using stochastic geometry to address inter-cell mobility and system-level beam switching. Our study establishes a relationship between the shape of the antenna array pattern and the beam switching rate. We validate our analysis via extensive Monte Carlo simulations and the results reveal the significant impact of the antenna configuration on beam switching rate. Even when the number of beams remains the same, the beam switching rate can almost double depending on how the antenna array elements are arranged.

In 5G cellular networks, Machine Learning (ML) can be exploited to predict if a user equipment (UE) is in the coverage area of a neighbouring cell. This could improve crucial cellular network functionalities, such as handovers, interference mitigation and carrier aggregation. In this paper, we study the enhancement of UEs’ privacy in a Differentially Private-Federated Learning (DP-FL) scheme relying on the sampled Gaussian mechanism, assuming honest-but-curious threat model. With this technique, the UE’s privacy is protected by perturbing the averaged updates conducted at the server; also, the usage of client subsampling results in an amplified privacy and a reduced overhead in terms of communication. We demonstrate that the models trained with our approach can achieve better privacy-utility tradeoff than previous works can. In addition, we conduct membership inference attack to study the factors that impact the empirical privacy protection to the training data. We make a novel observation that suggests that for coverage prediction task, larger datasets and/or smaller ML models would provide stronger empirical privacy protection to training data. Beyond the task we consider, this observation could be a useful insight for dataset curation or model architecture selection in other domains and warrants additional investigation.

It is well-established that mobility is a prominent challenge for beam-based communication. Despite the beam management functions specified by 3GPP to facilitate beam-based communication, its reliability under beam-level mobility remains questionable. Hence, this paper highlights the challenges impeding the reliability of beam-based communication under user mobility and poor propagation conditions. Specifically, this paper investigates beam-switching in mmWave networks and assesses the merits of beam-switching optimization through parametrization. Several parameters, including a Hysteresis margin and a Time-To-Trigger, are investigated with regards to enhancing beam switching. To carry-out the analysis, real beamformed mmWave data is used. The results report key beam switching performance measures and show a critical beam switching optimization trade-off.

Massive multiple-input multiple-output (MIMO) systems, wherein a massive number of antennas are deployed at the base stations, are expected to play a significant role in 5G networks. The drawback of using the massive MIMO technique is the need for advanced and complex signal processing schemes. In recent years, several iterative and learning-based techniques have been introduced to address the need for low-complexity signal detection in the uplink of a massive MIMO system. The complexity of the iterative methods is highly affected by the number of needed iterations. On the other hand, although the performance of low-complexity learning-based techniques is close to optimal, they need retraining after major changes in the wireless communication channel. In this paper, we introduce Hint, a robust learning-based technique that finds an initial vector tailored for the current realization of the wireless channel; this vector initializes the iterative detector to complete the task of massive MIMO detection.

Predicting packet volume accurately plays a vital role in network management and optimization. This study proposes a novel approach combining a hybrid wavelet transform and a deep stacking ensemble model to forecast packet volume. The proposed model leverages the wavelet transform's strengths and deep stacking ensemble techniques to enhance the predictive performance. The univariate prediction is conducted for different horizons, including 1, 3, 7, and 10 steps ahead. The wavelet transform is employed to capture the time-frequency characteristics of the packet volume data, enabling a more comprehensive analysis. The model can extract local and global features by decomposing the time series into different scales using wavelet analysis, improving prediction accuracy. The deep stacking ensemble model is utilized to leverage the collective intelligence of multiple base models. Through a series of stacking layers, the model learns to combine the predictions of individual models, allowing for a more robust and accurate forecast. The proposed hybrid wavelet transform and deep stacking ensemble model was subjected to experimental evaluations using real-world packet volume datasets. The outcomes of these evaluations exhibit the effectiveness of the model. The model achieves superior predictive performance compared to traditional methods, showcasing its potential for practical network management and optimization applications.

Long-term average proportional-fair (LTAPF) throughput optimization through power control is a popular resource allocation problem which is typically approximated by weighted sum-rate (WSR) maximization. WSR optimization is non-convex and strongly NP-hard in general. In this letter, we demonstrate that, in fact, the original sum-log-average-throughput power control problem can be recast as a convex program and thus solved to global optimality efficiently. We also generalize our result to show that the long-term average$\alpha$-fair utility maximization problem can be recast as convex for$\alpha \in (1,\infty)$. Numerical results demonstrate a substantial gain in LTAPF throughput compared to state-of-the art algorithms used to solve the max-WSR problem.

