The current landscape of data-centric Internet of Vehicles (IoVs) encompasses a fusion of Human-driven Vehicles, Autonomous Vehicles, Road-Side Units, and edge-based devices engaged in periodic communication. Given the stringent latency requirements inherent in vehicular communications, the emergence of edge-based vehicular Digital Twins (DTs) plays a pivotal role in problem-solving, ensuring rapid response, regulatory compliance, and seamless availability. While these communications serve as the backbone of IoV, they also create an opportune environment for cybercriminals to exploit. Vulnerabilities at the network layer facilitate intrusions, resulting in a surge of data falsification attacks in recent years. Addressing this challenge demands resilient and intelligent threat detection schemes capable of adapting to the dynamic nature of IoV. This study conducts a comprehensive examination of the vulnerabilities in Vehicle-to-DT (V2DT) data communication through the lens of an attacker utilizing False Data Injection Attack (FDIA). It utilizes cutting-edge Blockchain-based decentralized storage and buffering mechanisms for vehicle dynamics data en route to edge-based DTs. Further, deep learning-powered sensor data analysis serves as an additional layer of security. Evaluation of the proposed threat detection and mitigation model demonstrates 100% tamper detection in V2DT communication, coupled with a 96% accurate classification of anomalous driving behaviors, including aggressive driving or FDIAs.

As the proportion of renewable energy in the distribution grid continues to rise, the timely transmission of critical state information becomes essential to ensure the balance of energy flow. Existing metrics for information timeliness based on peak age of information (PAoI) and its variants fall short in fully characterizing the intricate influence of information flow on the dynamics of energy distribution. In this paper, a new information timeliness metric named energy dispatch cost-aware PAoI (EPAoI) is introduced from the perspective of integrating information and energy flows. We propose an information-energy flow integrated wireless resource scheduling algorithm based on fuzzy learning to minimize EPAoI. It exceptionally improves learning accuracy by exploiting key features of dual flows to guide resource scheduling optimization. Simulation results validate superior performances of the proposed algorithm in reducing EPAoI and energy dispatch cost.

In intelligent transportation systems (ITSs), computer vision and digital twin (DT) technologies are crucial for enhancing safety and efficiency. High-speed vehicles require timely alert systems to prevent collisions with other vehicles and infrastructure, as even a single misjudgment can lead to severe road accident. Advanced driver-assistance systems (ADASs) and vehicular ad-hoc networks (VANETs) enable vehicle-to-vehicle cooperation, facilitating the exchange of critical alerts. By deploying time-sensitive processing techniques at the edge and utilizing DTs for comprehensive analysis, vehicles can take preemptive actions to avoid accidents. Road potholes contribute to traffic disruptions, the accordion effect, and vehicle damage, making their detection essential. This work explores advanced computer vision techniques implemented at the edge, specifically on vehicles. Roadside units (RSUs) offload DT data, and edge detection results are updated on the DT, providing a control center with accurate road condition information and maintaining a precise virtual replica of the environment. This distributed edge intelligence (DEI) enables rapid decision making with reduced latency while offering a comprehensive view of vehicle lifecycle management through DT data. The proposed algorithm, tested in real time, achieves mean average precision of 85% using YOLOv9t with minimal latency of 3 ms, ensuring effective pothole detection and seamless communication among nearby vehicles.

The Artificial Intelligence-enabled Internet of Medical Things (AI-IoMT) envisions the connectivity of medical devices encompassing advanced computing technologies to empower large-scale intelligent healthcare networks. The AI-IoMT continuously monitors patients' health and vital computations via IoMT sensors with enhanced resource utilization for providing progressive medical care services. However, the security concerns of these autonomous systems against potential threats are still underdeveloped. Since these IoMT sensor networks carry a bulk of sensitive data, they are susceptible to unobservable False Data Injection Attacks (FDIA), thus jeopardizing patients' health. This paper presents a novel threat-defense analysis framework that establishes an experience-driven approach based on a deep deterministic policy gradient to inject false measurements into IoMT sensors, computing vitals, causing patients' health instability. Subsequently, a privacy-preserved and optimized federated intelligent FDIA detector is deployed to detect malicious activity. The proposed method is parallelizable and computationally efficient to work collaboratively in a dynamic domain. Compared to existing techniques, the proposed threat-defense framework is able to thoroughly analyze severe systems' security holes and combats the risk with lower computing cost and high detection accuracy along with preserving the patients' data privacy.

The dynamic nature of intelligent transportation systems (ITS) presents significant challenges in managing the resources of the network. Traditional methods often fail to handle this dynamism of the network, resulting in communication inefficiencies and delays. This paper introduces a novel framework, DTRiDMA, which integrates digital twins (DT), intelligent reflecting surfaces (IRS), and multi-agent deep deterministic policy gradient (MADDPG) to tackle these challenges. DTs simulate various traffic scenarios and network conditions, enabling optimized resource allocation strategies. IRSs improve signal strength and coverage, ensuring efficient communication. MADDPG dynamically allocates network resources based on real-time traffic data and simulated scenarios learned through DTs. The proposed framework is trained on a comprehensive data set of real-world transportation networks that incorporate diverse traffic conditions. Extensive simulations demonstrate that the proposed framework significantly outperforms the benchmarks, achieving higher accuracy (15.5 bps/Hz), a higher maximum achievable rate (17.3 bps/Hz), maximum resource allocation efficiency (96%), and higher scalability (97%). These results highlight the framework’s ability to improve the adaptability and efficiency of ITS networks.

