In the Metaverse, real-time digital twin (DT) updates enable immersive, interactive environments by reflecting real world states. Metaverse can engage its users to share data in order to ensure the completeness of the DT. However, the limitations and heterogeneity in IoT devices' computation and transmission resources are critical challenges to synchronizing the vast volume of real-world objects with their digital replicas. In this work, we propose a novel adaptive Vision Transformer (ViT)- based semantic communication (SemCom) system to extract semantic information from raw data collected by IoT devices. The system dynamically adjusts the model size and computational complexity according to the resource constraints of individual IoT devices, enables broader participation of heterogeneous devices, enhances feature extraction capabilities, and ensures completeness and efficient DT representation. We formulate our problem as an utility-maximization optimization to manage ViT complexity under resource constraints, allowing the Metaverse Services Provider (MSP) to select high-performing IoT devices. To guide the optimization, we profile ViT models with varying architectural complexities and conduct an empirical analysis to capture the relationship between model scale and performance. To address the scalability and privacy limitations of the optimization, we propose a decentralized solution where each IoT device independently optimizes its own utility under local constraints. The MSP, in turn, selects among these devices to ensure quality and maximize its overall utility. We show that our distributed solution achieves near-optimal performance and significantly outperforms other approaches in terms of MSP utility, semantic data quality, and overall IoT utility. © 2026 IEEE.

To address the limitations of existing wireless networks for demanding applications like brain-computer interfaces and intelligent transportation systems, we propose an advanced framework for joint resource allocation and task offloading across integrated terrestrial and non-terrestrial networks (TN-NTN). This framework utilizes multiple layers, including ground users, UAVs, HAPs, and satellites, to improve service quality and immersive experiences, particularly in scenarios like Metaverse applications. Ground users request resources, while UAVs and HAPs serve as resource providers, and satellites ensure reliable communication during emergencies. A double auction-based incentive scheme is employed in which operators control UAV and HAP resources to maximize utility, and users aim to minimize computation costs and protect data privacy. To handle the complexity of the operator-user interaction, which results in an NP-hard optimization problem, we applied a hierarchical multi-agent federated deep reinforcement learning (FeDRL) approach. Our simulation results demonstrate that the FeDRL algorithm significantly improves social welfare by 6.38%, 17.43%, and 28.73% over modified MADDPG, FRL, and DDPG algorithms, respectively.

In recent years, Compressed Sensing (CS) has attracted significant interest in acquiring high-resolution sensory signals while minimizing the amount of signal samples to be measured (so-called sub-Nyquist sampling). At the same time, autonomous robot navigation, such as rovers and drones, is increasingly used for remote data acquisition and environmental data sampling (e.g., temperature, humidity, air quality indicators, etc.). In this context, this paper presents a novel method of preparing the robot data acquisition path that takes advantage of the structure of the measurement matrices used in CS in order to derive robot navigation paths. In particular, we propose a novel Monte-Carlo optimization approach for generating wellsuited measurement matrices that jointly lead to short robot path lengths while minimizing the signal recovery error during the CS procedure. Crucially, our method uses Dictionary Learning (DL) to generate a well-suited CS sparsifying transform matrix, enabling high-precision signal recovery while minimizing the number of samples the robot needs to sense. Our proposed method is applied to recover $N O_{2}$ pollutant maps from the Gulf region. Experimental results demonstrate that our proposed method reduces the length of the robot data acquisition paths to less than 10% of the total path length normally required for total area coverage, while leading to high-precision signal recovery, achieving more than $\times 5$ lower signal recovery errors compared to the use of standard DCT- and Polynomial-based CS procedures.

We present FedADHD, a distributed Federated Learning (FL) framework designed to enhance the diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) while preserving patient privacy. Leveraging the HYPERAKTIV dataset, which contains health activity and neuropsychological data from adults diagnosed with ADHD, we developed a hybrid deep learning model that integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The model analyzes key diagnostic indicators such as the ADHD Confidence Index, omission/commission T-scores, and reaction times extracted from the Conners CPT-II. FedADHD enables collaborative training across multiple mental healthcare institutions, treated as autonomous agents in a federated network, without requiring raw data sharing. This privacy-preserving architecture addresses critical ethical and legal concerns in mental health research. Evaluated using Accuracy, Precision, Recall, F1-score, and Matthews Correlation Coefficient (MCC), FedADHD outperforms traditional centralized Machine Learning (ML) models, showcasing its robustness and generalization capabilities. This work demonstrates how distributed ML and secure collaboration can significantly advance mental health diagnostics in real-world, multi-institutional settings.

In the dynamic vehicular metaverse, delivering a seamless user experience (UX) and effective human-machine interaction (HMI) is challenging due to vehicle mobility and varying resource needs. This paper introduces an adaptive resource allocation and twin migration framework using Multi-Agent Deep Reinforcement Learning (MADRL) for a multi-tier vehicular metaverse. The framework enables cooperative agents to dynamically allocate resources and migrate vehicle twins across vehicle, edge, and cloud layers, ensuring seamless UX and efficient HMI. The joint resource allocation and twin migration optimization problem is modeled as MDP and a hierarchical multi-agent deep deterministic policy gradient-with QMIX (MADDPG-Q) strategy is adopted to solve it, reducing latency and optimizing resource use. Moreover, the proposed framework is designed to be context-aware, adjusting HMI based on real-time conditions, and enhancing interaction quality. Simulation results show significant improvements in UX, latency reduction, and resource efficiency.

Unmanned aerial vehicles (UAVs) are proven useful for enabling wireless power transfer (WPT), resource offloading, and data collection from ground IoT devices in post-disaster scenarios where conventional communication infrastructure is compromised. As 6G networks emerge, offering ultra-reliable low-latency communication and enhanced energy efficiency, UAVs are poised to play a critical role in extending 6G features to challenging environments. The key challenges in this context include limited UAV flight duration, energy constraints, limited resources, and the reliability of data collection, all of which impact the effectiveness of UAV operations. Motivated by the need for efficient resource allocation and reliable data collection, we propose a solution using UAV swarms combined with reconfigurable intelligent surfaces (RIS) to optimize energy harvesting for IoT devices and enhance communication quality. We formulate the problem of resource optimization, UAVs-RIS trajectory planning, and RIS configuration as a mixed integer nonlinear programming optimization problem and solve it in a dynamic condition by transforming it into a Markov decision process and utilizing a deep reinforcement learning (DRL) approach based on proximal policy optimization (PPO) algorithm to solve it. Simulation results demonstrate that our framework outperforms traditional approaches, including the Actor-Critic (AC) algorithm and a greedy solution, achieving superior performance in energy harvesting efficiency, data collection, and communication reliability.

The shift to virtual networks has facilitated the use of deep learning (DL) models for flexible, real-time AI services across various applications. However, to maintain inference accuracy and Quality-of-Service (QoS), these models need regular retraining as data patterns change over time, such as the appearance of new classes or changes in feature distributions. Continuous edge-assisted retraining reduces the communication cost to the cloud, however, it remains limited by network constraints. To address these issues, this paper introduces a Balanced Data Selection (BDS) algorithm, which reduces data imbalance and improves retraining accuracy within resource-constrained environments. BDS offers a low-complexity solution that scales efficiently with the size of new data. Furthermore, we introduce a continuous training framework that supports both data and class incremental learning. Experimental results indicate that our framework achieves retraining accuracy that is superior to baseline solutions, while maintaining lower complexity and effectively addressing data imbalance. This framework provides an effective approach for edge-assisted DL model retraining.

The advent of$\mathbf{6 G}$Internet of Things (IoT) networks demands ultra-reliable, energy-efficient communications to support the massive integration of connected devices. Non-orthogonal multiple access (NOMA) has emerged as a key technology to improve spectral efficiency (SE) by allowing multiple IoT devices (IDs) to share the same frequency resource block through power-domain multiplexing. However, as the number of IDs increases, NOMA faces significant interference challenges, which limit its scalability and degrade system performance. To address these limitations, we propose a clustered NOMA (C-NOMA) framework, which organizes IDs into clusters and applies NOMA within each cluster, reducing interference and improving the effectiveness of successive interference cancellation (SIC). Additionally, we integrate hybrid beamforming (HBF) with C-NOMA, where unmanned aerial vehicles (UAVs) serve as mobile base stations using 2D uniform planar array (UPA) antennas for beam steering. This enables multiple IDs to be served within each cluster with fewer RF chains, further enhancing SE through spatial multiplexing and beam steering. In order to solve the energy efficiency (EE) maximization problem, we reformulate the optimization problem of HBF and power allocation (PA) as a Markov decision process (MDP) and solve it using multi-agent reinforcement learning (MARL). Simulation results show that our proposed Full-RL algorithm achieves up to 37.7 % higher EE compared to the baseline RL-based PA method. This baseline only uses RL for PA and relies on the averaged phase for analog beamforming without further optimization.

The integration of terrestrial and non-terrestrial networks (TN-NTN) in 6 G is essential to support real-time applications like the Metaverse and intelligent edge services, which demand ultra-reliable low-latency communications (xURLLC). Managing these networks and maintaining robust security presents significant challenges due to their complexity and high-dimensional environments. Quantum communication, particularly quantum key distribution (QKD), offers a promising solution by providing unbreakable encryption and enhancing security across TN-NTN architectures. In this paper, we propose a novel deep reinforcement learning approach for QKD-enabled resource allocation in 6 G TN-NTN Metaverse service and transform the joint resource allocation and QKD deployment cost optimization problem into a stochastic game model to ensure secure and efficient resource distribution across TN-NTN environment. We introduce a novel hierarchical multi-agent proximal policy optimization (MAPPO) framework to address the formulated optimization problem. This framework enables dynamic and secure allocation of Metaverse resources and services from multiple providers to users while minimizing QKD deployment costs. Our simulations demonstrate that the proposed framework significantly enhances network performance, reduces key generation costs, and optimizes resource utilization and service quality.

Satellite communication is expected to play a key role in future networks due to its ability to deliver wide-area coverage and high-capacity links. Inter-satellite communication (ISC), which facilitates real-time data exchange between satellites, is therefore critical for important satellite applications such as navigation, earth observation, and defense. However, the broadcast nature of the wireless medium renders ISC vulnerable to various security threats. In this paper, we investigate impersonation attack scenarios in LEO ISC and propose a novel machine learning (ML)-based physical layer authentication (PLA) scheme. The proposed method leverages Doppler frequency shift (DFS) features, arising from relative satellite motion, to enable secure authentication of the transmitting satellite. To address the challenge of acquiring ground-truth labels, we employ a long short-term memory (LSTM) network to learn temporal patterns from the satellite dynamics. A synthetic dataset simulating a 30-day mission involving three satellites (two legitimate and one malicious) is generated using a MATLAB-based orbital propagation method, incorporating 3D position and velocity vectors. The LSTM model is trained on 25 days of data from legitimate satellites and evaluated over the remaining 5 days using both legitimate and malicious transmissions. Authentication is performed via binary hypothesis testing, and we derive tractable analytical expressions for the false alarm and missed detection probabilities and validate the results through simulations.

This paper introduces a novel federated learning framework termed LoRa-FL designed for training low-rank one-shot image detection models deployed on edge devices. By incorporating low-rank adaptation techniques into one-shot detection architectures, our method significantly reduces both computational and communication overhead while maintaining scalable accuracy. The proposed framework leverages federated learning to collaboratively train lightweight image recognition models, enabling rapid adaptation and efficient deployment across heterogeneous, resource-constrained devices. Experimental evaluations on the MNIST and CIFAR10 benchmark datasets, both in an independent-and-identically-distributed (IID) and non-IID setting, demonstrate that our approach achieves competitive detection performance while significantly reducing communication bandwidth and compute complexity. This makes it a promising solution for adaptively reducing the communication and compute power overheads, while not sacrificing model accuracy.

Quishing, a novel form of phishing that exploits QR codes, has emerged as a growing cybersecurity threat. Attackers embed malicious URLs within QR codes to deceive users into accessing fraudulent websites or executing harmful actions. Given the increasing reliance on QR codes in banking, retail and public services, the need for robust detection mechanisms is critical. This paper presents a machine learning-based approach to detecting malicious URLs within QR codes, integrating lexical and behavioral analysis to improve classification accuracy. We evaluated multiple models, including Decision Trees, Support Vector Machines (SVM), Random Forest, and Long-Short-Term Memory (LSTM) networks. Experimental results indicate that the Random Forest model achieves superior performance in terms of detection accuracy and computational efficiency, making it suitable for real-time deployment. The findings contribute to the advancement of QR code security and malicious URL detection, providing practical solutions for cybersecurity applications.

Millimeter-wave (mmWave) beam selection in MIMO systems presents significant challenges in dynamic environments due to computational constraints, data heterogeneity, and privacy concerns. In this paper, we propose a novel Maturing Federated Transfer Learning (MFTL) framework that integrates radar and image data to enhance beam prediction accuracy while ensuring user data privacy. The proposed approach utilizes ResNet-50 as a pre-trained model, fine-tuned locally at distributed Antenna Units (AUs) to adapt to diverse scenarios. To mitigate the effects of data heterogeneity, we evaluate multiple aggregation strategies, with FedMedian demonstrating superior robustness compared to FedAvg and weighted averaging. Our optimized MFTL configuration, utilizing a learning rate of 0.005, a batch size of 32, and five aggregation rounds, significantly improves model performance. Experimental results on the DeepSense 6G dataset indicate that our approach achieves a Top-1 accuracy of 57.58% and a Top-5 accuracy of${9 4. 7 \%}$, outperforming state-of-the-art methods. These findings highlight the effectiveness of federated learning, transfer learning, and robust aggregation techniques in improving beam selection accuracy for next-generation mmWave communication systems.

Generative AI (GAI) and Large Language Models (LLMs) have revolutionized natural language processing and content creation. However, their significant computational demands during inference often require cloud servers, which are currently the only viable option for handling complex multi-modal models like GPT-4. The inherent complexity of these models increases latency, posing challenges even within cloud environments. Furthermore, cloud reliance brings other challenges, including high bandwidth consumption to transfer diverse data types. Worse, in personalized GAI applications like virtual assistants, similar prompts frequently occur, causing redundant transmission and computation of replies, which further increases overhead. Accelerating the inference of multi-modal systems is, therefore, critical in artificial intelligence. In this paper, we aim to improve the inference efficiency through prompt caching; if a current prompt is semantically similar to a previous one, the system can reuse the earlier response without invoking the model again. We leverage collaborative edge computing to cache popular replies and store their request embeddings. New prompts are locally processed to extract embeddings, with their qualities determined by the resources available on edge servers. Our problem is formulated as an optimization to manage offloading decisions for GAI tasks, aiming to avoid cloud inferences and minimize latency while maximizing reply quality. Given its non-convex nature, we propose to solve it via Block Successive Upper Bound Minimization (BSUM). Reinforcement learning is employed to actively pre-cache prompts, tackling the complexity of unknown prompt popularity. Our approach demonstrates near-optimal performance, significantly outperforming cloud-only solutions.

Abstract Satellite communications have emerged as a promising extension of terrestrial networks in future 6G network research due to their extensive coverage in remote areas and their ability to support the increasing traffic rate and heterogeneous networks. Like other wireless communication technologies, satellite signals are transmitted in a shared medium, making them vulnerable to attacks such as eavesdropping, jamming, and spoofing. A good candidate to overcome these issues is physical layer security (PLS), which utilizes physical layer characteristics to provide security, mainly due to its suitability for resource‐limited devices such as satellites and IoT devices. This paper provides a comprehensive and up‐to‐date review of PLS solutions to secure satellite communication. Main satellite applications are classified into five domains: satellite‐terrestrial, satellite‐based IoT, satellite navigation systems, FSO‐based, and inter‐satellite. In each domain, how PLS can improve the overall security of the system, preserve desirable security properties, and resist widespread attacks are discussed and investigated. Finally, some gaps in the related literature are highlight and open research problems, including uplink secrecy techniques, smart threat models, authentication and integrity techniques, PLS for inter‐satellite links, and machine learning‐based PLS, are discussed.

The integration of IoT devices with smart home energy management systems (SHEMS) presents a significant advancement in energy demand response (DR) optimization. However, due to the rapid proliferation of home appliances with varying operating characteristics as well as the variable comfort level demands of users, making effective DR decisions becomes more challenging. In this paper, we propose a hierarchical Stackelberg game-based incentive mechanism with multi-agent deep reinforcement learning (MADRL) to optimize DR in IoT-based SHEMS. We formulate the hierarchical decision-making problem as a Markov decision process (MDP) and then adopt the multi-agent deep deterministic policy gradient (MADDPG) algorithm to solve it by finding an equilibrium solution. Through extensive simulations, we demonstrate that our proposed DR optimization approach can effectively reduce overall energy consumption and peak load by 30.41% and 28.57% from the benchmark approaches, respectively. In addition, the proposed approach maintains user comfort and increases system utility by 13.11% and 15.74% than the benchmark schemes, respectively, resulting in improved energy efficiency.

With its significant security potential, the quantum internet is poised to revolutionize technologies like cryptography and communications. Although it boasts enhanced security over traditional networks, the quantum internet still encounters unique security challenges essential for safeguarding its Confidentiality, Integrity, and Availability (CIA). This study explores these challenges by analyzing the vulnerabilities and the corresponding mitigation strategies across different layers of the quantum internet, including physical, link, network, and application layers. We assess the severity of potential attacks, evaluate the expected effectiveness of mitigation strategies, and identify vulnerabilities within diverse network configurations, integrating both classical and quantum approaches. Our research highlights the dynamic nature of these security issues and emphasizes the necessity for adaptive security measures. The findings underline the need for ongoing research into the security dimension of the quantum internet to ensure its robustness, encourage its adoption, and maximize its impact on society.

Unmanned Aerial Vehicle (UAV)-powered 5G/6G networks integrated with rechargeable wireless sensor networks (RWSNs) offer promising solutions for extending system lifetime, collecting data, and providing computing services and power to sensor nodes (SNs). UAVs offer significant advantages, including exceptional mobility, cost-effective deployment, and the ability to be easily reprogrammed for a wide range of missions. However, the limited onboard power capacity of UAVs, coupled with the lack of dynamic and intelligent charging station (CS) management and inefficient path planning, can lead to SN failure in dynamic mobile environments. To address these challenges, we propose an energy-efficient laser-charged UAV (LCU)-enabled RWSN environment, wherein UAVs, powered by laser beams from ground-based stations, provide services, collect data, and transfer energy to SNs. We formulate a joint optimization problem involving power allocation, dynamic charging strategy (DCS), and path planning to minimize task completion time and sensor node death time. Given the NP-hard nature of the problem, we employ a stochastic game model based on a Markov decision process (MDP) for its solution. To solve this problem, we propose a deep reinforcement learning (DRL) based algorithm that enables real-time charging scheduling decisions while optimizing network performance. We introduce a multi-agent double deep Q-network (MA-DDQN) model to determine the optimal trajectories for all UAVs in large and complex environments. Simulation results demonstrate that the MA-DDQN approach outperforms state-of-the-art techniques, showing significant improvements in terms of average delay, energy consumption, and task completion time.