Class-of-service (CoS) network traffic classification (NTC) classifies a group of similar traffic applications. The CoS classification is advantageous in resource scheduling for Internet service providers and avoids the necessity of remodelling. Our goal is to find a robust, lightweight, and fast-converging CoS classifier that uses fewer data in modelling and does not require specialized tools in feature extraction. The commonality of statistical features among the network flow segments motivates us to propose novel segmented learning that includes essential vector representation and a simple-segment method of classification. We represent the segmented traffic in the vector form using the essential vector representation (EVR). Then, the segmented traffic is modelled for classification using random forest based simple-segment method of classification (S2MC). Our solution's success relies on finding the optimal segment size and a minimum number of segments required in modelling. The solution is validated on multiple datasets for various CoS services, including virtual reality (VR). Significant findings of the research work are i) Synchronous services that require acknowledgment and request to continue communication are classified with 99 % accuracy, ii) Initial 1,000 packets in any session are good enough to model a CoS traffic for promising results, and we therefore can quickly deploy a CoS classifier, and iii) Test results remain consistent even when trained on one dataset and tested on a different dataset. In summary, our solution is the first to propose segmentation learning NTC that uses fewer features to classify most CoS traffic with an accuracy of 99 %. The implementation of our solution is available on GitHub.

This paper proposes beam failure prediction to recover from inevitable link failures in beam-based mmWave communication proactively. The proposed system consists of two components. First, a prediction engine to foresee future beam failures and their severity. For this purpose, machine learning and deep learning are proposed to perform prediction. The second component is a proactive recovery mechanism, that matches the prediction failure results with a suitable recovery action, with the goal to maintain seamless connectivity and prevent service interruptions. The performance of the proposed system is compared against conventional beam failure detection and recovery. Simulations were carried out using real beamforming data. The results indicate a substantial improvement in the network performance. The improvement is measured in terms of prediction accuracy, beam failure probability and successful beam failure probability. This paper also assesses a drawback of the proposed system, particularly the increase in handover rate, and shows that the achieved gain outweighs this weakness.

Cooperative driving is a promising technology in the future Connected Autonomous Vehicles (CAV) because of its benefits to safety and fuel efficiency. However, since CAV will be relying heavily on wireless communication to cooperatively coordinate road maneuvering, latency and reliability of communication still pose a challenge. In this paper, we propose a novel scheme based on deep learning prediction to enhance the uplink resource allocation process in 5G C-V2X. The proposed scheme enables the base station to predict vehicle maneuvers, subsequently, assign it the required resource in advance without the need for scheduling request and granting process. This scheme improved the ability of 5G NR to support cooperative driving requirements. Moreover, we compare both traditional and proposed schemes discussing issues that arise from the introduction of prediction models and possible approaches for further enhancements in the future.

As one of the key technologies in 5G networks, Carrier Aggregation (CA) is studied in this paper. In CA, Component Carriers (CCs) can be activated and deactivated depending on multiple factors, e.g., energy consumption and Quality of Service (QoS) demand of users. We propose CC management strategies where each User Equipment (UE) minimizes its average delay and at the same time minimizes its power consumption while considering that CCs can be activated and deactivated only at certain times, as in real-world CA implementations. We first model the problem as a centralized multi-objective optimum CC management problem. Since centralized approaches would impose a large overhead on the system, we then develop a semi-distributed solution by modeling the problem as a stochastic game and propose a multi-agent Double Deep Q-Network (DDQN) based CC management algorithm to solve the stochastic game. We finally compare the proposed approaches with single CC activation and all-CC activation baseline schemes. Simulation results show that our proposed algorithms outperform the all-CC algorithm in terms of UE power consumption and have the capability of transmitting a number of bits with delay close to the all-CC scheme. Meanwhile, our DDQN-based algorithm decreases the UE power consumption by about 20% with respect to the all-CC scheme.

Connected Autonomous Vehicles (CAV) utilize vehicular communication to collect information about the surrounding environment to make informed decisions about speed and maneuvering. This enables safe driving and decreases the number of accidents and thereby the associated fatalities. However, vehicular communication may suffer from high latency and low reliability, especially in dense vehicle environments, which may negatively affect the safety of CAVs. Therefore, it is crucial to study the impact of these metrics on the safety application performance while taking into account realistic CAV kinematics and dynamics. In this paper, we address this problem by comparing the performance of the Short Range Communication (DSRC) to that of the Fifth-Generation New Radio (5G-NR) and their impacts on the safety applications in the CAV environment under different settings. We develop a full-fledged simulation framework that can realistically model both vehicular mobility and communication and can capture the impact of communication on safety applications. Within this framework, we implement an important CAV's safety application, namely, the forward collision avoidance system, in which following vehicles use vehicular communications to gather information from leading vehicles to compute the safe speed and avoid collisions. We then use this framework to study and compare the performance safety of the forward collision avoidance system using both DSRC and 5G-NR communications. The results show that the packet delays and drops in communication networks can adversely affect CAV safety. The results also demonstrate that 5G is more capable of supporting the safety requirements under higher packet traffic loads and vehicle densities.