This paper addresses the challenges faced by 6G-enabled vehicular networks (V-Nets), including increasing road traffic, ultra-reliable and low latency communication, high data rates, and energy efficiency. The intelligent reflecting surface (IRS) is proposed as a solution to configure the propagation channel in a smart radio environment by adjusting phase shifts. However, designing IRS-assisted V-Nets that achieve ultra-reliability in dynamic and noisy communication is challenging due to the passive nature of the IRS and the limitations of deep reinforcement learning (DRL) methods. To overcome these challenges, this paper presents a computer vision (CV) enabled IRS framework for V-Nets, which combines a convolutional neural network and CV techniques. The framework utilizes real-time visual information to estimate and configure optimal beamforming for IRS-assisted V-Nets. Adapting to real-time network dynamics and intelligently guiding signals, the CV-IRS framework improves prediction accuracy to 95%, an achievable maximum rate of 11.2 bps/Hz with 100 IRS elements, and resource allocation efficiency of 88% with 10 vehicles. The simulation results demonstrate the superiority of the CV-IRS framework over benchmark schemes, making it a promising approach for the efficient configuration of IRS-assisted 6G V-Nets.

The integration among 6G communication networks, power grids, and transportation systems is emerging as a promising paradigm to achieve mutual benefits among autonomous-driving electric vehicle (EV) users, communication operators, and power grids. Task offloading strategies for autonomous driving and the traveling patterns of EVs can induce communication load fluctuation within 6G network, which subsequently influences energy flow in power grid. Conversely, electricity price from the power grid affects EV charging/discharging strategies, impacting traffic flow and autonomous driving task offloading within the 6G network. Based on the interdependencies among the three networks, this paper constructs a communication-power-transportation coupling network with 6G base stations (BSs) and fast charge stations (FCSs) acting as coupling hubs. Besides, a spatio-temporal electricity price model considering spatial traffic distribution and temporal load fluctuation is developed. Moreover, the optimization problem is formulated to jointly coordinate FCS selection, bidirectional charging/discharging power regulation, task offloading decisions, and route selection strategies to maximize demand response quality of experience (QoE), grid stability and balance under the constraint of autonomous driving quality of service (QoS). Then, a knowledge transfer collaboration-based spatio-temporal EV task offloading, energy, and traffic management joint optimization algorithm is proposed, which improves the optimization performance through knowledge transfer collaboration among EV. Finally, simulation results validate the performance improvement of the proposed algorithm in demand response QoE, grid stability and balance, and autonomous driving QoS.

The dynamic evolution of wireless communication, driven by the Internet of Everything (IoE) and the envisioned 6G networks, presents both challenges and opportunities. IoE expands beyond IoT, encompassing diverse devices, human interactions, and environmental elements. To unlock IoE’s vast potential and harness the capabilities of 6G, we propose a framework named ISRiD, which assimilates three key components: Integrated Sensing and Communication (ISAC), Reconfigurable Intelligent Surfaces (RIS), and Deep Deterministic Policy Gradient (DDPG). This creates an adaptive, data-driven communication framework for IoE and 6G. ISAC enhances situational awareness, RIS optimizes signal paths, and DDPG adds intelligence. This empowers devices to collect environmental data for optimization and intelligent decisions. By leveraging real-time sensor data, ISRiD optimizes communication protocols, significantly improving efficiency and reliability in wireless networks. Despite challenges, this approach equips IoE, including the advancements brought by 6G, to meet evolving demands, as validated by empirical experiments and simulations.

Blockchain technology has found applications across diverse domains owing to its ability to establish trust in a decentralized manner. Nevertheless, the integration of blockchain into critical infrastructure domains encounters significant challenges posed by the computational demands and storage requirements associated with the proof-of-work puzzle during the mining process. This scenario becomes particularly complex in the context of applications within the Industrial Internet of Things (IIoT), where stringent timeliness constraints are inherent, notably in functions such as intrusion detection and control. This paper presents a novel solution that takes into account the time-sensitive nature of application constraints within the IIoT. Specifically, we focus on online functions involving intrusion detection and control. By doing so, we address the imperative need for timely and secure data delivery, crucial in maintaining the integrity of hard-to-tamper ledger blocks. These blocks encapsulate measurements that are seamlessly utilized by various system functions and components. The proposed approach optimizes the utilization of heterogeneous resources governing blockchain computations. This optimization ensures that the desired properties for logging within the blockchain are met, enabling the prompt delivery of measurements. The novel collaborative mining technique entails the sharing of nonce ranges among miners, which effectively reduces the overall mining time and enhances the efficiency of the process.