The integration of terrestrial and non-terrestrial networks (TN-NTN) with open radio access network (O-RAN) technology presents a significant advancement for facilitating scalable and immersive Metaverse services within 6G networks. Seamless virtual experiences necessitate highly reliable, low-latency communication, effective resource management, and adaptive decision-making to satisfy the varied and rigorous requirements of Metaverse applications, including gaming, healthcare, and autonomous systems. The inherent heterogeneity, dynamic nature, and substantial resource requirements of TN-NTN present significant challenges for effective resource allocation and optimizing quality of experience (QoE). Then, we formulate a multi-objective optimization problem for joint resource allocation and spectrum sharing in O-RAN-enabled TN-NTN Metaverse environments. This problem is inherently NP-hard due to the intricate coupling between continuous action spaces and discrete decision variables. Solving such a complex problem using traditional optimization approaches is complex. To overcome this, we transform the problem into a decentralized partially observable Markov decision process (Dec-POMDP) and address it using a hierarchical multi-agent deep reinforcement learning (MADRL) approach. This study presents a hierarchical multi-agent proximal policy optimization (MAPPO) framework, a new MADRL solution for dynamic resource allocation and spectrum sharing in O-RAN-enabled TN-NTN Metaverse environments. MAPPO facilitates collaborative learning among intelligent agents to optimize resource management strategies in a decentralized manner, considering essential metrics, including energy consumption, latency, and meta-distance. The proposed framework enhances resource utilization efficiency, minimizes latency, and improves the QoE for Metaverse users through the seamless allocation and management of resources. Comprehensive simulations show that MAPPO outperforms baseline methods, such as conventional reinforcement learning and centralized optimization approaches, achieving better energy efficiency, lower latency, and improved QoE. This demonstrates its effectiveness in adapting to dynamic 6G-enabled Metaverse requirements, enabling intelligent and scalable TN-NTN networks.

Recently, unmanned aerial vehicles (UAVs) have demonstrated exemplary performance in various scenarios, such as search and rescue, smart city services, and disaster response applications. UAVs can facilitate wireless power transfer (WPT), resource offloading, and data collection from ground IoT devices. However, employing UAVs for such applications poses several challenges, including limited flight duration, constrained energy resources, and the age of information of the data collected. To address these challenges, we employ a UAV swarm to maximize energy harvesting (EH) and data rates for IoT devices by optimizing UAV paths and integrating reconfigurable intelligent surfaces (RIS) technology. We tackle critical constraints, including UAV energy consumption, flight duration, and data collection deadlines, by formulating an optimization problem to find optimal UAV paths and RIS phase shifts. Given the complexity of the problem, its combinatorial nature, and the challenges of obtaining an optimal solution through conventional optimization methods, we decompose the problem into two sub-problems, employing deep reinforcement learning (DRL) to optimize EH and particle swarm optimization (PSO) to optimize RIS phase shifts. Our extensive simulations show that the proposed solution outperforms competitive algorithms, including Brute-Force-PSO, AC-PSO, and PPO-PSO algorithms, providing a robust solution for modern IoT applications.

The forthcoming 6G networks will embrace a new realm of AI-driven services that requires innovative network slicing strategies, namely slicing for AI, which involves the creation of customized network slices to meet Quality of Service (QoS) requirements of diverse AI services. This poses challenges due to time-varying dynamics of users’ behavior and mobile networks. Thus, this paper proposes an online learning framework to determine the allocation of computational and communication resources to AI services, to optimize their accuracy as one of their unique key performance indicators (KPIs), while abiding by resources, learning latency, and cost constraints. We define a problem of optimizing the total accuracy while balancing conflicting KPIs, prove its NP-hardness, and propose an online learning framework for solving it in dynamic environments. We present a basic online solution and two variations employing a pre-learning elimination method for reducing the decision space to expedite the learning. Furthermore, we propose a biased decision space subset selection by incorporating prior knowledge to enhance the learning speed without compromising performance and present two alternatives of handling the selected subset. Our results depict the efficiency of the proposed solutions in converging to the optimal decisions, while reducing decision space and improving time complexity. Additionally, our solution outperforms State-of-the-Art techniques in adapting to diverse environmental dynamics and excels under varying levels of resource availability.

Wireless networks have undergone significant advancements with the rapid progress in Software Defined Networks (SDN), Open RAN (O-RAN) and 5G technology. Among the most notable developments is the emergence of network slicing, which leverages the concept of virtual networks to separate the end-to-end network and computational resources into individual network slices per one or more services/tenants. However, determining the appropriate allocation of computational and network resources for each network slice to meet the specific requirements of each service remains a challenge, especially with continuously changing demands and varying Key Performance Indicators (KPIs) per service and the risk of insufficient or excessive resource allocation. To address these issues, this paper proposes an intelligent predictive framework based on Deep Reinforcement Learning (DRL). Our framework utilizes historical demand and KPI requirements to predict and reserve optimized network slices for multiple services in the future, considering unique constraints, dynamic pricing and under-provisioning. Using different datasets, we validated our system's effectiveness, scalability, and adaptiveness by comparing it with different baselines and state-of-the-art approaches. Our results affirm the efficiency of the proposed solution, showcasing a minimum cost reduction of 15% compared to different baselines and state-of-the-art solutions while incurring less than 2% additional resource consumption. Furthermore, our system demonstrates excellent scalability and adaptability across varying network conditions.

The paper introduces Opportunistic Federated Learning (OFL) as an approach to enhance the efficiency of distributed learning in intelligent IoT systems. OFL allows any node in the network to initiate a learning task and collaboratively use local resources. The framework enables nodes to adapt configurations based on circumstances, optimizing resource utilization. Hence, this paper proposes a reliable node selection mechanism that accommodates the dynamic nature of local data and computing resources. Incentives for participating nodes are explored through a peer-to-peer communication using the Bertrand game to determine optimal pricing strategies. Results demonstrate the Nash equilibrium of the game-based incentive mechanism in a realistic FL setup.

The reciprocity of channel state information (CSI) observed by two devices communicating wirelessly has been leveraged to develop security solutions for resource-limited IoT devices. Despite considerable research in this area, much of the attention has been on theoretical and simulated analyses. However, the practical implementation of these security solutions faces significant challenges, primarily due to limited hardware capabilities and varying channel conditions. To bridge this research gap, we revisit the assumption of channel reciprocity from an experimental perspective. Our experimental investigations uncover a notable decline in channel reciprocity for low-cost devices due to the variability in channel conditions and the asynchronous nature of CSI measurements. Through our experiments, we highlight key practical factors contributing to the diminished channel reciprocity and demonstrate that Pearson’s correlation and time-lagged cross-correlation can effectively measure and assess the channel reciprocity property between two communicating devices. Building upon the experiments’ findings, we then introduce a technique that exploits the reciprocity of collected CSI data, as well as its temporal variations and time shifts to enhance device authentication resiliency through an effective detection of replay attacks.

The industrial Internet of Things (IIoT) and network slicing (NS) paradigms are key enablers of the industrial revolution in current and future mobile networks. However, peer-to-peer (P2P) resource blocks (RBs) exchange to match supply and demand in sliced IIoT networks requires proper incentivization and renegotiations between the service providers (SPs). This paper models the business strategic interactions between seller and buyer SPs as a coalitional game in which sellers form coalitions to set RB prices and buyers join coalitions to determine their best-response RB demand. The aim is to maximize the profit of the seller coalition and minimize the expenses of the buyer coalition while jointly contributing to maximize system RB utilization. Due to the uncertainty of network traffic, we propose a coalitional game-guided multiagent reinforcement learning approach that takes the output of the coalitional game as the starting Nash equilibrium (NE) and computes the optimal price and demand strategies of the coalitions regardless of network condition changes. Simulation results and analysis prove the efficacy of the proposed approach in terms of optimizing seller and buyer coalition payoffs, as well as maximizing the overall RB utilization.

The integration of Mobile Edge Computing (MEC) with aerial platforms introduces novel potential for the Metaverse world by providing low-latency and highly reliable computing and communication services at the network edge. Nevertheless, this integration presents critical challenges, such as low Quality of Experience (QoE) due to the dynamic nature of aerial platforms, high resource demands, and the requirements for real-time data processing in the Metaverse environment. To address these challenges, we propose a Combinatorial Client-Master Multiagent Deep Reinforcement Learning (CCM-MADRL) based joint resource allocation and QoE maximization framework to enable intelligent real-time decision-making in aerial MEC enabled Metaverse services. We form a collaborative ecosystem where agents are designed to represent both Metaverse service providers and aerial platforms to promote fairness and efficiency in resource allocation, as well as optimize service delivery. By incorporating CCM, our approach considers diverse metrics, such as latency, reliability, meta-distance, and energy efficiency, to ensure a holistic optimization of Metaverse services. The MADRL approach enables adaptive decision-making, allowing the system to respond to the dynamic and unpredictable nature of Metaverse applications. Results from simulations that mimic realistic Metaverse scenarios demonstrate the effectiveness of the proposed CCM-MADRL framework in terms of improved service performance, reduced latency, cost, and virtual meta-distance, maximized average QoE utility of Metaverse users, and enhanced resource utilization compared to baseline algorithms.

Recently, Unmanned Aerial Vehicles (UAVs) have attracted the attention of researchers in academia and industry for providing wireless services to ground users in diverse scenarios like festivals, large sporting events, natural and man-made disasters due to their advantages in terms of versatility and maneuverability. However, the limited resources of UAV s (e.g., energy budget and different service requirements) can pose challenges for adopting UAV s for such applications. Our system model considers a UAV swarm that navigates an area, providing wireless communication to ground users with RIS support to improve the coverage of the UAV s. In this work, we introduce an optimization model with the aim of maximizing the throughput and UAVs coverage through optimal path planning of UAVs and multi-RIS phase configurations. The formulated optimization is challenging to solve using standard linear programming techniques, limiting its applicability in real-time decision-making. Therefore, we introduce a two-step solution using deep reinforcement learning and particle swarm optimization. We conduct extensive simulations and compare our approach to two competitive solutions presented in the recent literature. Our simulation results demonstrate that our adopted approach is 20 % better than the brute-force approach and 30% better than the baseline solution in terms of QoS.

Today, wireless networks are becoming responsible for serving intelligent applications, such as extended reality and metaverse, holographic telepresence, autonomous transportation, and collaborative robots. Although current fifth-generation (5G) networks can provide high data rates in terms of Giga-bytes/second, they cannot cope with the high demands of the aforementioned applications, especially in terms of the size of the high-quality live videos and images that need to be communicated in real-time. Therefore, with the help of artificial intelligence (AI)-based future sixth-generation (6G) networks, the semantic communication concept can provide the services demanded by these applications. Unlike Shannon's classical information theory, semantic communication urges the use of the semantics (meaningful contents) of the data in designing more efficient data communication schemes. Hence, in this paper, we model semantic communication as an energy minimization framework in heterogeneous wireless networks with respect to delay and quality-of-service constraints. Then, we propose a sub-optimal solution to the NP-hard combinatorial mixed-integer nonlinear programming problem (MINLP) by utilizing efficient techniques such as discrete optimization variables' relaxation. In addition, AI-based autoencoder and classifier are trained and deployed to perform semantic extraction, reconstruction, and classification services. Finally, we compare our proposed sub-optimal solution with different state-of-the-art methods, and the obtained results demonstrate its superiority.

The integration of multi-agent deep reinforcement learning (MADRL) in adaptive and intelligent home energy management systems (AI-HEMS) enhances real-time energy management by enabling intelligent decision-making among multiple agents to optimize various problems. This approach allows smart homes to dynamically respond to changes in energy demand, pricing, and user preferences. The integration of Internet of Things (IoT) devices with AI-HEMS has been promoted to efficiently manage energy resources and maintain occupants’ comfort, where IoT devices collect data on energy consumption, usage patterns, and environmental conditions. However, ensuring trade-offs between conflicting optimization objectives, such as reducing energy consumption and electricity prices, and maximizing users’ comfort levels is challenging. In this paper, we propose a MADRL-based multi-objective demand response (MODR) optimization framework to efficiently manage and control the energy consumption of smart homes. The proposed approach aims to simultaneously reduce energy costs and maximize users’ comfort, improving the overall reliability of energy systems. We first formulate the MODR optimization problem as MDP and then adopt the MADRL algorithm to solve it. The simulation results demonstrate that our proposed DR optimization approach can effectively balance the trade-off between energy cost and user comfort levels, resulting in improved energy efficiency compared to benchmark approaches.

The Internet of Vehicles (IoV) has revolutionized transportation by enabling seamless communication among vehicles and infrastructure. In emergency scenarios, the immediate dissemination of alert messages is vital for ensuring the safety of passengers, drivers, and pedestrians. This paper proposes an innovative cluster-based approach for efficient emergency message dissemination within the IoV network. Leveraging Software-Defined Networking (SDN) and Fog Computing, the proposed scheme seeks to alleviate transmission latencies and network congestion during the propagation of emergency messages in IoV networks. Empirical results unequivocally validate the superior efficacy of the proposed approach over existing methods.

Emerging megatrends like the Internet of Things (IoT), and social and mobile communication technologies are imposing new challenges on the future Internet, for which path reliability is crucial. Traditional IP networks are complex to operate and difficult to configure because they are vertically integrated: data and control plane bundled. The emerging Software-Defined Networking (SDN) architecture breaks vertical integration and separates the control logic from the data plane devices, such as switches and routers, providing a programmable infrastructure for application deployment. As a result, SDN is positioned to compute a reliable path for connected users in the event of a link failure scenario. To minimize the impact of a link failure on ongoing data flows, the prediction of a link failure requires careful attention. Machine Learning (ML) algorithms play a vital role in the link failure prediction process; however, they often have a low detection rate. To achieve a higher link failure detection rate in SDN, there is a need to design an enriched detection architecture, especially when employing ensemble ML models. This work presents LRS2, which is a meta-classification approach using base classifiers to compute a highly reliable data flow path. $\mathrm{L}\mathrm{R}\mathrm{S}^{2}$ utilizes a stacked generalization ensemble, where the base classifiers with low complexity and high diversity receive the original data as input, and each classifier predicts its subproblem. The output is a high degree of accuracy of a metaclassifier in predicting a link’s failure. Our experimental study demonstrates that the stacking ensemble has higher accuracy in predicting link failures than other ensembles or single classifiers used in the LRS2.

Demand response (DR) plays a significant role in modern energy management systems, particularly within the context of adaptive and intelligent building energy management systems (AI-BEMS). In the AI-BEMS context, DR focuses on dynamically adjusting energy usage in response to external factors, such as electricity prices, grid conditions, and environmental considerations. This survey paper explores the evolving landscape of DR within the framework of AI-BEMS, focusing on the integration of advanced technologies and adaptive strategies to optimize energy consumption and enhance grid reliability. This article reviews state-of-the-art research addressing the key concepts associated with integrating DR and AI-BEMS, including an overview of DR techniques in AI-BEMS, and an artificial intelligence and machine learning applications for the development of adaptive control strategies and DR optimization. Then, insights are provided on the future directions and the challenges in this field regarding the implementation of DR within AI-BEMS.

In recent years, significant strides in various domains have been fueled by the convergence of large-scale datasets and sophisticated machine learning algorithms. Nevertheless, the utilization of these datasets poses challenges, including privacy concerns, data ownership issues, and resource limitations. Cooperative data learning approaches have emerged as a solution, allowing multiple parties to collaboratively train machine learning models using their distributed data. While Federated Learning (FL) addresses the issue of privacy concerns, reluctance among data owners to share their data remains a challenge. It is imperative to provide incentives for participation in these cooperative learning settings to boost effectiveness and promote the widespread adoption of such approaches. This paper introduces an RL-ICDL-BC framework that seamlessly integrates principles of incentive design and cooperative learning, fostering effective collaboration among data owners. The framework’s primary objective is to motivate and reward participants for contributing their models while simultaneously preserving privacy and ensuring fairness in the learning process. Experimental evaluations utilizing Covid-19 datasets and diverse collaborative learning scenarios demonstrate the effectiveness of the proposed framework. The results reveal that incentivizing cooperative data learning leads to increased participation rates, improved model performance, and enhanced fairness in the learning process. Despite the challenges posed by non-iid data, the experiments yield outstanding outcomes, showcasing a Covid19 virus detection accuracy rate of approximately $99 \%$. This exceptional accuracy underscores the efficacy of our proposed approach in effectively detecting and mitigating the transmission of infectious diseases.

In the 5G Advanced and 6G era, wireless communication systems face security challenges, notably adversarial interference from unknown jammers in multi-user scenarios. Reconfigurable Intelligent Surfaces (RIS) present a cost-effective solution due to their low power consumption and easy deployment. Existing RIS techniques typically address simple jamming scenarios with a single static jammer, focusing on a single objective. This study introduces a multi-objective optimization approach deploying UAV-mounted RIS to counter jamming threats in wireless communications within a densely populated smart city environment. The proposed solution aims to safeguard essential services from potential disruptions caused by malicious jamming attacks during public events. We employ Proximal Policy Optimization (PPO), a lightweight Deep Reinforcement Learning (DRL) technique, to concurrently optimize the trajectory of UAV and RIS passive beamforming to address computational complexity. The objectives include maximizing the average sum rate and minimizing energy consumption. Our experiments highlight the efficacy of the PPO-based strategy, demonstrating significant improvements in average sum rates and energy efficiency amid numerous mobile devices and moving jammers. Importantly, our proposed system model outperforms a baseline from related works in maximizing the sum rate and minimizing overall energy consumption.

Digital Twin-Edge Network (DTEN) architecture is emerging as a critical component in the landscape of 6G networks, offering the promise of real-time data processing, system simulation, and edge-cloud computing. The integration of unmanned aerial vehicles (UAVs) and high-altitude platform systems (HAPS) within these architectures further adds to the complexity and capabilities, particularly in time-sensitive scenarios. The study of delay-sensitive queue-aware task offloading of real-time applications in such intricate dynamic energy-constrained networks remains nascent. This paper aims to bridge this gap by exploring optimizing IoT device association, offloading decisions, and resource allocation to maximize energy efficiency (EE) in an Air-to-Ground DTEN (A2G-DTEN). Our primary objective is to maximize the EE of the network while adhering to constraints related to queuing delays, maximum permissible task latency, and computing capabilities of edge servers. We proposed a comprehensive problem formulation and offered solutions leveraging a deep deterministic policy gradient (DDPG) based algorithm with two other baselines. The numerical results show that our proposed DDPG-based algorithm achieves high EE despite the strict task delay constraints.