Carrier aggregation (CA) is considered a key enabler technology for delivering higher rates to users of LTE and 5G networks. However, the increased transmission rate comes with the price of higher energy consumption which stems from users continuously monitoring the control channel of the active component carriers (CCs) whether data transmission is ongoing or not. In order to reduce energy consumption, we exploit the activation-deactivation procedure at the medium access control (MAC) layer of LTE/5G network. In this paper, we propose a reinforcement learning-based algorithm to improve energy-efficiency by dynamically activating-deactivating secondary component carriers (SCCs) with awareness of the user traffic profiles. The proposed algorithm aims to predict the arrival of data and identify SCCs to activate for each user. In addition, a traffic splitting approach and an intelligent exploration strategy are proposed to balance users' load among CCs and improve the convergence of the algorithm, respectively. Results of the proposed algorithm are compared with three baseline algorithms. The first baseline always activates all CCs for each user, the second baseline activates one carrier only (i.e., the primary carrier) and the third baseline algorithm relies on a reactive method, where the activation-deactivation decision is performed after observing the arrival of data. Results show that Q-learning outperforms the baseline algorithms by achieving the highest sum throughput (and lowest average delay) with the lowest number of activated SCCs, which is obtained by learning to dynamically activate SCCs according to the traffic pattern. Hence, Q-learning is considered the most energy-efficient compared to the baseline algorithms.

Cloud virtual reality (VR) gaming traffic characteristics such as frame size, inter-arrival time, and latency need to be carefully studied as a first step toward scalable VR cloud service provisioning. To this end, in this paper we analyze the behavior of VR gaming traffic and Quality of Service (QoS) when VR rendering is conducted remotely in the cloud. We first build a VR testbed utilizing a cloud server, a commercial VR headset, and an off-the-shelf WiFi router. Using this testbed, we collect and process cloud VR gaming traffic data from different games under a number of network conditions and fixed and adaptive video encoding schemes. To analyze the application-level characteristics such as video frame size, frame inter-arrival time, frame loss and frame latency, we develop an interval threshold based identification method for video frames. Based on the frame identification results, we present two statistical models that capture the behaviour of the VR gaming video traffic. The models can be used by researchers and practitioners to generate VR traffic models for simulations and experiments - and are paramount in designing advanced radio resource management (RRM) and network optimization for cloud VR gaming services. To the best of the authors' knowledge, this is the first measurement study and analysis conducted using a commercial cloud VR gaming platform, and under both fixed and adaptive bitrate streaming. We make our VR traffic datasets publicly available for further research by the community.

Unmanned Aerial Vehicles (UAV) are expected to play a crucial role in the future of 5G and beyond. However, designing efficient routing protocols for UAV is challenging due to the mobility and energy constraints. This problem becomes harder in UAV-assisted 5G networks because of its impact on the time slot assignment for the uplink and downlink in Time Division Duplex (TDD) frame structure. Thus, in this paper, we propose a new optimum routing technique for UAV-assisted TTD 5G networks, the Optimized Load-Balancing Routing (OLBR). The optimum routing problem is formulated in such a way that the decision variables are used to compute the time slot assignment in the 5G connection between UAV nodes. The objective of the optimization model is to minimize the network-wide delay. By distributing traffic across different alternative routes, OLBR minimizes network congestion, resulting in shorter queuing delays. Such a load-balancing also decreases the possibility of node failure due to energy depletion. The proposed OLBR is compared to the shortest path routing using Monte Carlo simulation on two different network topologies at different network traffic loads. The simulation results show that the OLBR produces significant savings in network-wide packet delay compared to the shortest path.

Carrier Aggregation (CA) has been a breakthrough in LTE that led to increased throughput for users, and is still one of the key technologies in 5G that helps to enhance spectrum utilization. In CA, Component Carriers (CCs) are dynamically activated and deactivated depending on several performance factors. Optimal selection of CCs has been studied in the literature. However, the latency associated with activation and deactivation of CCs, control channel overhead for switching CCs, as well as the energy consumed for monitoring the active CCs have not been a part of the optimal CC selection problem. Nevertheless, those become stringent design constraints in practice. In this paper, we address optimal CC selection and resource allocation in 5G networks, where the above constraints are considered and the 5G network supports several service types with different 5G QoS Identifiers (5QI). The proposed optimum joint CC selection and Radio Resource Block (RB) allocation schemes maximize average throughput of users and satisfy QoS of users in terms of delay. In addition, the proposed schemes take CC activation and deactivation burden into consideration and aim to minimize the number of activations and deactivations. The simulation results demonstrate that our proposed solution outperforms the state of the art solution while satisfying the QoS requirements and creating close to 95.5% reduction on the number of CCs activations and deactivations.

The ability to accurately forecast network resource utilization is vital in next-generation wireless networks. Based on the predicted load, telecom operators can proactively allocate network resources in an efficient way. In this paper, we perform a thorough analysis of a cellular network downlink load dataset collected at millisecond resolution. We first evaluate various statistical metrics of the physical resource block (PRB) utilization data to investigate its predictability. Then, we develop deep learning-based models to forecast PRB utilization in radio access networks (RANs). In particular, we propose univariate and multivariate long short-term memory (LSTM) network-based architectures for the forecasting task and investigate the impact of various prediction horizons and history lengths. When predicting PRB utilization, our approach showed up to 49% improvement in the Coefficient of Determination (r2score) and 19.5% decrease in the Root Mean Square Error (RMSE) compared with the baseline methods used.

To meet the ever-increasing communication services with diverse requirements, situation-aware intelligent utilization of multi-dimensional communication resources is becoming essential. In this paper, considering a time-division-duplex downlink cellular scenario, a deep learning-based framework for multi-dimensional intelligent multiple access (MD-IMA) scheme is developed for beyond 5G and 6G wireless networks to meet the real-time and diverse quality of service (QoS) requirements by fully utilizing the available radio resources in heterogeneous domains. To achieve intelligent operation of MD-IMA, the proposed deep learning scheme is achieved based on the convergence of long short term memory (LSTM) and deep reinforcement learning (DRL). Specifically, an LSTM neural network is used to predict the long-term network dynamics and inference changes in QoS requirements of the MD-IMA. Meanwhile, a deterministic policy gradient (DDPG) algorithm, a model-free DRL technique, is adopted to optimize the multi-dimensional radio resource allocation in real-time by dynamically following the fluctuations of the network situation. With the aid of the DDPG algorithm, radio resource management for MD-IMA can be achieved efficiently with reduced processing latency as compared to the conventional model-based approaches. Furthermore, the effectiveness of our proposed deep learning framework for MD-IMA is validated through real-world cellular traffic data-sets. The experimental results demonstrate that the proposed scheme can outperform state-of-the-art algorithms.

Network slicing is a key paradigm in 5G and is expected to be inherited in future 6G networks for the concurrent provisioning of diverse quality of service (QoS). Unfortunately, effective slicing of Radio Access Networks (RAN) is still challenging due to time-varying network situations. This paper proposes a new intelligent RAN slicing strategy with two-layered control granularity, which aims at maximizing both the long-term QoS of services and spectrum efficiency (SE) of slices. The proposed method consists of an upper-level controller to ensure the QoS performance, which enforces loose control by performing adaptive slice configuration according to the long-term dynamics of service traffic. The lower-level controller is to improve SE of slices, by tightly scheduling radio resources to users at the small time-scale. To realize the proposed RAN slicing strategy, we propose a model-free deep reinforcement learning (DRL) framework, which is a hierarchical structure that collaboratively integrating the modified deep deterministic policy gradient (DDPG) and double deep-Q-network algorithm. Specifically, the lower-level control problem is a mixed-integer stochastic optimization problem with multiple constraints. This kind of problem is hard to be directly solved by the exiting DRL algorithms, since it involves searching for the solution in a vast set of mixed-integer action space, which will induce unbearable computational complexity. Thus, we propose a novel action space reducing approach, embedding the convex optimization tools into the DDPG algorithm, to speed up the lower-level control. Furthermore, simulation results confirm the effectiveness of our proposed intelligent RAN slicing scheme.

The ever-growing wireless applications and their diverse Quality of Service (QoS) requirements bring the challenge of tailored QoS provisioning with limited radio resources in future cellular networks. While resource constraint is ubiquitous, different communication equipment in cellular networks could experience very different constraints in the multi-dimensional resource domains. To achieve stringent yet diverse QoS with limited resources, a novel multi-dimensional intelligent multiple access (MD-IMA) scheme is proposed in this paper to exploit disparate resource constraints among heterogeneous equipment for 5G beyond and 6G networks. With the assist of real-time data analysis, real-time QoS requirements, and resource availability of the related equipment are first determined in the proposed MD-IMA. Based on this, multiple access (MA) scheme is then intelligently adapted accordingly for each equipment in multi-dimensional resource domain to maximize the overall system requirement with operational constraints. The resource allocation in the MD-IMA system is further formulated as an optimization problem. To solve this non-convexity optimization of high computational complexity, the overall optimization is divided into several sub-problems and a joint optimization algorithm is adopted. Simulation results demonstrate the system energy efficiency performance gain of proposed MD-IMA over traditional MA is around 15% - 18%.