The metaverse, the next digital frontier, demands high-performance models and quick personalization due to the dynamic nature of user tasks despite limited data availability. The frequent user customization is resource-intensive and data-heavy. Meta-learning, especially federated meta-learning (FML) known for its adaptive capabilities, is crucial for addressing the dynamics in metaverse, characterized by user heterogeneity, diverse data structures, and varied tasks. However, the diversity of tasks can compromise global training outcomes due to statistical heterogeneity. Given this, an urgent need arises for smart coalition formation that accounts for these disparities. This paper proposes a game-theoretic framework for managing FML in metaverse services, with meta-learners as workers. A blockchain-based cooperative coalition formation game is introduced, grounded on a reputation metric, the similarity of users, and their incentives. The reputation metric is derived based on our novel reputation system, which takes into account users' historical contributions and potential contributions to current tasks, by exploiting the correlations between past and new tasks. Meanwhile, the incentive mechanism is formulated as an optimization to minimize users energy cost and boost the users contribution for higher federated meta-learning efficacy. Simulations show the framework's resilience against misbehavior and its superiority over other schemes, improving service utility and worker profitability in metaverse meta-learning.

Deep Neural Networks (DNNs) have become the key technique to revolutionize the healthcare sector. However, conducting online remote inference is often impractical due to privacy constraints and latency requirements. To enable local computation, researchers have attempted network pruning with minimal accuracy loss or DNN distribution without affecting the performance. Yet, distributed inference can be inefficient due to the energy overhead and fluctuation of communication channels between participants. On the other hand, given that realistic healthcare systems use pre-trained models, local pruning and retraining relying only on the available scarce data is not possible. Even pre-pruned DNNs are limited in their ability to customize to the local load of data and device dynamics. The online pruning of DNN inferences without retraining is viable; however, it was not considered in the literature as most well-known techniques do not perform well without adjustment. In this paper, we propose a novel pruning strategy using Explainable AI (XAI) to enhance the performance of pruned DNNs without retraining, a necessity due to the scarcity and bias of local healthcare data. We combine distribution and pruning techniques to perform online distributed inference assisted by dynamic pruning when needed for highest accuracy. We use Non-Linear Integer Programming (NLP) to formulate our approach as a trade-off between resources and accuracy, and Reinforcement Learning (RL) to relax the problem and adapt to dynamic requirements. Our pruning criterion shows high performance compared to other reference techniques and ability to assist distribution by reducing resource usage while keeping high accuracy.

The metaverse, envisioned as the next digital frontier for avatar-based virtual interaction, involves high-performance models. In this dynamic environment, users’ tasks frequently shift, requiring fast model personalization despite limited data. This evolution consumes extensive resources and requires vast data volumes. To address this, meta-learning emerges as an invaluable tool for metaverse users, with federated meta-learning (FML), offering even more tailored solutions owing to its adaptive capabilities. However, the metaverse is characterized by users heterogeneity with diverse data structures, varied tasks, and uneven sample sizes, potentially undermining global training outcomes due to statistical difference. Given this, an urgent need arises for smart coalition formation that accounts for these disparities. This paper introduces a dual game-theoretic framework for metaverse services involving meta-learners as workers to manage FML. A blockchain-based cooperative coalition formation game is crafted, grounded on a reputation metric, user similarity, and incentives. We also introduce a novel reputation system based on users’ historical contributions and potential contributions to present tasks, leveraging correlations between past and new tasks. Finally, a Stackelberg game-based incentive mechanism is presented to attract reliable workers to participate in meta-learning, minimizing users’ energy costs, increasing payoffs, boosting FML efficacy, and improving metaverse utility. Results show that our dual game framework outperforms best-effort, random, and non-uniform clustering schemes -improving training performance by up to 10%, cutting completion times by as much as 30%, enhancing metaverse utility by more than 25%, and offering up to 5% boost in training efficiency over non-blockchain systems, effectively countering misbehaving users.

With the development of low-cost computer chips and wireless networks, any object or thing can become a component of the Internet of Things (IoT). As a result, these disparate things will gain digital intelligence, enabling them to connect with real-time data and be used for a wide range of valuable and practical IoT applications. However, due to the broadcast nature of wireless communication and the presence of eavesdroppers, the IoT systems pose serious threats to privacy and message integrity, particularly with mobile sensors. Recently, physical-layer security (PLS) has been proposed as a cost-effective solution that mitigates the impact of growing security threats. In this article, we propose a PLS-based hybrid nonorthogonal multiple access (NOMA)/power division multiplexing (PDM) IoT system that provides a high probability of secured transmission, a low computational complexity, and a low-power consumption. 3-D stochastic geometry tools have been used to introduce and evaluate our proposed scheme in a variety of practical scenarios where users are randomly located in a 3-D space. Furthermore, we derive the new scheme’s key agreement ratio (KAR) expression, the probability expressions of using NOMA and PDM modes. Moreover, we derive the associated secrecy outage probability (SOP), and the average ergodic capacity (AEC) expressions for the proposed scheme as well as for the pure NOMA and pure PDM schemes. In addition, we introduce and investigate the security power efficiency (SPE) metric, that serves as a new key agreement optimization metric. Numerical results are performed to validate the obtained analytical expressions and to assess the proposed scheme performances in terms of KAR, SOP, and AEC, when compared to pure NOMA and pure PDM schemes.

Intrusion detection systems (IDS) for the Internet of Things (IoT) systems can use AI-based models to ensure secure communications. IoT systems tend to have many connected devices producing massive amounts of data with high dimensionality, which requires complex models. Complex models have notorious problems such as overfitting, low interpretability, and high computational complexity. Adding model complexity penalty (i.e., regularization) can ease overfitting, but it barely helps interpretability and computational efficiency. Feature engineering can solve these issues; hence, it has become critical for IDS in large-scale IoT systems to reduce the size and dimensionality of data, resulting in less complex models with excellent performance, smaller data storage, and fast detection. This paper proposes a new feature engineering method called LEMDA (Light feature Engineering based on the Mean Decrease in Accuracy). LEMDA applies exponential decay and an optional sensitivity factor to select and create the most informative features. The proposed method has been evaluated and compared to other feature engineering methods using three IoT datasets and four AI/ML models. The results show that LEMDA improves the F1 score performance of all the IDS models by an average of 34% and reduces the average training and detection times in most cases.

Although Deep Neural Networks (DNN) have become the backbone technology of several Internet of Things (IoT) applications, their execution in resource-constrained devices remains challenging. To cater for these challenges, collaborative deep inference conducted by IoT devices was introduced. However, the prevalence of DNN computation suffers from severe privacy problems, e.g. data-reverse and model leakage. Particularly, malicious participants can accurately recover the received data to access sensitive information. Furthermore, the system is composed of heterogeneous data-sources represented by different DNN models that wish to execute classifications without exposing their data and models. Though, relaying the trained models to a centralized unit managing the collaboration leads to major risks because some features can be revealed through these models, in addition to dependency and scalability problems. In this paper, we present an approach that targets the privacy of collaborative inference via controlling the amount of data assigned to different participants, to prevent them from reversing attempts. Moreover, each independent data-source requesting inference will be responsible to manage the distribution of its DNN locally. In this context, different sources are required to compete over the pervasive resources while cooperating to maintain privacy welfare. We formulate this methodology, as an integer programming problem, where we establish a trade-off between the latency of co-inference and the privacy required by heterogeneous entities. A distributed solution scheme is also developed based on the Lagrangian dual problem. Next, to relax the optimization, we shape our approach as a cooperative and competitive Multi-Agent Reinforcement Learning (MARL) that supports heterogeneous/independent agents. Our comprehensive simulations demonstrated that our method yields results on par with those of a single RL agent in terms of action performance, while maintaining the privacy of individual agents’ information. Additionally, it surpasses the Independent Q-Learning (IQL) approach, where agents operate autonomously, in safeguarding inference privacy.

According to research, the vast majority of road accidents (90%) are the result of human error, with only a small percentage (2%) being caused by malfunctions in the vehicle. Smart vehicles have gained significant attention as potential solutions to address such issues. In the future of transportation, travel comfort and road safety will be ensured while also offering several value-added services. The automotive industry has undergone a significant transformation through the use of emerging technologies and wireless communication channels, resulting in vehicles becoming more interconnected, intelligent, and safe. However, these technologies and communication systems are susceptible to numerous security attacks. The objective of this paper is to present a comprehensive overview of the smart vehicle’s architecture, encompassing emerging technologies and security challenges and solutions associated with smart vehicles. There has been a significant surge in the utilization of machine learning techniques in smart vehicles. We categorically discuss common security measures, including machine learning and deep learning based solutions that have been mentioned in the literature and implemented against security threats on smart vehicles. This paper has also been titled a tutorial due to its layout, which begins with covering preliminary knowledge, terminologies, and encompassing technologies required to comprehend smart vehicles. Following this, the paper addresses the overall challenges associated with smart vehicles and then focuses on security issues. In terms of solutions, the paper discusses overall solutions to security issues in smart vehicles before delving into a specific solution based on machine learning and deep learning.

In sixth-generation (6G) networks, unmanned aerial vehicles (UAVs) are expected to be widely used as aerial base stations (ABS) due to their adaptability, low deployment costs, and ultra-low latency responses. However, UAVs consume large amounts of power to collect data from multiple sensor nodes (SNs). This can limit their flight time and transmission efficiency, resulting in delays and low information freshness. In this paper, we present a multi-access edge computing (MEC)-integrated UAV-assisted wireless sensor network (WSN) with a laser technology-based energy harvesting (EH) system that makes the UAV act as a flying energy charger to address these issues. This work aims to minimize the age of information (AoI) and improve energy efficiency by jointly optimizing the UAV trajectories, EH, task scheduling, and data offloading. The joint optimization problem is formulated as a Markov decision process (MDP) and then transformed into a stochastic game model to handle the complexity and dynamics of the environment. We adopt a multi-agent deep Q-network (MADQN) algorithm to solve the formulated optimization problem. With the MADQN algorithm, UAVs can determine the best data collection and EH decisions to minimize their energy consumption and efficiently collect data from multiple SNs, leading to reduced AoI and improved energy efficiency. Compared to the benchmark algorithms such as deep deterministic policy gradient (DDPG), Dueling DQN, asynchronous advantage actor-critic (A3C) and Greedy, the MADQN algorithm has a lower average AoI and improves energy efficiency by 95.5%, 89.9%, 78.02% and 65.52% respectively.

In the past decade, Unmanned Aerial Vehicles (UAVs) have grabbed the attention of researchers in academia and industry for their potential use in critical emergency applications, such as providing wireless services to ground users and collecting data from areas affected by disasters, due to their advantages in terms of maneuverability and movement flexibility. The UAVs' limited resources, energy budget, and strict mission completion time have posed challenges in adopting UAVs for these applications. Our system model considers a UAV swarm that navigates an area collecting data from ground IoT devices focusing on providing better service for strategic locations and allowing UAVs to join and leave the swarm (e.g., for recharging) in a dynamic way. In this work, we introduce an optimization model with the aim of minimizing the total energy consumption and provide the optimal path planning of UAVs under the constraints of minimum completion time and transmit power. The formulated optimization is NP-hard making it not applicable for real-time decision making. Therefore, we introduce a light-weight meta-reinforcement learning solution that can also cope with sudden changes in the environment through fast convergence. We conduct extensive simulations and compare our approach to three state-of-the-art learning models. Our simulation results prove that our introduced approach is better than the three state-of-the-art algorithms in providing coverage to strategic locations with fast convergence.

The space-air-ground integrated network (SAGIN) is an emerging architecture that has the potential to provide seamless, high data rates, and reliable transmission with a vastly increased coverage for intelligent edge devices (iEDs). However, the SAGIN infrastructure is quite complex consisting of multiple network segments; it is thus critical to efficiently manage the network segments' resources to ensure QoS satisfaction (e.g., delay and rate) for the various services provided to the iEDs. In this regard, network slicing (NS) and overall network softwarization technologies can play an essential role in addressing iEDs QoS and utility needs. In this work, we propose an optimal intelligent end-to-end resource allocation with network slicing in multi-tier SAGIN to maximize the network performance. We model the network depending on its service requirements. As the above optimization problem turns out to be NP-hard, we transform it into a stochastic game model and efficiently solve it through hierarchical multi-agent deep reinforcement learning (HMADRL). In particular, we decompose it into two parts, i.e., optimizing the mapping combined with slice adjustment and the resource allocation with association problem. Both problems are then solved using multi-agent DRL. The simulation results demonstrate that our proposed HMADRL algorithm outperforms the baseline algorithms in terms of maximizing the utility and QoS satisfaction of iEDs.

The conventional approach for Federated Learning (FL) is to train a global model by averaging local models trained on local data sets. However, given the limited computing resources at the mobile-edge nodes, unreliable models may be received from the Edge Nodes (ENs), which can lead to a significant performance degradation in the FL. Thus, this paper proposes a reliable and age sensitive FL framework that captures the dynamic nature of the local data and computing resources at each participating EN. Specifically, we formulate two optimization problems to select the optimal subset of ENs that can upload their local models in each round of the global model training, given a limited learning cost budget. The first problem aims at selecting the most reliable ENs that should cooperate to complete the FL process, while considering stationary data distributions at different ENs. The second problem aims at minimizing the average age of information experienced by each EN while selecting the most reliable ENs, given fast changing data distributions. Efficient solutions are proposed for the two problems with a worst-case linear complexity. Our Results, leveraging a real-world dataset, depict the efficiency of our solutions in obtaining a better performance compared to conventional FL approach.

The healthcare sector has undergone a significant transformation with the widespread adoption of Deep Neural Networks (DNN). However, due to privacy constraints and stringent latency requirements, online remote inference is not a viable option in healthcare scenarios. Many efforts have been conducted to enable local computation, such as network compression using pruning or DNN distribution among multiple resource-constrained devices. Yet, it is still challenging to conduct distributed inference due to the latency and energy overheads resulting from intermediate shared data. On the other hand, given that realistic healthcare systems use pre-trained models, local pruning and fine-tuning relying only on the scarce and biased data is not possible. Even pre-pruned DNNs are not efficient as they are not customized to the local load of data and the dynamics of devices. The dynamic and online pruning of DNN without fine-tuning is a promising solution; however, it was not considered in the literature as most well-known techniques do not perform well without adjustment. In this paper, driven by the data restrictions in healthcare sector, we propose a novel pruning strategy based on Explainable AI (XAI), with a target to enhance the pruned DNN performance without fine-tuning. Moreover, to maintain the highest possible accuracy, we propose to combine distribution and pruning techniques to perform online distributed inference assisted by dynamic pruning only when needed. Our experiments show the performance of our pruning criterion compared to other reference techniques, in addition to its ability to assist the distribution by reducing the shared data, while keeping high accuracy.

The high-altitude platform station (HAPS) is a promising 6G network technology that can meet the stringent requirements for high reliability, ultra-reliable low latency, and large-capacity communications, particularly in vehicular networks. HAPS with aerial computing and intelligent aerial software-defined networks (A-SDN) is a prominent solution to empower vehicles with limited resources. It allows vehicles in any geographical area to offload tasks and allocate resources within the dynamic infrastructure. The traditional MEC-based Internet of Vehicles (IoV) network is suffering from offloading various high data-rate real-time applications to B5G and the upcoming 6G networks. To handle this issue, we propose an intelligent HAPS-enabled IoV network to provide network connectivity, allocate resources, and allow computation in IoV networks. The HAPS is equipped with an aerial computing server and SDN, connected to the backhaul network of satellites and the cloud. The main objective is to maximize the utility of HAPS by jointly optimizing the association and resource allocation strategies of vehicles and other mobile devices. We formulate the optimization problem as a Stackelberg game. However, the formulated problem is complex to solve directly due to dynamism and multi-objective problems. Therefore, we transform it into a stochastic game model and utilize a distributed multi-agent deep reinforcement learning (MADRL) approach. In the proposed MADRL-based HAPS-assisted IoV network, the HAPS and vehicles are intelligent agents. We utilize a multi-agent deep deterministic policy gradient (MADDPG) algorithm to manage the continuous state-action. The simulation results prove that the proposed framework maximizes the network's utility and optimizes the association and resource allocation.

Telemedicine applications have recently received substantial potential and interest, especially after the COVID-19 pandemic. Remote experience will help people get their complex surgery done or transfer knowledge to local surgeons, without the need to travel abroad. Even with breakthrough improvements in internet speeds, the delay in video streaming is still a hurdle in telemedicine applications. This imposes using image compression and region of interest (ROI) techniques to reduce the data size and transmission needs. This paper proposes a Deep Reinforcement Learning (DRL) model that intelligently adapts the ROI size and non-ROI quality depending on the estimated throughput. The delay and structural similarity index measure (SSIM) comparison are used to assess the DRL model. The comparison findings and the practical application reveal that DRL is capable of reducing the delay by 13% and keeping the overall quality in an acceptable range. Since the latency has been significantly reduced, these findings are a valuable enhancement to telemedicine applications.

Crowdsourced live streaming services (CLS) present significant challenges due to massive data size and dynamic user behavior. Service providers must accommodate personalized QoE requests, while managing computational burdens on edge servers. Existing CLS approaches use a single edge server for both transcoding and user service, potentially overwhelming the selected node with high computational demands. In response to these challenges, we propose the Reinforcement Learning-based-Collaborative Edge-Assisted Live Streaming (RL-CEALS) framework. This innovative approach fosters collaboration between edge servers, maintaining QoE demands and distributing computational burden cost-effectively. By sharing tasks across multiple edge servers, RL-CEALS makes smart decisions, efficiently scheduling serving and transcoding of CLS. The design aims to minimize the streaming delay, the bitrate mismatch, and the computational and bandwidth costs. Simulation results reveal substantial improvements in the performance of RL-CEALS compared to recent works and baselines, paving the way for a lower cost and higher quality of live streaming experience.