With the advancements in wireless network technologies over the past few decades and the deployment of 4G LTE networks, the capabilities and services provided to end-users have become seemingly endless. Users of smartphones utilize high-speed network services while commuting on public transit and hope to have a consistent, high-quality connection for the duration of their trip. Due to the massive load demand on cellular networks and frequent changes in the underlying radio channel, users often experience sudden unexpected variations in the connection quality. To overcome such variations and maintain a consistent connection, these variations need to be predicted before they occur. This can be accomplished by the spatio-temporal analysis of the different network quality parameters and the investigation of the main factors that affect the network's performance and QoS. To this end, we conducted a network survey via Kingston Transit in Kingston, Ontario, Canada. We used the Android network monitoring application G-NetTrack Pro to build a dataset of various client-side wireless network quality parameters. The dataset consists of 30 repeated public transit bus trips at three different times of the day, each lasting around one hour. In this paper, we describe the data collection process, present an analysis of the collected data, and investigate the effects of time and location on the network's measured throughput and signal strength. We made the collected data, including more than 190 thousand unique records, publicly available to researchers in a domain where open data is rare.

With the deployment of large scale antenna array in millimeter wave (mmWave) band, the resolution of beamforming has been dramatically improved. To reduce the long beam-training process using reference signal (RS) in codebook-based high resolution beamforming, hierarchical codebook is often used to reduce the number of beam-training symbols. However, the large beam-training overhead is still the bottleneck for overall system performance improvement in term of the true achievable data rate. In this paper, with the angle reciprocity in frequency duplex division (FDD) system, a neural network based line of sight path angle of arrival (LAoA) estimation algorithm is proposed for beam selection, in order to achieve the non-RS-aided codebook-based beamforming. To further achieve high accuracy LAoA estimation, two-step neural network models are designed to capture the relationship between the receiving signal and the corresponding LAoA. The numerical results show that the proposed algorithm outperforms the benchmark algorithm in terms of sum weighted data rate (SWR) and sum data rate (SR). In the low signal to noise ratio (SNR) environments with a couple of uplink signal snapshots, our algorithm also performs better than MUSIC based beam selection algorithm.

In order to exploit the potential capacity of 5G, the deployment of ultra-dense small cells is an approach that can dramatically increase the radio resource reuse factor and network capacity. However, network densification with a large number of small cells brings challenges due to increased network complexity, deployment cost and inter-cell interference. In this paper, a new 5G architecture with virtual small cells (VSCs), which are dynamically formed by grouping a number of user devices in close proximity and adapted according to traffic condition, is proposed to improve the cost and energy efficiency compared with the traditional fixed deployment of small cells. In each virtual small cell, one mobile device is selected as a cell head (CH) to aggregate intra- cell traffic using unlicensed band transmissions and then communicates with its macro-cell base station in a licensed band through beamformed transmission, which reduces the inter-cell interference and improves spectrum efficiency. In this paper, a highly directional beamforming technique is employed to enable a dedicated inband fronthaul link for VSC. Our work focuses on how to design adaptive beamforming to minimize the transmit power under throughput requirements and power constraints. Both the mathematical analysis and simulation results demonstrate that VSCs can increase power efficiency dramatically while providing flexibility and reduced cellular load, when compared with macrocell only deployment and traditional fixed small cells scenario.

In order to support dramatically increased traffic from diverse network services, deployment of ultra dense networks to improve the overall capacity of the fifth generation (5G) wireless networks becomes inevitable. However, network densification with increased number of small cells brings significant challenges in terms of quality of service provisioning and deployment cost due to increased network complexity, signalling overhead and inter-cell interference. In this paper, virtual small cell (VSC), which is formed adaptively according to traffic condition and service requirements, is investigated as a solution for cost-effective and reliable service provisioning in 5G ultra dense networks. A K-means clustering based VSC formation scheme is proposed in this paper, and the corresponding protocol conversion for data transmission across unlicensed and licensed networks at cell head (CH) is developed. Based on the VSC architecture design, a new resource allocation algorithm is also proposed for VSC scenario in order to improve the system throughput with comparable fairness.

In this paper, we tackle the problem of multi-cell resource scheduling, where the objective is to maximize the weighted sum-rate through inter-cell interference coordination (ICIC). The blanking method is used to mitigate the inter-cell interference, where a resource is either used with a predetermined transmit power or not used at all, i.e., blanked. This problem is known to be strongly NP-hard, which means that it is not only hard to solve in polynomial time, but it is also hard to find an approximation algorithm with guaranteed optimality gap. In this work, we identify special scenarios where a polynomial-time algorithm can be constructed to solve this problem with theoretical guarantees. In particular, we define a dominant interference environment, in which for each user the received power from each interferer is significantly greater than the aggregate received power from all other weaker interferers. We show that the originally strongly NP-hard problem can be tightly relaxed to a linear programming problem in a dominant interference environment. Consequently, we propose a polynomial time distributed algorithm that is not only guaranteed to be tight in a dominant interference environment, but which also computes an upper bound on the optimality gap without additional computational complexity. The proposed scheme is based on the primal-decomposition method, where the problem is divided into a master-problem and multiple subproblems. We solve the master-problem iteratively using the projected-subgradient method. We also show that each subproblem has a special network flow structure. By exploiting this network structure, each subproblem is solved using the network-based optimization methods, which significantly reduces the complexity in comparison to the general-purpose convex or linear optimization methods. In comparison with baseline schemes, simulation results of the International Mobile Telecommunications-Advanced (IMT-Advanced) scenarios show that the proposed scheme achieves higher gains in aggregate throughput, cell-edge throughput, and outage probability.

Despite the rich literature on cooperative networks, employment of different modulation levels by the source and relay terminals has not been investigated thoroughly from the physical layer perspective. In this paper, we investigate the bit error rate (BER) performance of selective relaying in a multi-relay decode-and-forward cooperative network where the source and the relays transmit using different modulation levels. Specifically, we derive a closed form expression for the end-to-end (uncoded) BER. To draw further insights on the BER performance, we also provide a simpler approximate BER expression that is accurate in the high signal-to-noise ratio regime. Finally, simulation results are presented to verify the analytical results. The derived BER expressions can be utilized in various other scenarios in which the destination selects the best signal (in terms of minimizing BER) among a set of signals which use different modulation levels. The set of signals to choose from may have already been received through orthogonal channels (selection combining), or this signal set may correspond to a set of “candidate” transmissions. The latter scenario is often referred to as selective transmission; applications of this scenario include selective relaying (the setting in this paper), fast base-station selection, and coordinated multipoint transmission and reception (CoMP).

The focus of this paper is on studying the tradeoff between the sum efficiency and Jain's fairness index in general resource allocation problems. Such problems are frequently encountered in wireless communication systems with M users. Among the commonly-used methods to approach these problems is the one based on the α-fair policy. Analyzing this policy, it is shown that it does not necessarily achieve the optimal Efficiency-Jain tradeoff (EJT) except for the case of M=2 users. When the number of users M>2, it is shown that the gap between the efficiency achieved by the α-fair policy and that achieved by the optimal EJT policy for the same Jain's index can be unbounded. Finding the optimal EJT corresponds to solving a family of potentially difficult non-convex optimization problems. To alleviate this difficulty, we derive sufficient conditions which are shown to be sharp and naturally satisfied in various radio resource allocation problems. These conditions provide us with a means for identifying cases in which finding the optimal EJT and the rate vectors that achieve it can be reformulated as convex optimization problems. The new formulations are used to devise computationally-efficient resource schedulers that enable the optimal EJT to be achieved for both quasi-static and ergodic time-varying communication scenarios. Analytical findings are confirmed by numerical examples.

In this paper, we study tradeoff policies between efficiency and the Jain's fairness index of the benefits received by M users in general resource allocation scenarios. Analyzing the commonly-used α-fair tradeoff policy, it is shown that, except for the case of M =2 users, this policy does not necessarily achieve the optimal Efficiency-Jain tradeoff. In particular, it is shown that, when the number of users M >;2, the gap between the efficiency achieved by the α-fair and the optimal Efficiency-Jain tradeoff policy can be unbounded, for the same Jain's index. Finding the optimal Efficiency-Jain tradeoff for arbitrary set of admissible benefits is generally difficult. To alleviate this difficulty, we derive sufficient conditions, which, when satisfied by the set of admissible benefits, lead to efficiently computable optimal tradeoff and benefit vectors. Numerical results for a typical communication network scenario are provided to confirm analytical findings.