Federated learning (FL) is a deep-learning framework developed for cases where data privacy protection is essential due to security and privacy guidelines. Collaboration between independent institutions is critical to achieving better deep-learning model accuracy due to a single institution's shortage of information acquisition. This study focuses on medical image analysis of brain tumor dataset, using a federated learning framework. One of the drawbacks of FL is the global model accuracy impact due to the imbalanced distribution of dataset's samples and classes, called non-independent and identically distributed (non-IID). FL global model accuracy degradation can be optimized by various approaches, either by manipulating the dataset using augmentation techniques and data sharing or optimizing the global model aggregation algorithm. Our method uses two augmentation techniques: Generative adversarial network (GAN) and Synthetic Minority Over-Sampling Technique (SMOTE) to balance non-IID with the typical FedAvg aggregation algorithm to optimize global model accuracy. Global model accuracy using SMOTE and GAN outperforms IID and non-IID with a few numbers of global model iterations using local imbalance or globally imbalanced datasets.

Food Computing is an emerging research field that leverages Natural Language Processing (NLP) techniques to extract valuable insights from textual data. A key task within NLP is Named Entity Recognition (NER), which involves identifying and categorizing words or phrases into predefined categories. Current, NER methods are limited in their capacity to recognize novel entity types, such as food names. Enhancing their capabilities to encompass new entities necessitates supervised training, that needs substantial labeled dataset. Labeling such datasets is time-intensive and challenging, particularly for novel entities like foods, that lack standardized definitions across various applications. Furthermore, existing state-of-the-art transformer-based techniques are not suitable for lightweight applications due to their large size and computational complexity. In this study, we present a neuro-heuristic based approach for food name recognition, specifically targeting food names or recipe names. To mitigate the need for extensive labeling, we adopt a template-based approach to prepare a dataset with labeled food entities. Our system achieves an impressive F1 accuracy of 0.97, on the dataset prepared by using multiple publicly available resources, including the Branded Food Dataset and NPR Dataset.

The widespread use of IoT devices and advances in communication technology have led to rapid development in building management systems. Considered one of the heaviest loads in commercial buildings, heating, ventilation, and air conditioning (HVAC) has been the focus of numerous studies. This paper proposes a novel approach to provide the optimal thermal sensor location for a large commercial building. The approach combines Computational Fluid Dynamics (CFD), network coverage, and clustering to establish a multi-step flow leading to the discovery of the optimal placements within the area of interest. The simulation results show that the combination of CFD and clustering can be very effective to identify potential candidates, which is then tuned using the coverage area of the network. Multiple scenarios were considered to simulate several environmental conditions, each of which leads to a different set of locations.

In recent years, the deployment of Vehicular Ad hoc Networks (VANETs) has gained significant attention due to their potential to enhance road safety and traffic efficiency. However, the dynamic nature of VANETs makes them vulnerable to various security threats, including attacks on network infrastructure and misbehavior of individual vehicles. To address these challenges, Machine Learning (ML) and Deep Learning (DL) techniques have emerged as promising solutions for the detection of attacks and misbehavior in VANETs. In this paper, we present an empirical evaluation of ML and DL approaches for misbehavior detection in the context of VANETs using realistic simulation. We employ a synthetic generated dataset that includes a wide range of attacks commonly encountered in VANETs. To simulate realistic scenarios, we utilize a popular widely used and validated network simulator (i.e., Omnet++) with different open source projects to generate VANET-specific traffic patterns and communication dynamics. An useful overview of the whole process from data generation, passing by pre-processing and model training to performance evaluation is provided with an open source guithub repository. Our evaluation encompasses different ML and DL algorithms, including support vector machines (SVM), random forests (RF), convolutional neural networks (CNN), and recurrent neural networks (RNN). We assess the performance of these approaches by measuring key metrics such as accuracy, precision, recall, and F1-score. Additionally, we compare the computational efficiency of the algorithms to identify their suitability for real-time deployment in VANET environments.

The Internet of Things (IoT) has revolutionized industrial environments by offering various solutions for control and automation. However, the increasing number of machines and the resulting massive traffic volumes pose significant challenges in achieving Quality of Service (QoS) and avoiding network overload. In addition, it is important to note that various categories of applications within the IoT necessitate distinct QoS considerations. Moreover, traffic allocation among IoT servers should be based on their respective capacity levels. In order to tackle these challenges, this study presents an innovative framework utilizing Software-Defined Networking (SDN) to effectively meet the QoS demands of diverse IoT services while also achieving traffic equilibrium among IoT servers. The experimental results indicate improved IoT QoS parameters, including throughput and delay, while maintaining a low control plane overhead.

The Wireless Sensor Networks (WSN) are designed to remotely monitor and control specific physical or environmental conditions. However, due to the open nature of WSN, many threats and attacks may arise by malicious users such as jamming attacks. Several techniques have been developed for detecting such attack. However, the majority of these solutions try to decrease the impact of signal-jamming by increasing transmission power or using complicated coordinating schemes, which might be challenging in WSNs, where the sensor devices are limited in their energy and communication capabilities. In this paper, we present a new model for securing WSNs against jamming attacks based on the Colonel Blotto game where the equilibrium defines the minimization of the worst-case attack effect on the sensors communications. Then, by investigating the Nash Equilibrium (NE) of the game and for all the potential attackers, the system computes the optimal power allocation strategy to protect the network against the malicious nodes. The simulation results show that the proposed model can secure the channel communication for WSN by 55% compared to the other technique while using the same network resources.

The number of applications of internet of things (IoT) devices in smart buildings keeps growing continuously, and with it, the computational tasks rendered by those devices. In smart buildings, IoT devices generate massive data traffic, and the number of devices and traffic volume increases exponentially. This issue is more sensitive in smart buildings as the management of their data is critical. Therefore, matching the task’s differential needs (e.g., energy, delay) with the network resources is paramount. In a device-to-device (D2D) aided edge computing (EC) architecture, tasks can be offloaded to the resource-rich IoT device or edge node to improve offloading efficiency and minimize energy consumption and delay. Exploiting these benefits, in this paper, we propose enhanced resource allocation and energy management in smart buildings enabled by software-defined networking and EC, as well as D2D aided end-to-end communications (REED). REED aims to minimize energy consumption and delay in a smart building by jointly optimizing resource allocation and offloading decisions. To find the near-optimal solution, we use the model-free deep reinforcement learning, i.e., deep deterministic policy gradient algorithm, because the formulated problem is a mixed-integer nonlinear optimization problem with a large dimensional continuous state and action spaces in a dynamic environment. Simulation results show that the intended REED model can perform better in terms of energy consumption and delay than the other benchmark approaches.

As deep neural networks continue to expand and become more complex, most edge devices are unable to handle their extensive processing requirements. Therefore, the concept of distributed inference is essential to distribute the neural network among a cluster of nodes. However, distribution may lead to additional energy consumption and dependency among devices that suffer from unstable transmission rates. Unstable transmission rates harm real-time performance of IoT devices causing low latency, high energy usage, and potential failures. Hence, for dynamic systems, it is necessary to have a resilient DNN with an adaptive architecture that can downsize as per the available resources. This paper presents an empirical study that identifies the connections in ResNet that can be dropped without significantly impacting the model’s performance to enable distribution in case of resource shortage. Based on the results, a multi-objective optimization problem is formulated to minimize latency and maximize accuracy as per available resources. Our experiments demonstrate that an adaptive ResNet architecture can reduce shared data, energy consumption, and latency throughout the distribution while maintaining high accuracy.

The spread of infectious diseases in crowded spaces such as shopping malls, markets, and hospitals is a growing concern. In order to mitigate this risk, it is crucial to develop a method that leverages the power of distributed crowd to learn, de- tect, and alert individuals about potential health hazards. Hence, the integration of federated learning (FL), and blockchain (BC) to provide intelligent platforms that facilitate pervasive AI and trust amongst IoT devices and smart phones can play a significant role in achieving this goal. In this study, we propose a new technique named BC-FL Location-Based, which utilizes smart applications installed on IoT devices and smart phones to detect and predict imminent health risks. The technique works by using algorithms such as maximal clique to detect individuals in close proximity and sharing their health data through a blockchain network. A smart contract then triggers a node with sufficient resources to gather users' learning experiences from the blockchain, aggregate it, and run a model to determine if any of the individuals present in the area are infected. To demonstrate the effectiveness of the proposed technique, we conducted simulation experiments using Ethereum-based private blockchain network, where nodes represent individuals in different locations. We used the maximal clique algorithm to simulate the movement of individuals and compared the results of the model run on individual data versus aggregated data. Experiments showed promising results, with accuracy of detection increasing to 99% when using iid data and 90% when using non-iid data.

A cyber-physical system (CPS) is a promising paradigm in 5G and future 6G networks that controls physical components through computing and communication while ensuring efficacy, intelligence, and security. The number of smart mobile devices or sensors in smart cities is growing very fast. These devices can process applications in real-time only for a short time due to limited resource capacity. The Mobile Edge Computing (MEC) paradigm is a prominent solution that allows devices to offload intensive tasks and allocate resources. However, the terrestrial MEC servers will be overwhelmed and unable to meet the requirements of 6G technologies for ultra-low-latency applications and mobile devices. Aerial-borne MEC servers have recently supported ultra-reliable, low-latency communication applications and mobile devices in an emergency scenario by providing resources and relaying them to a cloud server. In the intelligent aerial-enabled smart city CPS (S2CPS), decisionmaking tasks such as resource allocation, association, and ensuring trust between links are challenging, and the optimization problem is multi-objective. Therefore, we proposed a hierarchical, deep federated learning-empowered, energy-efficient resource allocation for aerial-enabled S2CPS to minimize the overall energy consumption while considering the quality of service of user devices and the privacy of task offloading in a dynamic environment. We validated the proposed framework through extensive simulations, proving it outperformed the baseline algorithms.

Recently, Unmanned Aerial Vehicles (UAVs) have shown impressive performance in many critical applications, such as surveillance, search and rescue operations, environmental monitoring, etc. In many of these applications, the UAVs capture images as well as other sensory data and then send the data processing requests to remote servers. Nevertheless, this approach is not always practical in real-time-based applications due to unstable connections, limited bandwidth, limited energy, and strict end-to-end latency. One promising solution is to divide the inference requests into subtasks that can be distributed among UAVs in a swarm based on the available resources. Moreover, these tasks create intermediate results that need to be transmitted reliably as the swarm moves to cover the area. Our system model deals with real-time requests, aiming to find the optimal transmission power that guarantees higher reliability and low latency. We formulate the Low Latency and High-Reliability (LLHR) distributed inference as an optimization problem, and due to the complexity of the problem, we divide it into three subproblems. In the first subproblem, we find the optimal transmit power of the connected UAVs with guaranteed transmission reliability. The second subproblem aims to find the optimal positions of the UAVs in the grid, while the last subproblem finds the optimal placement of the CNN layers in the available UAVs. We conduct extensive simulations and compare our work to two baseline models demonstrating that our model outperforms the competing models.

The rise of chronic disease patients and the pandemic pose immediate threats to healthcare expenditure and mortality rates. This calls for transforming healthcare systems away from one-on-one patient treatment into intelligent health systems, leveraging the recent advances of Internet of Things and smart sensors. Meanwhile, reinforcement learning (RL) has witnessed an intrinsic breakthrough in solving a variety of complex problems for distinct applications and services. Thus, this article presents a comprehensive survey of the recent models and techniques of RL that have been developed/used for supporting Intelligent-healthcare (I-health) systems. It can guide the readers to deeply understand the state-of-the-art regarding the use of RL in the context of I-health. Specifically, we first present an overview of the I-health systems’ challenges, architecture, and how RL can benefit these systems. We then review the background and mathematical modeling of different RL, deep RL (DRL), and multiagent RL models. We highlight important guidelines on how to select the appropriate RL model for a given problem, and provide quantitative comparisons, showing the results of deploying key RL models in two scenarios that can be followed in monitoring applications. After that, we conduct an in-depth literature review on RL’s applications in I-health systems, covering edge intelligence, smart core network, and dynamic treatment regimes. Finally, we highlight emerging challenges and future research directions to enhance RL’s success in I-health systems, which opens the door for exploring some interesting and unsolved problems.

With the swift growth of mobile devices in a wireless Internet of Things (IoT) network, mobility management in IP networks has attracted significant research interest due to certain issues with the frequent motion of mobile nodes (MNs) participating in the handover process. Hierarchical mobile IPv6 (HMIPv6) is one of the protocols proposed to accommodate recurrent mobility of MNs to decrease the signaling amount and improve packet loss issues, by localizing the mobility. HMIPv6 treats micro and macro mobility separately by introducing a new level in mobile IPv6 (MIPv6) with the addition of a node called mobility anchor point (MAP) which significantly improved handover performance specifically in micro-mobility. However, macro mobility yet needed to be improved as it is managed in a way as MIPv6 does. The registration of MN with the new MAP domain is a lengthy process, which leads to longer handover latency with high signaling cost to start proper communication again. Here, we proposed an advance-binding update HMIPv6 (A-BU), a group-based scheme to lessen interdomain handoff latency of IoT MNs. The efficiency of the proposed technique is validated with numerical analysis. The results compared with state-of-the-art mobility protocols illustrate a visible reduction in handover cost, signaling cost and provide seamless packet delivery during group-based interdomain mobility.

The deployment flexibility and maneuverability of unmanned aerial vehicles (UAVs) increased their adoption in various applications, such as wildfire tracking, border monitoring, etc. In many critical applications, UAVs capture images and other sensory data and then send the captured data to remote servers for inference and data processing tasks. However, this approach is not always practical in real-time applications due to the connection instability, limited bandwidth, and end-to-end latency. One promising solution is to divide the inference requests into multiple parts (layers or segments), with each part being executed in a different UAV based on the available resources. Furthermore, some applications require the UAVs to traverse certain areas and capture incidents; thus, planning their paths becomes critical particularly, to reduce the latency of making the collaborative inference process. Specifically, planning the UAVs trajectory can reduce the data transmission latency by communicating with devices in the same proximity while mitigating the transmission interference. This work aims to design a model for distributed collaborative inference requests and path planning in a UAV swarm while respecting the resource constraints due to the computational load and memory usage of the inference requests. The model is formulated as an optimization problem and aims to minimize latency. The formulated problem is NP-hard so finding the optimal solution is quite complex; thus, this article introduces a real-time and dynamic solution for online applications using deep reinforcement learning. We conduct extensive simulations and compare our results to the state-of-the-art studies demonstrating that our model outperforms the competing models.

Remote monitoring systems analyze the environment dynamics in different smart industrial applications, such as occupational health and safety, and environmental monitoring. Specifically, in Industrial Internet of Things (IIoT) systems, the huge number of devices and the expected performance put pressure on resources, such as computational, network, and device energy. Distributed training of machine and deep learning (ML/DL) models for intelligent industrial IoT applications is very challenging for resource limited devices over heterogeneous wireless networks (HetNets). Hierarchical federated learning (HFL) performs training at multiple layers offloading the tasks to nearby multiaccess edge computing (MEC) units. In this article, we propose a novel energy-efficient HFL framework enabled by wireless energy transfer (WET) and designed for heterogeneous networks with massive multiple-input–multiple-output (MIMO) wireless backhaul. Our energy-efficiency approach is formulated as a mixed-integer nonlinear programming (MINLP) problem, where we optimize the HFL device association and manage the wireless transmitted energy. However due to its high complexity, we design a heuristic resource management algorithm, namely, H2RMA, that respects energy, channel quality, and accuracy constraints, while presenting a low-computational complexity. We also improve the energy consumption of the network using an efficient device scheduling scheme. Finally, we investigate device mobility and its impact on the HFL performance. Our extensive experiments confirm the high performance of the proposed resource management approach in HFL over HetNets, in terms of training loss and grid energy costs.

In the 5G/B5G network paradigms, intelligent medical devices known as the Internet of Medical Things (IoMT) have been used in the healthcare industry to monitor remote users’ health status, such as elderly monitoring, injuries, stress, and patients with chronic diseases. Since IoMT devices have limited resources, mobile edge computing (MEC) has been deployed in 5G networks to enable them to offload their tasks to the nearest computational servers for processing. However, when IoMTs are far from network coverage or the computational servers at the terrestrial MEC are overloaded/emergencies occur, these devices cannot access computing services, potentially risking the lives of patients. In this context, unmanned aerial vehicles (UAVs) are considered a prominent aerial connectivity solution for healthcare systems. In this article, we propose a multiagent federated reinforcement learning (MAFRL)-based resource allocation framework for a multi-UAV-enabled healthcare system. We formulate the computation offloading and resource allocation problems as a Markov decision process game in federated learning with multiple participants. Then, we propose an MAFRL algorithm to solve the formulated problem, minimize latency and energy consumption, and ensure the quality of service. Finally, extensive simulation results on a real-world heartbeat data set prove that the proposed MAFRL algorithm significantly minimizes the cost, preserves privacy, and improves accuracy compared to the baseline learning algorithms.

Runtime-verification of smart contracts ensures the absence of exploitations within a transaction during execution. It is a crucial security aspect that is often omitted due to its high onchain overhead. The lack of runtime-verification in public blockchains allowed attackers to compromise vulnerable contracts and cause significant monetary losses. Although several runtime protection solutions have been proposed, they do not discuss the onchain overhead limitation, which may hinder their deployment and undermine their effectiveness. To address this problem, we propose an efficient Smart contract Runtime Protection framework, called SRP, that minimizes the onchain burden of runtime-verification by integrating an off-chain mechanism with onchain contract execution. The proposed hybrid architecture is designed to protect already-deployed smart contracts from attacks in real-time while maintaining the throughput of the underlying blockchain. We first present SRP from a design perspective proposing a protocol customized for off-chain runtime-verification interoperability. Then, we evaluate our approach empirically and demonstrate the applicability of SRP using a proof-of-concept implementation on a local instance of the Ethereum network. Our empirical and experimental results indicate the feasibility and efficiency of our approach, where SRP outperforms the onchain-only mechanism in terms of service time and throughput, for increasing workloads.

Self-supervised contrastive learning has shown a significant improvement in performance for action recognition tasks by discovering useful signals from unlabeled videos. Nevertheless, the unique features of existing video benchmark datasets have led the learned video representations to be contextually biased toward dominant backgrounds and scene correlations. Thus, ultimately leading to poor generalizations on scene-invariant action recognition. Therefore, we propose Actor-aware Self-supervised Learning for Semi-supervised Video Representation Learning (ActorSL). We aligned localized actors and their corresponding scene information to encourage the model to learn discriminative regions and mitigate the model’s dependency on the video background during contrastive training. Furthermore, we present an inter-video Background Mixing (iBM) augmentation strategy to introduce scene consistency into the model. We patch inter-video crops of four randomly selected frames for iBM to create a unique frame for each video. The patched frame is blended with the target video frames to generate a spatially augmented sample. Then, the actor-scene aligned features and features of iBM-augmented videos are utilized to optimize contrastive loss and consistency regularization jointly in a semi-supervised way. Moreover, iBM combines the one-hot-encoded labels of patches with the label of the target video as a label smoothing regularizer to soften the decision boundaries of the semi-supervised model. Our experimental results reveal that, ActorSL notably improved current state-of-the-art semi-supervised methods on the Kinetics-400, UCF101, and HMDB51 datasets under a low-label regime. Code released athttps://github.com/Endarzboy/ActorSL.

In recent years researchers have shown significant interest in vehicular networks to augment road safety by providing real-time messaging services among vehicles. This work aims to provide a detailed analysis of emergency message dissemination techniques for the Internet of Vehicles (IoV). We explored position-based data dissemination techniques for emergency message dissemination, which is considered the best routing method because it does not rely on predestination entries of the route. Position-based schemes encounter some challenges, such as delay and accurate positioning. Existing survey papers of IoV focused on architecture, technologies, and layers. However, this article examines a brief comparison of subtypes of position-based emergency message routing, beacon-oriented and beacon-less techniques. In the end, we presented the basic challenges of emergency message dissemination; moreover, future directions are highlighted to promote the development of new protocols for emergency message dissemination to enhance the efficiency of IoV in a better way.

5G-and-beyond networks are designed to fulfill the communication and computation requirements of various industries, which requires not only transporting the data, but also processing them to meet/address diverse key performance indicators (KPIs). Network Function Virtualization (NFV) has emerged to enable this vision by: (i) collecting the requirements of diverse services, using graphs of Virtual Network Functions (VNFs); and (ii) mapping these requirements into network management decisions. Because of the latter, we need to efficiently allocate computing and network resources to support the desired services, and because of the former such decisions must be jointly optimized considering all KPIs associated with supported services. Thus, this paper proposes an optimized, intelligent network slicing framework to maintain a high performance of network operation by supporting diverse and heterogeneous services, while meeting new KPIs, e.g., reliability, energy consumption, and data quality. Different from the existing works, which are mainly designed considering traditional metrics like throughput and latency, we present a novel methodology and resource allocation schemes that enable high-quality selection of radio points of access, VNF placement and data routing, as well as data compression ratios, from the end users to the cloud. Our results depict the efficiency of the proposed framework in enhancing the network performance when compared to baseline approaches that consider partial network view or fair resource allocation.

With the Industrial Internet of Things (IIoT), mobile devices (MDs) and their demands for low-latency data communication are increasing. Due to the limited resources of MDs, such as energy, computation, storage, and bandwidth, IIoT systems cannot meet MDs’ quality of service (QoS) and security requirements. Recently, UAVs have been deployed as aerial base stations in the IIoT network to provide connectivity and share resources with MDs. We consider a resource trading environment where multiple resource providers compete to sell their resources to MDs and maximize their profit by continually adjusting their pricing strategies. Multiple MDs, on the other hand, interact with the environment to make purchasing decisions based on the prices set by resource providers to reduce costs and improve QoS. We propose a novel intelligent resource trading framework that integrates multi-agent deep reinforcement Learning (MADRL), blockchain, and game theory to manage dynamic resource trading environments. A consortium blockchain with a smart contract is deployed to ensure the security and privacy of the resource transactions. We formulated the optimization problem using a Stackelberg game. However, the formulated optimization problem in the multi-agent IIoT environment is complex and dynamic, making it difficult to solve directly. Thus, we transform it into a stochastic game to solve the dynamics of the optimization problem. We propose a dynamic pricing algorithm that combines the Stackelberg game with the MADRL algorithm to solve the formulated stochastic game. The simulation results show that our proposed scheme outperforms others to improve resource trading in UAV-assisted IIoT networks.

Clustered federated Multitask learning is introduced as an efficient technique when data is unbalanced and distributed amongst clients in a non-independent and identically distributed manner. While a similarity metric can provide client groups with specialized models according to their data distribution, this process can be time-consuming because the server needs to capture all data distribution first from all clients to perform the correct clustering. Due to resource and time constraints at the network edge, only a fraction of devices is selected every round, necessitating the need for an efficient scheduling technique to address these issues. Thus, this paper introduces a two-phased client selection and scheduling approach to improve the convergence speed while capturing all data distributions. This approach ensures correct clustering and fairness between clients by leveraging bandwidth reuse for participants spent a longer time training their models and exploiting the heterogeneity in the devices to schedule the participants according to their delay. The server then performs the clustering depending on predetermined thresholds and stopping criteria. When a specified cluster approximates a stopping point, the server employs a greedy selection for that cluster by picking the devices with lower delay and better resources. The convergence analysis is provided, showing the relationship between the proposed scheduling approach and the convergence rate of the specialized models to obtain convergence bounds under non-i.i.d. data distribution. We carry out extensive simulations, and the results demonstrate that the proposed algorithms reduce training time and improve the convergence speed by up to 50% while equipping every user with a customized model tailored to its data distribution.

Federated learning (FL) paradigms aim to amalgamate diverse data properties stored locally at each user, while preserving data privacy through sharing users’ learning experiences and iteratively aggregating their local learning models into a global one. However, the majority of FL architectures with centralized cloud do not guarantee the trust in sharing users’ models, and hence, open the door for slowing and/or contaminating the global learning experience. In this paper, we propose a decentralized Blockchain (BC)-based framework and define a comprehensive protocol for exchanging local models, in order to guarantee users’ mutual trust while sharing their local learning experiences. We then propose a technique to optimize the global learning experience using Reinforcement Learning (RL), namely RL-FL-BC, to tackle the trade-off between information age of the learning parameters, data skewness (i.e., non-iid), and BC transaction cost (i.e., Ether price). We implement the proposed framework in a realistic containerized environment to facilitate the comparative study of the RL-FL-BC technique with baselines techniques. Our results show the efficacy of the BC-based protocol to facilitate the exchange of both the models’ and the optimization parameters to guarantee users’ mutual trust, while improving global learning performance compared to baselines techniques.

Federated edge learning (FEEL) is a rapidly growing distributed learning technique for next-generation wireless edge systems. Smart systems across various application domains face challenges, such as data heterogeneity, limited wireless resources, and device heterogeneity, which necessitate intelligent participant selection schemes that accelerate convergence rates. Consequently, this article presents joint participant selection and bandwidth allocation schemes to address these challenges. First, we formulate an optimization problem that considers communication and computation latencies, as well as imbalanced data distribution, while meeting round deadlines and bandwidth constraints. To address the combinatorial problems of participant selection, we employ a relaxation method followed by a proposed priority selection algorithm to select near-optimal participants. The proposed algorithm initially prioritizes participants with larger datasets, effective channel states, and better CPU speeds. To address data heterogeneity, we propose a randomized deadline-controlling algorithm that diversifies updates by allowing the edge server to include different participants with fewer data samples in training rounds. The proposed algorithms offer near-optimal performance compared to the brute-force method. Experiments demonstrate that our proposed scheme accelerates the convergence rate by up to 55% under extensive non-IID settings compared to benchmarks. Furthermore, the deadline-controlling algorithm improves performance at high levels of data heterogeneity, resulting in faster FEEL systems.

In 6G networks, unmanned aerial vehicles (UAVs) can serve as aerial flying base stations (AFBS) with aerial mobile edge computing (AMEC) server capabilities. AFBS is an increasingly popular solution for delivering time-sensitive applications, extending network coverage, and assisting ground base stations in the healthcare systems for remote areas with limited infrastructure. Furthermore, the UAVs are deployed in the healthcare system to support the Internet of medical things (IoMT) devices in data collection, medical equipment distribution, and providing smart services. However, ensuring the privacy and security of patients' data with the limited UAV resources is a major challenge. In this paper, we present a federated deep reinforcement learning framework for resource allocation in UAV-enabled healthcare systems, where IoMT devices send their trained model parameters without transmitting sensitive raw data to the AMEC server. In the proposed framework, the IoMT device is associated with AFBS based on the quality of the data and its demand in order to maximize learning efficiency and accuracy. This work aims to minimize the computation costs of the IoMT devices while considering UAV resources and the fairness of UAV coverage. Simulation results prove that our proposed algorithm outperforms other baseline algorithms in learning accuracy and computational cost.

In recent years, Federated Edge Learning has gained interest from both industry and academia for deployment at the wireless network edge. However, some resource-restricted edge devices (EDs) bear more computation and communication loads due to the heterogeneity of data and resources. Several approaches have been proposed in the literature to reduce energy costs by scheduling only a few EDs to complete training tasks based on their energy budgets. Nevertheless, from a practical perspective, the incongruent data distribution cannot be captured, resulting in a biased model for EDs that are frequently selected. Furthermore, the frequently scheduled devices deplete their energy quickly, making them inaccessible. Thus, this paper proposes a novel scheduling policy based on the historical participation of each ED that ensures an unbiased model while balancing learning tasks so that all EDs consume equivalent energy at the end of the training. We formulate an optimization problem based on Jain's fairness index, followed by tractable algorithms to solve this problem. Extensive experiments have been conducted, and the results show that the proposed algorithm balances the energy consumption among EDs and accelerates the convergence rate while achieving satisfactory performance.

Telemedicine is a rising technology that is gaining a lot of interest in the recent decades. Several applications of telemedicine are delay-sensitive and need to be operated in real-time. One of which is surgical tele-mentoring where a remote expert surgeon mentors local surgeons during an operation. While the advances done in telecommunications and robotics have made tele-mentoring possible in modern days, there are still many challenges that stop such telemedical applications from being completely legalized and approved as medical tools across the world. One of the main issues is the need for very high bandwidth to allow the surgery to be done accurately in real-time. Such bandwidth requirements are difficult to provide especially in rural areas with limited communications infrastructure. We propose an adaptive Region of Interest (ROI) detection and an optimization model that addresses the trade-off between the overall quality of a surgical video and the network delay. The model aims to maximize the size of the ROI, where highest video quality must be used, depending on the available network throughput, while avoiding excessive degradation of the quality of the background.

The extremely heavy global reliance on IoT devices is causing enormous amounts of data to be gathered and shared in IoT networks. Such data need to efficiently be used in training and deploying of powerful artificially intelligent models for better future event detection and decision making. However, IoT devices suffer from many limitations regarding their energy budget, computational power, and storage space. Therefore, efficient solutions have to be studied and proposed for addressing these limitations. In this paper, we propose an energy-efficient Hierarchical Federated Learning (HFL) framework with optimized client-edge association and resource allocation. This was done by formulating and solving a communication energy minimization problem that takes into consideration the data distribution of the clients and the communication latency between the clients and edges. We also implement an alternative less complex solution leveraging Reinforcement Learning (RL) that provides a fast user-edge association and resource allocation response in highly dynamic HFL networks. The proposed two solutions are compared with several state-of-the-art client-edge association techniques, leveraging MNIST dataset. Moreover, we study the trade-off between minimizing the per-round energy consumption and Kullback-Leibler Divergence (KLD) of the data distribution, and its effect on the total energy consumption.

A new generation of advanced information technologies are used nowadays by healthcare systems to provide access to affordable and high-quality healthcare services. However, such services, generally require a large amount of data that needs to be stored, shared and secured efficiently. Therefore, a secure distributed data storing and sharing mechanism is proposed in this paper for healthcare systems. By using a specifically designed data splitting and encryption approach, the proposed sharing mechanism ensures that any user in the network can recuperate the data only if it gets the approval of a prefixed number of trusted nodes. This ensure that although the data is distributed among different network nodes, it becomes useless without the collection of the necessary data parts and approvals. In order to enhance the data sharing robustness to failures while minimizing the transmission delays, and satisfying the network constraints, an iterative algorithm is proposed to optimize the selection of the nodes that should participate in the data storage process. The simulation results confirm the efficiency of the proposed approaches to efficiently and securely store and share the data with the other legitimate nodes.

Federated Learning (FL) is a collaborative machine learning (ML) approach, where different nodes in a network contribute to learning the model parameters. In addition, FL provides several attractive features such as data privacy and energy efficiency. Due to its collaborative nature, model parameters among nodes should be efficiently exchanged, while considering the scarce availability of clean spectral slots. In this work, we propose low-power efficient algorithms for FL of model parameters updates. We consider mobile edge nodes connected to a leading node (LD) with practical wireless links, where uplink updates from the nodes to the LD are shared without orthogonalizing the resources. In particular, we adopt a non-orthogonal multiple access (NOMA) uplink scheme, and investigate its effect on the convergence round (CR) of the model updates. Through deriving an analytical expression of the CR, we leverage it to formulate an optimization problem to minimize the total number of communication rounds and maximize the communication fairness among the nodes. We further investigate the performance of our proposed algorithms by considering different factors, including limited per-node energy and node heterogeneity. Monte-Carlo simulations are used to verify the accuracy of our derived expression of the CR. Moreover, through comprehensive simulation, we show that our proposed schemes largely reduce the communication latency between the LD and the nodes, and improve the communication fairness among the nodes.

5G networks are designed not only to transport data, but also to process them while supporting a vast number of services with different key Performance Indicators (KPIs). Network virtualization has emerged to enable this vision, however it calls for designing efficient computing and network resource allocation schemes to support diverse services, while jointly considering all KPIs associated with these services. Thus, this paper proposes a dynamic network slicing and resource allocation framework that aims at maintaining high-level network operational performance, while fulfilling diverse services’ requirements and KPIs, e.g., availability, reliability, and data quality. Differently from the existing works, which are designed considering traditional metrics like throughput and latency, we present a novel methodology and resource allocation schemes that enable high-quality selection of radio points of access, resource allocation, and data routing from end users to the cloud. Our results depict that the proposed solutions could obtain the best trade-off between diverse services’ requirements when compared to baseline approaches that consider partial network view or fair resource allocation.

With the advent of Internet of Things (IoT) systems, privacy and integrity of messages are becoming critical issues and are threatened, especially with mobile sensors. The broadcast nature of wireless communications increase information leakage in the presence of eavesdroppers. This paper proposes a hybrid Non-Orthogonal Multiple Access (NOMA)/Orthogonal Multiple Access (OMA)- based IoT systems to improve the data transmission security of moving sensors. We derive the Key Agreement Probability (KAP) expression of the proposed scheme, and we investigate the corresponding Secrecy Outage Probability (SOP) and the Average Bit Rate (ABR), when compared to pure NOMA and pure OMA transmission schemes. Simulation results are used to validate the derived expression and to evaluate the performance of the proposed scheme in terms of KAP, SOP, and ABR.

In this paper, we investigate an energy-efficient Long Range (LoRa) wireless network powered by hybrid energy which consists of an energy harvesting source and the grid. The grid allows to compensate for the randomness and intermittency of the harvested energy. The aim is to propose a dynamic energy-efficient resource management scheme for LoRa wireless networks that enables green Internet of Things (IoT). Hence, we formulate a grid energy cost minimization problem subject to minimum received signal-to-noise ratio (SNR), and channel, spreading factor (SF) and energy availability constraints. The formulated problem is simplified and decoupled into two sub-problems which allows to derive the optimal resource management solution but with high computational complexity. Then, we propose a low complexity heuristic channel and SF assignment, and energy management algorithm for dynamic LoRa wireless networks. Numerical results shows the efficient use of renewable energy in green dynamic LoRa wireless networks.

Federated Learning (FL) is a distributed learning methodology that allows multiple nodes to cooperatively train a deep learning model, without the need to share their local data. It is a promising solution for telemonitoring systems that demand intensive data collection, for detection, classification, and prediction of future events, from different locations while maintaining a strict privacy constraint. Due to privacy concerns and critical communication bottlenecks, it can become impractical to send the FL updated models to a centralized server. Thus, this paper studies the potential of hierarchical FL in Internet of Things (IoT) heterogeneous systems. In particular, we propose an optimized solution for user assignment and resource allocation over hierarchical FL architecture for IoT heterogeneous systems. This work focuses on a generic class of machine learning models that are trained using gradient-descent-based schemes while considering the practical constraints of non-uniformly distributed data across different users. We evaluate the proposed system using two real-world datasets, and we show that it outperforms state-of-the-art FL solutions. Specifically, our numerical results highlight the effectiveness of our approach and its ability to provide 4–6% increase in the classification accuracy, with respect to hierarchical FL schemes that consider distance-based user assignment. Furthermore, the proposed approach could significantly accelerate FL training and reduce communication overhead by providing 75–85% reduction in the communication rounds between edge nodes and the centralized server, for the same model accuracy.

The security and privacy of the network in Internet of Things (IoT) systems are becoming more critical as we are more dependent on smart systems. Considering that packets are exchanged between the end user and the sensing devices, it is then important to ensure the security, privacy, and integrity of the transmitted data by designing a secure and a lightweight authentication protocol for IoT systems. In this article, in order to improve the authentication and the encryption in IoT systems, we present a novel method of authentication and encryption based on elliptic curve cryptography (ECC) using random numbers generated by fuzzy logic. We evaluate our novel key generation method by using standard randomness tests, such as: frequency test, frequency test with mono block, run test, discrete Fourier transform (DFT) test, and advanced DFT test. Our results show superior performance compared to existing ECC based on shift registers. In addition, we apply some attack algorithms, such as Pollard’s$\rho $and Baby-step Giant-step, to evaluate the vulnerability of the proposed scheme.

Federated learning (FL) is a promising paradigm for future sixth-generation wireless systems to underpin network edge intelligence for smart cities applications. However, most of the data collected by the Internet of Things devices in such applications is unlabeled, necessitating the use of semi-supervised learning. Existing studies have introduced solutions to run semi-supervised FL; however, they overlooked the inherent critical impacts of the wireless characteristics at the network edge. We fill this gap by proposing novel solutions to run semi-supervised FL over wireless network edge, considering the limited computation and communication resources and deadline constraints and realizing that unlabeled data can be automatically labeled during the training rounds to improve the performance of the global model. The problem is first formulated as an optimization problem followed by a two-phase solution. In the first phase, we propose a bisection-based algorithm to find the transmit power and local processing speed that optimally fit the new injected labeled data. In the second phase, we propose three algorithms to control the local updates and injected samples that meet the deadline constraint. We analyze the performance of each algorithm concerning the tradeoffs between learning performance, training time, and total energy consumption. Targeting two applications in smart cities, human activity recognition and object detection, we conduct extensive simulations using realistic federated data sets under nonindependent and identically distributed settings. Numerical results show that the proposed algorithms effectively utilize unlabeled samples while accounting for the characteristics of wireless edge networks in smart cities.