Resource scheduling in OFDMA cellular wireless networks is a powerful technique on the MAC layer. Utilizing adaptive modulation and coding allows the effective use of all signal-to-interference ratio (SINR) ranges. Typical single antenna spectral efficiency values for LTE-Advanced range between 4.8 near the base station and 0.2 b/s/Hz at the cell edge. With best-effort traffic and full buffer assumption the tradeoff between emphasizing the cell center or cell edge can be explored extensively. However, with real-time traffic present, this takes priority without fairness adjustment alternatives. In this paper the mixed traffic scenario is studied with an abstract stochastic Petri net model. The exploration of the degrees of freedom by studying the real-time traffic proportion and a fairness adjustment parameter provides new insight to the potential feasible region. The results show that the tradeoff between emphasizing the cell edge performance and maintaining a high average spectral efficiency is most powerful in the best-effort case, while an increasing level of real-time traffic reduces the room for a tradeoff. The stochastic Petri net analysis approach allows numeric analysis without simulation by utilizing Markov chain equivalence and steady state calculations. This model is deliberately abstract but flexible enough to study the tradeoff.

Cellular wireless networks based on OFDMA utilize adaptive modulation and coding to operate effectively in regions of high and low SINR. Therefore the local single antenna spectral efficiency ranges between 5 in the cell center and 0.2 b/s/Hz at the cell edge. The scheduling goal of high average spectral efficiency contradicts the goal of a good rate fairness among all terminals. Also there is a tradeoff between increasing the cell edge performance and maintaining a high average spectral efficiency. In this paper a stochastic Petri net analysis approach is taken and a numeric analysis is performed based on Markov chain equivalence and steady state calculations. The proposed models are deliberately abstract but offer commonly used tuning parameters in order to study the tradeoff without too many degrees of freedom.

In this paper, we propose a novel distributed inter-cell interference coordination (ICIC) scheme. The proposed scheme, which runs in polynomial time, finds a near-optimum dynamic resource partitioning that maximizes a proportional-fairness criterion in the entire network. The proposed scheme is based on primal-decomposition method, where the problem is divided into a master and multiple sub-problems. The master-problem is solved using projected-subgradient method while each of the sub-problems is solved using minimum-cost network flow optimization. Through extensive simulations of four IMT-advanced scenarios, we quantify the gains achieved using the proposed scheme. We demonstrate that the proposed scheme achieves both high cell-edge throughput, that is comparable to frequency reuse 3, and high aggregate throughput, that is at least as good as the aggregate throughput achieved by frequency reuse 1.

In this paper the system analysis of modern wireless systems is simplified by providing simple yet powerful models for the wireless channel in the environment of higher layer abstract system descriptions with generalized stochastic Petri nets (SPN). This modeling approach is capable of deriving performance metrics in terms of packet delays even under heterogeneous, asymmetric, bursty and underutilized traffic conditions, because they are easy to model with SPN. The missing link in wireless systems are suitable channel models, which can now be used as a plug-in submodel inside a larger composite Petri net model. A number of models are proposed, starting from the finite-state Markov channel model approach. Performance results for a multihop relayed transmission under varied traffic load show the utility of this modeling approach.

In constellation rearrangement (CoRe), the base-station and the relay use different constellations, with the same number of signal points, to communicate with the user terminal. In contrast to the existing CoRe techniques, which restrict the possible constellations, we propose generalized quadrature amplitude modulation (QAM) constellations. Since generalized CoRe schemes do not restrict constellations, they have the potential of outperforming all other CoRe schemes, with a complexity penalty in decoding. We pose an optimization to find the generalized QAM constellations, which minimize an upper bound on the uncoded symbol error rate (SER). However, since the optimization is not convex, it is not possible to find constellations with globally minimum SER in a reasonable time. Nevertheless, we use a convex solver to find constellations, which are local minima to the optimization. We input the best known restricted CoRe constellations as starting points to the solver to find constellations, which are guaranteed to improve SER. We demonstrate the significant gains achieved by the proposed CoRe scheme with simulations.

Rate adaptation based on signal-to-noise ratio (SNR) measurements is a common channel adaptation scheme to increase throughput in wireless communication systems. To use rate adaptation efficiently in cooperative wireless networks, an adaptation algorithm must consider multiple channels (source- destination, source-relays, and relays-destination) to select modulation and code rates that maximize throughput. In this paper we analyze the potential gains that combining cooperation with rate adaptation brings in three steps: (1) We derive the theoretical capacity bounds for ideal rate adaptation schemes for typical topologies. (2) We propose an offline heuristic for computing SNR thresholds aimed at reaching the derived bounds. (3) Using this heuristic, we compare rate adaptation for maximal ratio combining (MRC), where links are equally adapted, with soft-bit MRC (SBMRC), where links are individually adapted. We find that adapting the rate per link is superior in terms of throughput.