Internet of Things (IoT) systems are becoming core building blocks for different services and applications supporting every day’s life. The heterogeneous nature of IoT devices and the complex use scenarios make it hard to build secure and private IoT systems. Physical-layer security (PLS) can lead to efficient solutions reducing the impact of the increasing security threats. In this work, we propose a new PLS-based IoT transmission scheme that offers a highly secured transmission probability, low-computational complexity, and reduced power consumption. We utilize 3-D stochastic geometry to model a more realistic IoT system and test our proposed scheme in different practical scenarios, where sensors, access points (APs), and eavesdroppers are randomly located in 3-D space. We focus on the system performance, in terms of secrecy outage probability (SOP) and secured successful transmission probability (SSTP), using tight closed-form expressions. An optimization problem is developed to deduce the optimal sensors’ transmit power, the APs’ density, and the maximum number of transmission tentative, when maximizing the SSTP. The proposed scheme outperforms the baseline retransmission scheme, in terms of SOP and SSTP based on analytical and simulation results.

LoRa wireless networks are considered as a key enabling technology for next-generation Internet of Things (IoT) systems. New IoT deployments (e.g., smart city scenarios) can have thousands of devices per square kilometer leading to huge amount of power consumption to provide connectivity. In this article, we investigate green LoRa wireless networks powered by a hybrid of the grid and renewable energy sources, which can benefit from harvested energy while dealing with the intermittent supply. This article proposes resource management schemes of the limited number of channels and spreading factors (SFs) with the objective of improving the LoRa gateway energy efficiency. First, the problem of grid power consumption minimization while satisfying the system’s quality of service demands is formulated. Specifically, both scenarios the uncorrelated and time-correlated channels are investigated. The optimal resource management problem is solved by decoupling the formulated problem into two subproblems: 1) channel and SF assignment problem and 2) energy management problem. Since the optimal solution is obtained with high complexity, online resource management heuristic algorithms that minimize the grid energy consumption are proposed. Finally, taking into account the channel and energy correlation, adaptable resource management schemes based on reinforcement learning (RL) are developed. Simulation results show that the proposed resource management schemes offer efficient use of renewable energy in LoRa wireless networks.

Unmanned aerial vehicles (UAVs) have attracted great interest in the last few years owing to their ability to cover large areas and access difficult and hazardous target zones, which is not the case of traditional systems relying on direct observations obtained from fixed cameras and sensors. Furthermore, thanks to the advancements in computer vision and machine learning, UAVs are being adopted for a broad range of solutions and applications. However, deep neural networks (DNNs) are progressing toward deeper and complex models that prevent them from being executed onboard. In this article, we propose a DNN distribution methodology within UAVs to enable data classification in resource-constrained devices and avoid extra delays introduced by the server-based solutions due to data communication over air-to-ground links. The proposed method is formulated as an optimization problem that aims to minimize the latency between data collection and decision-making while considering the mobility model and the resource constraints of the UAVs as part of the air-to-air communication. We also introduce the mobility prediction to adapt our system to the dynamics of UAVs and the network variation. The simulation conducted to evaluate the performance and benchmark the proposed methods, namely, optimal UAV-based layer distribution (OULD) and OULD with mobility prediction (OULD-MP), was run in an HPC cluster. The obtained results show that our optimization solution outperforms the existing and heuristic-based approaches.

Clustered Federated Multitask Learning (CFL) was introduced as an efficient scheme to obtain reliable specialized models when data is imbalanced and distributed in a non-i.i.d. (non-independent and identically distributed) fashion amongst clients. While a similarity measure metric, like the cosine similarity, can be used to endow groups of the client with a specialized model, this process can be arduous as the server should involve all clients in each of the federated learning rounds. Therefore, it is imperative that a subset of clients is selected periodically due to the limited bandwidth and latency constraints at the network edge. To this end, this paper proposes a new client selection algorithm that aims to accelerate the convergence rate for obtaining specialized machine learning models that achieve high test accuracies for all client groups. Specifically, we introduce a client selection approach that leverages the devices' heterogeneity to schedule the clients based on their round latency and exploits the bandwidth reuse for clients that consume more time to update the model. Then, the server performs model averaging and clusters the clients based on predefined thresholds. When a specific cluster reaches a stationary point, the proposed algorithm uses a greedy scheduling algorithm for that group by selecting the clients with less latency to update the model. Extensive experiments show that the proposed approach lowers the training time and accelerates the convergence rate by up to 50% while imbuing each client with a specialized model that is fit for its local data distribution.

Mobile Edge Learning (MEL) is a decentralized learning paradigm that enables resource-constrained IoT devices to either learn a shared model without sharing the data, or to distribute the learning task with the data to other IoT devices and utilize their available resources. In the former case, IoT devices (a.k.a learners) need to be assigned an orchestrator to facilitate the learning and models' aggregation from different learners. Whereas in the latter case, IoT devices act as orchestrators and look for learners with available resources to distribute the learning task to. However, the coexistence of multiple learning problems in an environment with limited resources poses the learners-orchestrator assignment problem. To this end, we aim to develop an energy-efficient learner assignment and task allocation scheme, in which each orchestrator gets assigned a group of learners based on their communication channel qualities and computational resources. We formulate and solve a multi-objective optimization problem to minimize the total energy consumption and maximize the learning accuracy. To reduce the solution complexity, we also propose a lightweight heuristic algorithm that can achieve near-optimal performance. The conducted simulations show that our proposed approaches can execute multiple learning tasks efficiently and significantly reduce energy consumption compared to current state-of-art methods.

The recent pandemic along with the rapid increase in the number of patients that require continuous remote monitoring imposes several challenges to support the high quality of services (QoS) in remote health applications. Remote-health (r-health) systems typically demand intense data collection from different locations within a strict time constraint to support sustainable health services. On the contrary, the end-users with mobile devices have limited batteries that need to run for a long time, while continuously acquiring and transmitting health-related information. Thus, this paper proposes an adaptive deep reinforcement learning (DRL) framework for network selection over heteroge-neous r-health systems to enable continuous remote monitoring for patients with chronic diseases. The proposed framework allows for selecting the optimal network(s) that maximizes the accumulative reward of the patients while considering the patients' state. Moreover, it adopts an adaptive compression scheme at the patient level to further optimize the energy consumption, cost, and latency. Our results depict that the proposed framework outperforms the state-of-the-art techniques in terms of battery lifetime and reward maximization.

LoRa supports the exponential growth of connected devices. In this paper, we investigate green LoRa wireless networks powered by both the grid power and a renewable energy source. The grid power compensates for the randomness and intermittency of the harvested energy. We propose an efficient and smart resource management scheme of the limited number of channels and spreading factors (SFs) with the objective of improving the LoRa gateway (LG) energy efficiency. We formulate the problem of grid power consumption minimization while satisfying the quality of service demands. The optimal resource management problem is solved by decoupling the formulated problem into two sub-problems: channel and SF assignment problem and energy management problem. Next, we develop an adaptable resource management schemes based on Reinforcement Learning (RL) taking into account the channel and energy correlation. Simulations results show that the proposed resource management schemes offer efficient use of renewable energy in LoRa wireless networks.

Training centralized machine learning (ML) models becomes infeasible in wireless networks due to the increasing number of internet of things (IoT) and mobile devices and the prevalence of the learning algorithms to adapt tasks in dynamic situations with heterogeneous networks (HetNets) and battery limited devices. Hierarchical federated learning (HFL) has been proposed as a promising learning that can preserve the data privacy of the wireless devices, tackle the communication bottlenecks in wireless networks, and improve the energy effi-ciency. We propose a novel energy-efficient HFL framework for HetNets with massive multiple-input multiple-output (MIMO) wireless backhaul enabled by wireless energy transfer (WET). We formulate a joint energy management and device association optimization problem in HFL over HetNets subject to maximal divergence constraints. Next, an optimal solution is developed, but with high complexity. To reduce the complexity, a heuristic algorithm for HFL over HetNets with energy, channel quality, and accuracy constraints, is developed in order to minimize the grid energy consumption cost and preserve the value of loss function, which captures the HFL performance. Simulation results show the efficiency of the proposed resource management approach in the HFL context in terms of grid power consumption cost and training loss.

The usage of unmanned aerial vehicles (UAVs) in civil and military applications continues to increase due to the numerous advantages that they provide over conventional approaches. Despite the abundance of such advantages, it is imperative to investigate the performance of UAV utilization while considering their design limitations. This paper investigates the deployment of UAV swarms when each UAV carries a machine learning classification task. To avoid data exchange with ground-based processing nodes, a federated learning approach is adopted between a UAV leader and the swarm members to improve the local learning model while avoiding excessive air-to-ground and ground-to-air communications. Moreover, the proposed de-ployment framework considers the stringent energy constraints of UAVs and the problem of class imbalance, where we show that considering these design parameters significantly improves the performances of the UAV swarm in terms of classification accuracy, energy consumption and availability of UAVs when compared with several baseline algorithms.

The rapid increase in the number of patients requiring constant monitoring inspires researchers to investigate the area of mobile health (m-Health) systems for intelligent and sustainable remote healthcare applications. Extensive real-time medical data transmission using battery-constrained devices is challenging due to the dynamic network and the medical system constraints. Such requirements include end-to-end delay, bandwidth, transmission energy consumption, and application-level Quality of Services (QoS) requirements. As a result, adaptive data compression based on network and application resources before data transmission would be beneficial. A minimal distortion can be assured by applying Convolutional Auto-encoder (CAE) compression approach. This paper proposes a cross-layer framework that considers the patients' movement while compressing and transmitting EEG data over heterogeneous wireless environments. The main objective of the framework is to minimize the trade-off between the transmission energy consumption along with the distortion ratio and monetary costs. Simulation results show that an optimal trade-off between the optimization objectives is achieved considering networks and application QoS requirements for m-Health systems.

The rapid production of mobile and wearable devices along with the wireless applications boom is continuing to evolve everyday. This motivates network operators to integrate and exploit wireless spectrum across multiple radio access networks to cope with such intensive demand, while improving quality of service. However, it is crucial to develop innovative network selection techniques that consider heterogeneous networks characteristics, while meeting applications' quality requirements. Thus, this paper develops an optimal network selection with resource allocation scheme over heterogeneous networks that aims to optimize the latency, cost, and energy consumption, while accounting for data compression at the edge. Indeed, our framework could significantly enhance the performance of wireless healthcare systems by enabling data transfer from patients edge nodes to the cloud in cost-effective and energy-efficient manner, while maintaining strict Quality of Service (QoS) requirements of health applications. Our simulation results depict that our solution significantly outperforms state-of- the-art techniques in terms of energy consumption, latency, and cost.

Smart Contracts (SCs), which are software programs that run on blockchain platforms, provide appealing security guarantees characterized by decentralized, autonomous, and verifiable execution. On the other hand, Service Provisioning (SP) systems (i.e., systems that assign users to service providers in a way that maximizes the global utility) have been leveraging SCs to provide trust and transparency features. Such features are obtained by deploying the SP’s assignment criteria as an SC on the blockchain. However, deploying optimal assignment criteria as SCs does not guarantee the best performance over time since the blockchain participants join and leave flexibly, and their load varies with time, potentially deeming the initial assignment sub-optimal. Furthermore, modifying the criteria manually by a third party at every variation in the blockchain jeopardizes the autonomous and independent execution promised by SCs. Thus, in this paper, we propose the use of online learning SCs that leverage the chained data to continuously self-tune their assignment criteria and maintain maximum utility. We show that the proposed data-driven method can achieve high performance on the multi-stage assignment problem. We also compare the proposed approach to multiple assignment algorithms as well as planning methods. Results show a significant performance advantage over heuristics and better adaptability to the dynamic nature of blockchain networks compared to planning techniques.

Cloud computing is a paradigm that provides multiple services over the internet with high flexibility in a cost-effective way. However, the growth of cloud-based services comes with major security issues. Recently, machine learning techniques are gaining much interest in security applications as they exhibit fast processing capabilities with real-time predictions. One major challenge in the implementation of these techniques is the available training data for each new potential attack category. In this paper, we propose a new model for secure network based on machine learning algorithms. The proposed model ensures better learning of minority classes using Generative Adversarial Network (GAN) architecture. In particular, the new model optimizes the GAN parameter including the number of inner learning steps for the discriminator to balance the training datasets. Then, the optimized GAN generates highly informative “like real” instances to be appended to the original data which improve the detection of the classes with relatively small training data. Our experimental results show that the proposed approach enhances the overall classification performance and detection accuracy even for the rarely detectable classes for both UNSW and NSL-KDD datasets. The simulation results show also that the proposed model could detect better the network attacks compared to the state-of-art techniques.

Cloud computing is attracting a lot of attention in the past few years. Although, even with its wide acceptance, cloud security is still one of the most essential concerns of cloud computing. Many systems have been proposed to protect the cloud from attacks using attack signatures. Most of them may seem effective and efficient; however, there are many drawbacks such as the attack detection performance and the system maintenance. Recently, learning-based methods for security applications have been proposed for cloud anomaly detection especially with the advents of machine learning techniques. However, most researchers do not consider the attack classification which is an important parameter for proposing an appropriate countermeasure for each attack type. In this paper, we propose a new firewall model called Secure Packet Classifier (SPC) for cloud anomalies detection and classification. The proposed model is constructed based on collaborative filtering using two machine learning algorithms to gain the advantages of both learning schemes. This strategy increases the learning performance and the system's accuracy. To generate our results, a publicly available dataset is used for training and testing the performance of the proposed SPC. Our results show that the accuracy of the SPC model increases the detection accuracy by 20% compared to the existing machine learning algorithms while keeping a high attack detection rate.

Recognizing the patient's emotions using deep learning techniques has attracted significant attention recently due to technological advancements. Automatically identifying the emotions can help build smart healthcare centers that can detect depression and stress among the patients in order to start the medication early. Using advanced technology to identify emotions is one of the most exciting topics as it defines the relationships between humans and machines. Machines learned how to predict emotions by adopting various methods. In this survey, we present recent research in the field of using neural networks to recognize emotions. We focus on studying emotions' recognition from speech, facial expressions, and audio-visual input and show the different techniques of deploying these algorithms in the real world. These three emotion recognition techniques can be used as a surveillance system in healthcare centers to monitor patients. We conclude the survey with a presentation of the challenges and the related future work to provide an insight into the applications of using emotion recognition.

Unmanned Aerial Vehicles (UAVs) have recently attracted significant attention due to their outstanding ability to be used in different sectors and serve in difficult and dangerous areas. Moreover, the advancements in computer vision and artificial intelligence have increased the use of UAVs in various applications and solutions, such as forest fires detection and borders monitoring. However, using deep neural networks (DNNs) with UAVs introduces several challenges of processing deeper networks and complex models, which restricts their on-board computation. In this work, we present a strategy aiming at distributing inference requests to a swarm of resource-constrained UAVs that classifies captured images on-board and finds the minimum decision-making latency. We formulate the model as an optimization problem that minimizes the latency between acquiring images and making the final decisions. The formulated optimization solution is an NP-hard problem. Hence it is not adequate for online resource allocation. Therefore, we introduce an online heuristic solution, namely DistInference, to find the layers placement strategy that gives the best latency among the available UAVs. The proposed approach is general enough to be used for different low decision-latency applications as well as for all CNN types organized into pipeline of layers (e.g., VGG) or based on residual blocks (e.g., ResNet).

The affordability and deployment-flexibility of Unmanned Air Vehicles (UAVs) have ignited the development of many smart applications, including surveillance, disaster management, and smart farming. Drone's energy consumption is a critical issue and it can be controlled through different factors, depending on the application. One approach is to minimize energy consumption by defining a minimal number of strategic target-coverage locations that the drone needs to traverse and efficiently plan the drone's route through these locations. In this paper, we provide solutions that efficiently allow UAVs to cover multiple targets using their cameras. These solutions identify a minimum set of strategic locations that cover the targets and plan the drone's routes across these locations. We address the problem with the objective of minimizing the total energy consumed by the drone during its mission. We model the problem as mixed-integer programming problem and provide a set of heuristics; with and without target clustering. We evaluate the system using simulations. The results indicate the significance of clustering in minimizing the number of strategic locations and saving the drone's energy. Moreover, flexibility in selecting cluster centers provides further reduction in the strategic locations and energy consumption.

Medical data exchange between diverse e-health entities can lead to a better healthcare quality, improving the response time in emergency conditions, and a more accurate control of critical medical events (e.g., national health threats or epidemics). However, exchanging large amount of information between different e-health entities is challenging in terms of security, privacy, and network loads, especially for large-scale healthcare systems. Indeed, recent solutions suffer from poor scalability, computational cost, and slow response. Thus, this article proposes medical-edge-blockchain (MEdge-Chain), a holistic framework that exploits the integration of edge computing and blockchain-based technologies to process large amounts of medical data. Specifically, the proposed framework describes a healthcare system that aims to aggregate diverse health entities in a unique national healthcare system by enabling swift, secure exchange, and storage of medical data. Moreover, we design an automated patients monitoring scheme, at the edge, which enables the remote monitoring and efficient discovery of critical medical events. Then, we integrate this scheme with a blockchain architecture to optimize medical data exchanging between diverse entities. Furthermore, we develop a blockchain-based optimization model that aims to optimize the latency and computational cost of medical data exchange between different health entities, hence providing effective and secure healthcare services. Finally, we show the effectiveness of our system in adapting to different critical events, while highlighting the benefits of the proposed intelligent health system.

The rapid evolution of remote health monitoring applications is foreseen to be a crucial solution for facing an unpredictable health crisis and improving the quality of life. However, such applications come with many challenges, including: the transmission of a large amount of private medical data and the limited power budget for battery-operated devices. Thus, this article proposes an intelligent, secure, and energy-efficient (I-SEE) framework for secure and energy-efficient medical data transmission, leveraging the potential of physical-layer security. In particular, we incorporate a practical secrecy metric, namely, the secrecy outage probability (SOP), along with the adaptive compression at the edge for providing a secure solution for health monitoring applications. In the proposed framework, we first formulate an optimization problem that maximizes the energy efficiency, while maintaining quality-of-service constraints of the health application. Second, we propose a deep reinforcement learning process that obtains the optimal strategy for secure data transmission. Specifically, a multiobjective reward function is defined to optimize energy efficiency and distortion, resulting from the compression scheme. Then, a deep deterministic policy gradients (DDPGs) algorithm, named Static-DDPG is proposed to solve our problem efficiently. Third, the problem is extended to consider the battery lifetime maximization with varying channel conditions. Indeed, a Dynamic-DDPG algorithm is proposed in order to allow the edge to adapt to the environment dynamics while maximizing its battery lifetime. The conducted simulations validate the efficiency of the proposed algorithms in terms of finding the optimal policy that addresses the tradeoff between the considered conflicting objectives, along with the battery lifetime maximization

The rise in embedded and IoT device usage comes with an increase in LTE usage as well. About 70% of an estimated 18 billion IoT devices will be using cellular LTE networks for efficient connections. This introduces several challenges, such as security, latency, scalability, and quality of service, for which reason edge computing or fog computing has been introduced. The edge is capable of offloading resources to the edge to reduce workload at the cloud. Several security challenges come with multiaccess edge computing (MEC), such as location-based attacks, the man- in-the-middle attacks, and sniffing. This article proposes a software-defined perimeter (SDP) framework to supplement MEC and provide added security. The SDP is capable of protecting the cloud from the edge by only authorizing authenticated users at the edge to access services in the cloud. The SDP is implemented within a mobile-edge LTE network. Delay analysis of the implementation is performed, followed by a Denial-of-Service (DoS) attack to demonstrate the resilience of the proposed SDP. Further analyses, such as CPU usage and port scanning were performed to verify the efficiency of the proposed SDP. This analysis is followed by concluding remarks with insight into the future of the SDP in MEC.