Cooperative relaying introduces spatial diversity through the creation of a virtual antenna array. The vast majority of the research in digital cooperative relaying assumes the modulation level used by both the source and relay to be the same. This assumption does not necessarily hold when adaptive modulation is implemented. In conventional selection combining, the branch with the highest SNR is chosen; we refer to this scheme as SNR-based selection combining (SNR-SC). In this paper, we introduce BER-based selection combining (BER-SC), as an alternative to SNR-SC, to be used in cooperative communications when a relay may use a modulation level different than that of the source. We provide BER performance analysis for the SNR-SC and BER-SC schemes and show that BER-SC significantly outperforms SNRSC, without any increase in complexity. Moreover, we analytically quantify the gain achieved by using BER-SC over SNR-SC through asymptotic approximation. We note that BER-SC and SNR-SC schemes are identical when the received signals belong to the same modulation level.

In digital cooperative relaying, signals from the source-destination and relay-destination links are combined at the destination to achieve spatial diversity. These signals may not necessarily belong to the same modulation scheme due to the varying channel qualities of the two links. Recently, we have proposed the "soft-bit maximum ratio combiner" (SBMRC) as a low complexity diversity combining scheme for signals with different modulation levels. SBMRC exhibits BER performance that is very close to the optimal maximum likelihood detector (MLD), but with much reduced complexity. In this paper, we revisit SBMRC and provide tight lower bound for the BER performance. Since SBMRC has BER performance slightly inferior to MLD, the derived lower bound can also be used as a good approximation for the BER performance of MLD.

In digital cooperative relaying, signals from the source-destination and relay-destination links are combined at the destination to achieve spatial diversity. These signals do not necessarily belong to the same modulation scheme due to the varying channel qualities of the two links. In this paper, we present novel and low complexity schemes for diversity combining of signals with different modulation levels. We start by developing the optimum solution as a maximum likelihood detector (MLD). Due to its high complexity, we propose two other receiver structures that we refer to as soft-bit maximum likelihood detector (SBMLD) and soft-bit maximum ratio combiner (SBMRC). The proposed schemes are simple bit-by-bit detectors and only 0.3 dB inferior to the MLD in performance. The SBMLD provides only marginal performance gain over SBMRC through the computation of the conditional probability density functions of the soft-bits. Consequently, the SBMRC is a more attractive and practical solution. The performance of SBMRC is compared to that of selection combining which is the current approach in the literature for combining signals with different modulations. The SBMRC, along with its simplicity, outperforms selection combining by almost 2 dB without bandwidth loss or the need for extra channel state information. The SBMRC scheme can be viewed as a more general form of the classical maximum ratio combiner (MRC).

Efficient image transmission over wireless networks is challenged with the limited bandwidth and time-varying nature of the underlying channels. In this paper, we propose a joint variable modulation and power allocation scheme for transmission of compressed images. In our scheme, the modulation level and allocated power are jointly optimized to minimize the mean square error (MSE) of the reconstructed image. We investigate fixed level 16-QAM modulations as well as variable M-QAM with adaptive power allocation. We also introduce an off-line iterative algorithm that finds the optimum combination of modulation and power allocation. Simulation results show that significant improvements in the MSE (in the order of 2~4 dB) and bandwidth efficiency have been achieved when compared to fixed power and modulation level schemes.

In this paper, joint optimization of power allocation and channel coding is proposed for image transmission over wireless channels. The proposed scheme works iteratively to find the optimum combination of coding and power transmitted for individual bits to minimize the mean square error for better image quality. It is shown that bits of significant importance (most significant bits) should always be coded and allocated most of the power transmitted. However, other bits of less significance may be sent without coding and with less power. This is done while maintaining the average energy per bit at the same level. The combined approach shows a gain of about 3 dB compared to the case of coding alone. It also has better performance compared to the case of power allocation alone while reducing the peak-to-average ratio.

In this paper, joint optimization of bit energy and coding is considered for improving the quality of compressed image transmission over wireless channels. The proposed scheme works iteratively to find the best combination of energy distribution among the transmitted bits as well as if coding should be used or not. The minimum mean-square error criterion is used in such optimization rather than the probability of bit error. Simulation results show that a significant gain in performance is achieved while reducing the peak-to-average power ratio and required bandwidth compared to the case of power optimization alone and coding alone, respectively

In this paper, a new technique for power allocation to transmitted bits according to their significance on the message quality is presented. The proposed scheme is based on optimizing the power allocation to minimize the mean-square error rather than the bit error probability of image and video signals transmitted over fading wireless channels. An analytical framework for the power allocation technique is developed. Two techniques of power allocation; fixed and adaptive, are investigated in the paper. Simulation results show that the proposed scheme provides a gain of about 3 dB in Eb/N0in AWGN channels and about 4 dB in flat fading channels over conventional equal-power allocation system. This gain is achieved without any increase in bandwidth, as opposed to that achieved with channel coding. The gains achieved with this algorithm come at the expense of slight increase in the peak-to-average power ratio of the transmitted signal