With the emergence of smart cities, Internet of Things (IoT) devices as well as deep learning technologies have witnessed an increasing adoption. To support the requirements of such paradigm in terms of memory and computation, joint and real-time deep co-inference framework with IoT synergy was introduced. However, the distribution of Deep Neural Networks (DNN) has drawn attention to the privacy protection of sensitive data. In this context, various threats have been presented, including black-box attacks, where a malicious participant can accurately recover an arbitrary input fed into his device. In this paper, we introduce a methodology aiming to secure the sensitive data through re-thinking the distribution strategy, without adding any computation overhead. First, we examine the characteristics of the model structure that make it susceptible to privacy threats. We found that the more we divide the model feature maps into a high number of devices, the better we hide proprieties of the original image. We formulate such a methodology, namely DistPrivacy, as an optimization problem, where we establish a trade-off between the latency of co-inference, the privacy level of the data, and the limited-resources of IoT participants. Due to the NP-hardness of the problem, we introduce an online heuristic that supports heterogeneous IoT devices as well as multiple DNNs and datasets, making the pervasive system a general-purpose platform for privacy-aware and low decision-latency applications.

Smart health systems improve the existing health services by integrating information and technology into health and medical practices. However, smart healthcare systems are facing major challenges including limited network resources, energy allocation, and latency. In this paper, we leverage the dense heterogeneous network (HetNet) architecture over 5G network to enhance network capacity and provide seamless connectivity for smart health systems. The network selection and energy allocation in HetNets are important factors in this regard due to their significant impact on system performance. Inspired by the success of Deep Reinforcement Learning (DRL) in solving complicated control problems, we present a novel DRL model for energy-efficient network selection in heterogeneous health systems. The proposed model selects the set of networks to be used for data transmission with adaptive compression at the edge with an optimal energy allocation policy for all the network participants. Our experimental results show that the proposed DRL model has a good performance compared to the existing state of art techniques while meeting different users' demands in highly dynamic environments.

The number of users adopting Tor to protect their online privacy is increasing rapidly. With a limited number of volunteered relays in the network, the number of clients' connections sharing the same relays is increasing to the extent that it is starting to affect the performance. Recently, Tor's resource allocation among circuits has been studied as one cause of poor Tor network performance. In this paper, we propose two scheduling approaches that guarantee proportional fairness between circuits that are sharing the same connection. In our evaluation, we show that the average-rate-base scheduler allocates Tor's resources in an optimal fair scheme, increasing the total throughput achieved by Tor's relays. However, our second proposed approach, an optimization-based scheduler, maintains acceptable fairness while reducing the latency experienced by Tor's clients.

Smart health systems have become the need of the hour taking into account the rising number of patients and the limited facilities available to treat them. This paper has profited by the advantages of two major fields of research in the recent times; deep learning and edge computing. A deep learning method for epileptic seizure detection using mobile edge computing is proposed. EEG signals are used for seizure detection. A novel deep Convolutional Neural Network (CNN) with six convolutional layer, two fully connected layer with softmax activation is used to classify the EEG signal into either seizure or non-seizure category. A three tier architecture with an edge layer between the end device and the cloud is used. Out of all the advantages the edge layer can enhance privacy, this paper is mainly focused on using the edge to reduce the size of the data being sent to the cloud. A dataset with 500 samples from healthy and seizure activities is used. The raw data is represented in both time and frequency domain. The best model proposed can achieve an accuracy of 92 % in time domain, 99.22 % in frequency domain.

Leveraging video caching to collaborative Mobile Edge Computing (MEC) servers is an emerging paradigm, where cloud computing services are extended to edge networks to allocate multimedia contents close to end-users. However, despite minimizing the traffic over the content delivery networks (CDN), congestions may occur in peak hours characterized by high load demands. Involving users' devices in data offloading through Device-to-Device (D2D) connections has proved its efficiency in relieving the cellular spectrum utilization. In this paper, the Collaborative Edge network (CE) and the devices (D2D) cluster are combined to form a CE-D2D framework aiming at maximizing video caching and efficiently using cellular and backhaul bandwidths. However, since we are dealing with large sized contents, the small storage and bandwidth capacities offered by users limit the number of cached videos and restrict offloading large volume data. This makes the CE-D2D framework, so far, an incomplete solution for multimedia contents. Therefore, we propose a caching strategy to cache only the chunks of videos to be watched and instead of caching or offloading each video content by one edge node (as performed in literature), helpers (MEC and mobiles) will collaborate to store and share different chunks to optimize the storage/transmission resources usage. In this work, we model both CE and D2D frameworks as linear programs and schedule the collaboration between them constrained by resource availability. Due to the NP-hardness of the problem, we introduce an online heuristic that presents a proactive chunks caching (HLPC) and a near-optimal data offloading with polynomial complexity.

In this paper, we conduct a biological data collection and analysis study for patients undergoing routine planned intravenous antibiotic treatment. The acquired data (i.e., Electroencephalogram (EEG), temperature and blood pressure) are processed using different machine learning and deep learning models to learn the dynamic properties of brain electrical activity from this group of patients. Thus, the primary objective of our study is the safe collection of EEG data from patients receiving antibiotic therapy, in addition to analyzing the acquired data for patterns that might indicate risk of seizure. We propose two machine learning models to analyze the acquired data from these patients split into three classes: data collected before, during, and after receiving the medication. Our results show the effectiveness of our models in analyzing the acquired data, which would not possible by imitative human analysis.

Network security is an critical subject in any distributed network. Recently, machine learning has proven their efficiency for intrusion detection. By using a comprehensive dataset with multiple attack types, a well-trained model can be created to improve the anomaly detection performance. However, high dimensional data sets are a significant challenge for machine learning. In fact, learning algorithms considering all features in the input data, may cause over-fitting to irrelevant aspects of the data and increase the computational time caused by the process of similar features that provide redundant information, which is a critical problem especially for users with constrained resources. In this paper, we propose a new and efficient feature selection technique for intrusion detection in modern networks called Iterative Per Group Feature Selection (IPGFS). IPGFS reduces the number of features in the input data and selects the best features using the performance accuracy of the classifier. The features are sorted and selected according to their accuracy score. Both the UNSW and NSLKDD datasets are used in this paper to validate the proposed model and verify its efficiency in detecting intrusions. The simulation results show that the proposed model can reduce the number of features for the two dataset while successfully detecting intrusions with better accuracy compared to state-of-the-art techniques. Index Cloud security, feature selection, accuracy, machine learning techniques.

Smart health systems improve the efficiency of healthcare infrastructures and biomedical systems by integrating information and technology into health and medical practices. However, reliability, scalabilty and latency are among the many challenges hindering the realization of next-generation healthcare. In fact, with the exponential increases in the volume of patient data being produced and processed, many healthcare system' are being overwhelmed with the deluge of data they are facing. Many systems have been proposed to improve the system latency and scalability. However, there are concerns related to some of theses systems regarding the increasing levels of required human interaction which impact their efficiency. Recently, machine learning techniques are gaining a lot of interest in health applications as they exhibit fast processing with realtime predictions. In this paper, we propose a new healthcare system to reduce the waiting time in emergency department and improve the network scalability in any distributed system. The proposed model integrates the power of edge computing with machine learning techniques for providing a good quality of healthcare services. The machine learning algorithm is used to generate a classifier that can predict with high levels of accuracy the likelyhood of a patient to have a heart attack using his physiological signals ECG. The proposed system stores the patient data in a centralized database and generates a unique index using a new data-dependent Indexing algorithm that transforms the patient data into unique code to be sent for any medical data exchange. Multiple machine learning algorithms are studied and the best algorithm will be selected based on efficient performance result for the prediction of heart attack problem. simulation results show that the proposed model can effectively detect the abnormal heart beats with 91% using SVM algorithm. We show also that the proposed system outperforms conventional indexing algorithm systems in terms of collisions rate.

The blockchain is a storage technology and transmission of information, transparent, secure, and operating without central control. In this paper, we propose a new decentralized trust management and cooperation model where data is shared via blockchain and we explore the revenue distribution under different consensus schemes. To reduce the power calculation with respect to the control mechanism, our proposal adopts the possibility of Proof on Trust (PoT) and Proof of proof-of-stake based trust to replace the proof of work (PoW) scheme, to carry out the mining and storage of new data blocks. To detect nodes with malicious behavior to provide false system information, the trust updating algorithm is proposed..

Recently, machine learning techniques are gaining a lot of interest in security applications as they exhibit fast processing with real-time predictions. One of the significant challenges in the implementation of these techniques is the collection of a large amount of training data for each new potential attack category, which is most of the time, unfeasible. However, learning from datasets that contain a small training data of the minority class usually produces a biased classifiers that have a higher predictive accuracy for majority class(es), but poorer predictive accuracy over the minority class. In this paper, we propose a new designed attacks weighting model to alleviate the problem of imbalanced data and enhance the accuracy of minority classes detection. In the proposed system, we combine a supervised machine learning algorithm with the node1past information. The machine learning algorithm is used to generate a classifier that differentiates between the investigated attacks. Then, the system stores these decisions in a database and exploits them for the weighted attacks classification model. Thus, for each attack class, the weight that maximizes the detection of the minority classes will be computed and the final combined decision is generated. In this work, we use the UNSW dataset to train the supervised machine learning model. The simulation results show that the proposed model can effectively detect intrusion attacks and provide better accuracy, detection rates and lower false alarm rates compared to state-of-the art techniques.1In this document we will use the words “node” to represent computing, storage, physical, and virtual machines.

With the advancement of rich media generating devices, the proliferation of live Content Providers (CP), and the availability of convenient internet access, crowdsourced live streaming services have witnessed unexpected growth. To ensure a better Quality of Experience (QoE), higher availability, and lower costs, large live streaming CPs are migrating their services to geo-distributed cloud infrastructure. However, because of the dynamics of live broadcasting and the wide geo-distribution of viewers and broadcasters, it is still challenging to satisfy all requests with reasonable resources. To overcome this challenge, we introduce in this paper a prediction driven approach that estimates the potential number of viewers near different cloud sites at the instant of broadcasting. This online and instant prediction of distributed popularity distinguishes our work from previous efforts that provision constant resources or alter their allocation as the popularity of the content changes. Based on the derived predictions, we formulate an Integer-Linear Program (ILP) to proactively and dynamically choose the right data center to allocate exact resources and serve potential viewers, while minimizing the perceived delays. As the optimization is not adequate for online serving, we propose a real-time approach based on Reinforcement Learning (RL), namely RL-OPRA, which adaptively learns to optimize the allocation and serving decisions by interacting with the network environment. Extensive simulation and comparison with the ILP have shown that our RL-based approach is able to present optimal results compared to heuristic-based approaches.

To support multimedia applications, Mobile Edge Computing (MEC) servers offer storage and computing capacities to handle videos close to end-users. However, the high load in peak hours consumes the limited available bandwidth of existing cellular and backhaul links leading to low network performance. Hence, an elastic system model is required to maintain the high Quality of Experience (QoE) as the resource demands increase. Caching popular videos at mobile devices is considered a promising technique for content delivery. Yet, mobile users offer small capacities that are not adequate for large-sized video sharing. In this paper, we extend the collaborative caching and processing framework in edge networks (Collaborative Edge - CE) to include the users' mobile video sharing (Device-to-Device - D2D). We propose a caching strategy to cache only the chunks of videos to be watched and instead of offloading one video content by one edge node, helpers (MEC servers and users) will collaborate to store and share different chunks to optimize the storage/transmission resources usage. To only cache popular contents, we designed a D2D-aware proactive chunks caching on users’ devices based on our chunks popularity model. Next, we formulate this CE-D2D collaborative problem as a linear program. Due to the NP-hardness of the problem, we introduce a sub-optimal relaxation and an online heuristic using the proactive caching and presenting a near optimal data offloading and a profitable payment determination, with polynomial time complexity. The simulation results show that our policies and heuristics outperform other edge caching approaches by more than 10% in terms of hit ratio, average delay, and cost.

During the last decade, empowered by the technological advances of mobile devices and the revolution of wireless mobile network access, crowdsourced live streaming has become more popular. Ensuring a stable high-quality playback experience is necessary to maximize the number of viewers and profits for content providers. Additionally, because of the instability of network conditions and the heterogeneity of the end-users capabilities, transcoding the original video into multiple bitrates is required. Video transcoding is a computationally exhaustive process, where generally a single cloud instance needs to be reserved to produce one single video bitrate representation. On-demand renting of resources or inadequate resources pre-renting may cause delay of the video playback or serving the viewers with a lower quality. On the other hand, if resources provisioning is much higher than required, the extra resources will be wasted. In this paper, we introduce our resources reservation framework for geo-distributed cloud sites, to maximize the Quality of Experience (QoE) of viewers and minimize the cost to the content providers. First, we formulate an offline optimization problem to allocate transcoding resources at the viewers' proximity, while creating a trade off between the network cost and viewers QoE. Second, based on the optimizer resource allocation decisions on historical live videos, we create our time series datasets containing historical records of the optimal resources needed at each geo-distributed cloud site. Finally, we adopt machine learning to build our distributed time series forecasting models to proactively forecast the exact needed transcoding resources ahead of time at each geo-distributed cloud site.

Driven by the tremendous technological advancement of personal devices and the prevalence of wireless mobile network accesses, the world has witnessed an explosion in crowdsourced live streaming. Ensuring a better viewers quality of experience (QoE) is the key to maximize the audiences number and increase streaming providers' profits. This can be achieved by advocating a geo-distributed cloud infrastructure to allocate the multimedia resources as close as possible to viewers, in order to minimize the access delay and video stalls. Moreover, allocating the exact needed resources beforehand avoids over-provisioning, which may lead to significant costs by the service providers. In the contrary, under-provisioning might cause significant delays to the viewers. In this paper, we introduce a prediction driven resource allocation framework, to maximize the QoE of viewers and minimize the resource allocation cost. First, by exploiting the viewers locations available in our unique dataset, we implement a machine learning model to predict the viewers number near each geo-distributed cloud site. Second, based on the predicted results that showed to be close to the actual values, we formulate an optimization problem to proactively allocate resources at the viewers proximity. Additionally, we will present a trade-off between the video access delay and the cost of resource allocation.

Cloud computing is gaining significant traction and virtualized data centers are becoming popular as a cost-effective infrastructure in telecommunication industry. Infrastructure as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (SaaS) are being widely deployed and utilized by end users, including many private as well as public organizations. Despite its wide-spread acceptance, security is still the biggest threat in cloud computing environments. Users of cloud services are under constant fear of data loss, security breaches, information theft and availability issues. Recently, learning-based methods for security applications are gaining popularity in the literature with the advents in machine learning (ML) techniques. In this work, we explore applicability of two well-known machine learning approaches, which are, Artificial Neural Networks (ANN) and Support Vector Machines (SVM), to detect intrusions or anomalous behavior in the cloud environment. We have developed ML models using ANN and SVM techniques and have compared their performances. We have used UNSW-NB-15 dataset to train and test the models. In addition, we have performed feature engineering and parameter tuning to find out optimal set of features with maximum accuracy to reduce the training time and complexity of the ML models. We observe that with proper features set, SVM and ANN techniques have been able to achieve anomaly detection accuracy of 91% and 92% respectively, which is higher compared against that of the one achieved in the literature, with reduced number of features needed to train the models.

In the past few years, a rapid increase in the number of patients requiring constant monitoring, which inspires researchers to develop intelligent and sustainable remote smart healthcare services. However, the transmission of big real-time health data is a challenge since the current dynamic networks are limited by different aspects such as the bandwidth, end-to-end delay, and transmission energy. Due to this, a data reduction technique should be applied to the data before being transmitted based on the resources of the network. In this paper, we integrate efficient data reduction with wireless networking transmission to enable an adaptive compression with an acceptable distortion, while reacting to the wireless network dynamics such as channel fading and user mobility. Convolutional Auto-encoder (CAE) approach was used to implement an adaptive compression/reconstruction technique with the minimum distortion. Then, a resource allocation framework was implemented to minimize the transmission energy along with the distortion of the reconstructed signal while considering different network and applications constraints. A comparison between the results of the resource allocation framework considering both CAE and Discrete wavelet transforms (DWT) was also captured.

The advancement of technology has pushed the cloud computing capabilities to the edge networks, paving the way for network operators and multimedia service providers to leverage video caching and transcoding to the Mobile Edge computing (MEC) servers. However, because of high load demands in peak hours and the limited bandwidth, congestions may occur, leading to lower network performance. This problem is worsened by the redundancies of the same content requests and the expectation for the highest video quality, which exhausts the cellular spectrum and the backhaul links. Collaboration between edge servers, to cache and transcode videos, is proposed and proved its efficiency to store highly requested contents and relieve the load on the backhaul links. Meanwhile, Device-to-device (D2D) offloading is considered to alleviate cellular spectrum utilization. In this paper, we will extend the Collaborative Edge (CE) network to include the mobile users (D2D) caching and offloading and create a CE-D2D dual framework. Still, this framework does not present the perfect solution for exhaustive bandwidth utilization. In fact, users' mobiles have small storage capacities and very scarce bandwidth availability, which limits the number of cached videos and constraints sharing large sized contents. Additionally, existing D2D approaches are considering video requests as simple contents similar to any HTML page request. However, in realistic cases, a lower bitrate version of the content can be offered to the viewers, if the bandwidth (cellular or mobile) is unavailable. Hence, to maximize the caching efficiency, we formulate the CE-D2D framework as a linear program, where MEC servers and users' mobiles collaborate to cache and offload different chunks of the requested content constrained by cache and bandwidth availability. In this way, instead of caching and serving full popular videos, as done in previous works, we will only cache popular chunks within different helpers, which maximizes the efficiency of caching in small storage devices.

Data Center Networks (DCNs) are attracting immense interest from the industry, research and academia to keep pace with the increase of Internet services demands. One of the major concerns that draws the attention of researchers is the exponential growth of the energy consumption and carbon emission of the DCNs. Studies conducted to identify the causes of the increasing energy consumption have proved that the growing size of computing demand, the over-provisioning of the networking resources, the under-utilization of the infrastructure, the fault-tolerance, the high bandwidth exigence and the inefficient hardware and cooling structure are leading to considerable energy waste. Therefore, in recent years, new data center (DC) architectures are proposed where new hardware types and new technologies are implemented for the sake of energy efficiency. Other efforts are focusing on designing algorithms and strategies to enhance the utilization of the network resources. Replacing brown power by renewable energy was also one of the attractive ideas to minimize the energy costs. In this survey paper, we will present energy-related problems in data centers and review the state of the art of the research literature on energy efficient architectures, techniques, technologies, resource management, and thermal control and monitoring. Additionally, we present the challenges facing each approach and the strategies to build a green DC. This paper serves as a specification document that shows step by step how to minimize the energy consumption of different components of the system.

Tor's anonymity network is one of the most widely used anonymity networks online, it consists of thousands of routers run by volunteers. Tor preserves the anonymity of its users by relaying the traffic through a number of routers (called onion routers) forming a circuit. The current design of Tor's transport layer suffers from a number of problems affecting the performance of the network. Several researches proposed changes in the transport design in order to eliminate the effect of these problems and improve the performance of Tor's network. In this paper. we propose "QuicTor", an improvement to the transport layer of Tor's network by using Google's protocol "QUIC" instead of TCP. QUIC was mainly developed to eliminate TCP's latency introduced from the handshaking delays and the head-of-line blocking problem. We provide an empirical evaluation of our proposed design and compare it to two other proposed designs, IMUX and PCTCP. We show that QuicTor significantly enhances the performance of Tor's network.

Algorithm complexity in machine learning problems has been a real concern especially with large-scaled systems. By increasing data dimensionality, a particular emphasis is placed on designing computationally efficient learning models. In this paper, we propose an approach to improve the complexity of a multi-classification learning problem in cloud networks. Based on the Random Forest algorithm and the highly dimensional UNSW-NB 15 dataset, a tuning of the algorithm is first performed to reduce the number of grown trees used during classification. Then, we apply an importance-based feature selection to optimize the number of predictors involved in the learning process. All of these optimizations, implemented with respect to the best performance recorded by our classifier, yield substantial improvement in terms of computational complexity both during training and prediction phases.

Internet of Things (IoTs) are Internet-connected devices that integrate physical objects and internet in diverse areas of life like industries, home automation, hospitals and environment monitoring. Although IoTs ease daily activities benefiting human operations, they bring serious security challenges worth concerning. IoTs have become potentially vulnerable targets for cybercriminals, so companies are investing billions of dollars to find an appropriate mechanism to detect these kinds of malicious activities in IoT networks. Nowadays intelligent techniques using Machine Learning (ML) and Artificial Intelligence (AI) are being adopted to prevent or detect novel attacks with best accuracy. This survey classifies and categorizes the recent Intrusion Detection approaches for IoT networks, with more focus on hybrid and intelligent techniques. Moreover, it provides a comprehensive review on IoT layers, communication protocols and their security issues which confirm that IDS is required in both layered and protocol approaches. Finally, this survey discusses the limitations and advantages of each approach to identify future directions of potential IDS implementation.

Rapid evolution of wireless medical devices and network technologies has fostered the growth of remote monitoring systems. Such new technologies enable monitoring patients' medical records anytime and anywhere without limiting patients' activities. However, critical challenges have emerged with remote monitoring systems due to the enormous amount of generated data that need to be efficiently processed and wirelessly transmitted to the service providers in time. Thus, in this paper, we leverage full-duplex capabilities for fast transmission, while tackling the trade-off between Quality of Service (QoS) requirements and consequent self-interference (SI) for efficient remote monitoring healthcare systems. The proposed framework jointly considers the residual SI resulting from simultaneous transmission and reception along with the compressibility feature of medical data in order to optimize the data transmission over wireless channels, while maintaining the application's QoS constraint. Our simulation results demonstrate the efficiency of the proposed solution in terms of minimizing the transmission power, residual self-interference, and encoding distortion.

Recently, the growing demand for rich multimedia content such as Video on Demand (VoD) has made the data transmission from content delivery networks (CDN) to end-users quite challenging. Edge networks have been proposed as an extension to CDN networks to alleviate this excessive data transfer through caching and to delegate the computation tasks to edge servers. To maximize the caching efficiency in the edge networks, different Mobile Edge Computing (MEC) servers assist each others to efficiently select which content to store and the appropriate computation tasks to process. In this paper, we adopt a collaborative caching and transcoding model for VoD in MEC networks. However, unlike other models in the literature, different chunks of the same video are not fetched and cached in the same MEC server. Instead, neighboring servers will collaborate to store and transcode different video chunks and consequently optimize the limited resources usage. Since we are dealing with chunks caching and processing, we propose to maximize the edge efficiency by studying the viewers watching pattern and designing a probabilistic model where chunks popularities are evaluated. Based on this model, popularity-aware policies, namely Proactive caching policy (PcP) and Cache replacement Policy (CrP), are introduced to cache only highest probably requested chunks. In addition to PcP and CrP, an online algorithm (PCCP) is proposed to schedule the collaborative caching and processing. The evaluation results prove that our model and policies give better performance than approaches using conventional replacement policies. This improvement reaches up to 50% in some cases.

Cloud computing has been presented as one of the most efficient techniques for hosting and delivering services over the internet. However, even with its wide areas of application, cloud security is still a major concern of cloud computing. In order to protect the communication in such environment, many secure systems have been proposed and most of them are based on attack signatures. These systems are often not very efficient for detecting all the types of attacks. Recently, machine learning technique has been proposed. This means that if the training set does not include enough examples in a particular class, the decision may not be accurate. In this paper, we propose a new firewall scheme named Enhanced Intrusion Detection and Classification (EIDC) system for secure cloud computing environment. EIDC detects and classifies the received traffic packets using a new combination technique called most frequent decision where the nodes'11In this document we will use the words “node” and “user” interchangeably.past decisions are combined with the current decision of the machine learning algorithm to estimate the final attack category classification. This strategy increases the learning performance and the system accuracy. To generate our results, a public available dataset UNSW-NB-15 is used. Our results show that EICD improves the anomalies detection by 24% compared to complex tree.

Carriers’ network services are distributed, dynamic, and investment intensive. Deploying them as virtual network services (VNS) brings the promise of low-cost agile deployments, which reduce time to market new services. If these virtual services are hosted dynamically over multiple clouds, greater flexibility in optimizing performance and cost can be achieved. On the flip side, when orchestrated over multiple clouds, the stringent performance norms for carrier services become difficult to meet, necessitating novel and innovative placement strategies. In selecting the appropriate combination of clouds for placement, it is important to look ahead and visualize the environment that will exist at the time a virtual network service is actually activated. This serves multiple purposes — clouds can be selected to optimize the cost, the chosen performance parameters can be kept within the defined limits, and the speed of placement can be increased. In this paper, we propose the P-ART (Predictive-Adaptive Real Time) framework that relies on predictive-deductive features to achieve these objectives. With so much riding on predictions, we include in our framework a novel concept-drift compensation technique to make the predictions closer to reality by taking care of long-term traffic variations. At the same time, near real-time update of the prediction models takes care of sudden short-term variations. These predictions are then used by a new randomized placement heuristic that carries out a fast cloud selection using a least-cost latency-constrained policy. An empirical analysis carried out using datasets from a queuing-theoretic model and also through implementation on CloudLab, proves the effectiveness of the P-ART framework. The placement system works fast, placing thousands of functions in a sub-minute time frame with a high acceptance ratio, making it suitable for dynamic placement. We expect the framework to be an important step in making the deployment of carrier-grade VNS on multi-cloud systems, using network function virtualization (NFV), a reality.

The omnipresence of unmanned aerial vehicles, or drones, among civilians can lead to technical, security, and public safety issues that need to be addressed, regulated and prevented. Security agencies are in continuous search for technologies and intelligent systems that are capable of detecting drones. Unfortunately, breakthroughs in relevant technologies are hindered by the lack of open source databases for drone’s Radio Frequency (RF) signals, which are remotely sensed and stored to enable developing the most effective way for detecting and identifying these drones. This paper presents a stepping stone initiative towards the goal of building a database for the RF signals of various drones under different flight modes. We systematically collect, analyze, and record raw RF signals of different drones under different flight modes such as: off, on and connected, hovering, flying, and video recording. In addition, we design intelligent algorithms to detect and identify intruding drones using the developed RF database. Three deep neural networks (DNN) are used to detect the presence of a drone, the presence of a drone and its type, and lastly, the presence of a drone, its type, and flight mode. Performance of each DNN is validated through a 10-fold cross-validation process and evaluated using various metrics. Classification results show a general decline in performance when increasing the number of classes. Averaged accuracy has decreased from 99.7% for the first DNN (2-classes), to 84.5% for the second DNN (4-classes), and lastly, to 46.8% for the third DNN (10-classes). Nevertheless, results of the designed methods confirm the feasibility of the developed drone RF database to be used for detection and identification. The developed drone RF database along with our implementations are made publicly available for students and researchers alike.

In the last few years, the number of patients with chronic diseases requiring constant monitoring increased rapidly, which motivates researchers to develop scalable remote health applications. Nevertheless, the amount of transmitted real-time data through current dynamic networks with limited and restricted bandwidth, end-to-end delay, and transmission power; limits having an efficient transmission of the data. Motivated by the high energy consumed for transmission, applying data reduction techniques to the vital signs at the transmitter side present an efficient edge-based approach that significantly reduces the transmission energy. However, a new problem arises, which is the ability of receiving the data at the server side with an acceptable distortion rate (i.e., deformation of vital signs because of inefficient data reduction). In this paper, we introduce a Deep Learning (DL) approach based on Convolutional Auto-Encoder (CAE), to compress and reconstruct the vital signs in general and Electroencephalogram Signal (EEG) specifically with minimum distortion. The results show that using CAE provides efficient distortion rate while maximizing compression ratio. However, learning makes CAE application-specific, where each CAE model is designed specifically for a certain application.

Cloud computing has been widely adopted by application service providers (ASPs) and enterprises to reduce both capital expenditures (CAPEX) and operational expenditures (OPEX). Applications and services previously running on private data centers are now being migrated to private or public clouds. Since most of the ASPs and enterprises have globally distributed user bases, their services need to be distributed across multiple clouds, spread across the globe which can achieve better performance in terms of latency, scalability and load balancing. The shift has eventually led the research community to study multi-cloud environments. However, the widespread acceptance of such environments has been hampered by major security concerns. Firewalls and traditional rule-based security protection techniques are not sufficient to protect user-data in multi-cloud scenarios. Recently, advances in machine learning techniques have attracted the attention of the research community to build intrusion detection systems (IDS) that can detect anomalies in the network traffic. Most of the research works, however, do not differentiate among different types of attacks. This is, in fact, necessary for appropriate countermeasures and defense against attacks. In this paper, we investigate both detecting and categorizing anomalies rather than just detecting, which is a common trend in the contemporary research works. We have used a popular publicly available dataset to build and test learning models for both detection and categorization of different attacks. To be precise, we have used two supervised machine learning techniques, namely linear regression (LR) and random forest (RF). We show that even if detection is perfect, categorization can be less accurate due to similarities between attacks. Our results demonstrate more than 99% detection accuracy and categorization accuracy of 93.6%, with the inability to categorize some attacks. Further, we argue that such categorization can be applied to multi-cloud environments using the same machine learning techniques.

Video streaming is one of the most popular and highest bandwidth consumers within the Internet today. Cloud's elastic and pay-per-use model offers viable solution to varying demands of heterogeneous viewers for large-scale video providers. Video providers are heavily exploiting cloud's elastic nature to cater the scalability and heterogeneity of video steaming related tasks. For instance, Netflix moved its whole infrastructure to Amazon cloud, and Twitch, one of the largest game streaming providers is owned by Amazon and now using Amazon's cloud. Video representations refer to multiple copies of same video transcoded in multiple bitrates, such as 240, 360, 720, 1080 etc. Viewers with varying bandwidth capacities are served with matching representations based on the available bandwidth to minimize buffering time and latency. However, video transcoding is a computation and communication intensive task, therefore, not all of the live videos are transcoded to different representations. For instance, Twitch transcodes only the video streams of premium member (which have 500+ regular viewers). All of the non-premium channels are broadcasted in source stream. A fundamental question therefore is: which channels should be considered to be transcoded to multiple representations to minimize the overall cloud leased resources cost and bandwidth, and to maximize user satisfaction. In this paper, we seek answer to this question by analyzing the impact of multiple representations on cost (based on leasing cloud resources), bandwidth, and Quality of Experience (QoE, measured in terms of user satisfaction). We use Twitch workload traces captured in 2015, to conduct the experimentation, and use latest real-world broadband and representation data rate statistics from Akamai and YouTube Live, and cost from Amazon EC2 and CloudFront to validate our results. Our analysis reveals that using cloud's resources to transcode channels with more than 40 average viewers per hour with a data rate of 720p or higher, leads to low cost and bandwidth consumption, and higher QoE, as compared to streaming source video without multiple representations.

Lately application service providers (ASPs) and Internet service providers (ISPs) are being confronted with the unprecedented challenge of accommodating increasing service and traffic demands from their geographically distributed users. Many ASPs and ISPs, such as Facebook, Netflix, AT&T and others have adopted micro-service architecture to tackle this problem. Instead of building a single, monolithic application, the idea is to split the application into a set of smaller, interconnected services, called micro-services (or simply services). Such services are lightweight and perform distinct tasks independent of each other. Hence, they can be deployed quickly and independently as user demands vary. Nevertheless, scheduling of micro-services is a complex task and is currently under-researched. In this work, we address the problem of scheduling micro-services across multiple clouds, including micro-clouds. We consider different user-level SLAs, such as latency and cost, while scheduling such services. Our aim is to reduce overall turnaround time for the complete end-to-end service in service function chains and reduce the total traffic generated. In this work we present a novel fair weighted affinity-based scheduling heuristic to solve this problem. We also compare the results of proposed solution with standard biased greedy scheduling algorithms presented in the literature and observe significant improvements.

Deployment of Network Function Virtualization (NFV) over multiple clouds accentuates its advantages like flexibility of virtualization, proximity to customers and lower total cost of operation. However, NFV over multiple clouds has not yet attained the level of performance to be a viable replacement for traditional networks. One of the reasons is the absence of a standard based Fault, Configuration, Accounting, Performance and Security (FCAPS) framework for the virtual network services. In NFV, faults and performance issues can have complex geneses within virtual resources as well as virtual networks and cannot be effectively handled by traditional rule-based systems. To tackle the above problem, we propose a fault detection and localization model based on a combination of shallow and deep learning structures. Relatively simpler detection has been effectively shown to be handled by shallow machine learning structures like Support Vector Machine (SVM). Deeper structure, i.e., the stacked autoencoder has been found to be useful for a more complex localization function where a large amount of information needs to be worked through to get to the root cause of the problem. We provide evaluation results using a dataset adapted from fault datasets available on Kaggle and another based on multivariate kernel density estimation and Markov sampling.

Network Function Virtualization (NFV) and Service Chaining (SC) are novel service deployment approaches in the contemporary cloud environments for increased flexibility and cost efficiency to the Application Service Providers and Network Providers. However, NFV and SC are still new and evolving topics. Optimized placement of these virtual functions is necessary for acceptable latency to the end-users. In this work we consider the problem of optimal Virtual Function (VF) placement in a multi-cloud environment to satisfy the client demands so that the total response time is minimized. In addition we consider the problem of dynamic service deployment for OpenADN, a novel multi-cloud application delivery platform.

Browsers have become mature execution platforms enabling web applications to rival their desktop counterparts. An important class of such applications is interactive multimedia: games, animations, and interactive visualizations. Unlike many early web applications, these applications are latency sensitive and processing (CPU and graphics) intensive. When demands exceed available resources, application quality (e.g., frame rate) diminishes because it is hard to balance timeliness and utilization. The quality of ambitious web applications is also limited by single-threaded execution prevalent in the Web. Applications need to scale their quality, and thereby scale processing load, based on the resources that are available. We refer to this as scalable quality.

Increasingly, multimedia applications need higher bandwidth to provide better quality, for example in multi-party HD video conferencing. This demanding class of interactive applications simultaneously require high bandwidth and low end-to-end latency, a conflicting combination that is poorly supported in existing transports. Conventional wisdom dictates that network applications have a choice of transport protocols between TCP, if a reliable service model is desired, or UDP, if control over timing is required. In this paper we present Paceline, an enhanced transport we have devised to support interactive, high-bandwidth applications. Paceline enhances the transport service model to support application adaptation, through prioritization to provide timely delivery of important data, and cancellation to adapt the application rate to match available bandwidth. However, contrary to conventional wisdom, Paceline has not been implemented over UDP, nor does Paceline propose changes to TCP. We believe that the deployment obstacles and duplication of effort faced by solutions that alter or replace TCP entirely outweigh the challenges of mitigating its impairments. Instead, Paceline employs several mechanisms to support timely priority order delivery and cancellation above TCP: an application-level rate controller to reduce queueing delay due to excessive socket buffering, failover among connections to handle extreme cases of congestion, and message fragmentation to reduce the granularity of preemption. Our evaluation shows that Paceline improves upon conventional end-to-end latency shortcomings of using TCP, by factor of 3 in median latency and a factor of 4 in worst case latency. Meanwhile, Paceline is able to preserve TCP's performance in terms of fairness and utilization. Finally, we compare application performance with Paceline to a representative TCP alternative, Structured Stream Transport (SST), showing Paceline to be highly competitive.

Large screen displays are being increasingly deployed in public areas for advertising, entertainment, and information display. Recently we have witnessed increasing interest in supporting interaction with such displays using personal mobile devices. To enable the rapid development of public large screen interactive applications, we have designed and developed the MAGIC Broker. The MAGIC Broker provides a set of common abstractions and a RESTful Web services protocol to easily program interactive public large screen display applications with a focus on mobile device interactions. We have carried out a preliminary evaluation of the MAGIC Broker via the development of a number of prototypes and believe our toolkit is a valid first step in developing a generic support infrastructure to empower developers of interactive large screen display applications.