Effectively managing network resources in the complex and ever-evolving realms of Internet of Things (IoT) ecosystems presents a formidable challenge. Conventional resource allocation methods often grapple with adapting to the dynamic nature of IoT environments, resulting in suboptimal performance and delayed responsiveness. The advent of stateof-the-art network technologies, notably intelligent reflecting surfaces (IRSs), further amplifies complexity, particularly in optimizing IRS configurations within dynamic networks. To address these intricacies, this paper introduces DTRiD, a fusion framework uniting digital twins (DTs), IRSs, and deep deterministic policy gradient (DDPG) to tackle these challenges. DTRiD offers a distinctive amalgamation of DTs, IRS functionalities, and DDPGs, all aimed at augmenting communication and resource allocation within the IoT. By leveraging real-world data from wireless networks, DTRiD compiles a diverse dataset encapsulating various network conditions. Extensive simulations showcase the frameworks superiority over conventional methodologies across key metrics, including accuracy, convergence, delay reduction, and energy efficiency in multiple dimensions. These results show the potential of DTRiD in restructuring the landscape of IoT communication by optimizing resource allocation dynamically, enabling it to handle complex scenarios and adapt to diverse environmental changes.

Addressing the challenge posed by the unpredictable and recurrent nature of epileptic seizures, which stand among the most significant neurological conditions, remains imperative, especially within settings inundated with high patient flow. The prompt identification of these seizures is paramount for effective patient care. Unfortunately, existing epilepsy seizure detection systems encounter limitations in availability and interpretability, thereby constraining their reliability and widespread application. Presently, neurophysiologists heavily rely on visually interpreting electroencephalogram (EEG) recordings displayed on screens to identify seizures. This article introduces an innovative method dedicated to detecting epileptic seizures within EEG signals, leveraging a specifically tailored fuzzy deep learning (FDL) architecture. The proposed methodology encompasses crucial stages of preprocessing and feature extraction, augmented by the utilization of explainable artificial intelligence models, such as local interpretable model-agnostic explanations (LIME) and Shapley additive explanation (SHAP) for enhancing model interpretability. The developed FDL model demonstrates promising results, achieving a noteworthy accuracy of 92.57%, precision of 0.96 for “normal” and 0.89 for “abnormal,” recall of 0.91 for “normal” and 0.94 for “abnormal,” and F1-score of 0.93 for “normal” and 0.91 for “abnormal,” affirming its robustness in classification tasks. In addition, to validate the effectiveness of the proposed FDL, comparisons are performed with long-short term memory networks and 1-D convolutional neural network model models. The integration of LIME and SHAP significantly enhances the interpretability of the model, providing valuable insights into influential features. This comprehensive framework adeptly balances accuracy and interpretability, thereby making a substantial stride in advancing EEG-based diagnostic tools.

In Intelligent Transportation Systems (ITS), vehicle-to-grid networks offer a promising solution to support the widespread adoption of electric vehicles (EVs) by enabling bidirectional power flow between the grid and EV batteries. However, the degradation of EV batteries over time poses challenges in assessing their reliability and minimizing system downtime. Traditional methods, such as complete charge and discharge cycles, could be more practical in dynamic operating conditions. This study, which looks at how virtual and real worlds can work together in ITS, solves this issue by showing a new way to measure how battery performance drops using a digital twin (DT) and the deep deterministic policy gradient (DDPG) method. To calculate the deterioration of battery performance and state of health (SoH), the DT records the complex interactions among state-of-charge (SoC), cell voltage, and health indicators (HI). The suggested method virtually drains the DT to estimate the actual battery capacity by using HI as a temporal measurement and the DDPG technique to train the DT model. This allows for an in-depth evaluation of performance degradation and SoH. The DT also calculates fuel consumption, offering essential battery efficiency information. In addition to demonstrating the usefulness of the DT in conjunction with the DDPG algorithm for assessing EV battery performance deterioration, SoH, and fuel consumption, experimental and simulation results also highlight the method’s potential in dynamic operating environments. Concerning practical EV applications, this comprehensive method helps to guarantee the safety, dependability, and efficiency of batteries within the framework of virtual-real integration in the ITS.

Intelligent Transportation Systems (ITSs) comprise a whole infrastructure of conventional vehicles, Connected Autonomous Vehicles (CAVs), roadside units, and communication equipment. As a result, a variety of smart sensors, cloud, and edge services are used. Due to the Vehicle-to-Everything (V2X) communication involved in these, the infrastructure becomes prone to security attacks. The most common of these is False Data Injection Attack (FDIA), which causes serious consequences upon driving decisions of a CAV. Blockchain is an ascending technology to provide proficient data security solutions; however, its implementation in securing CAV data is restricted due to its parallel reliance on cloud services. Furthermore, a standalone blockchain is prone to transaction verification delay and reduced transaction throughput, which is intolerable in the fast-paced CAV communication. This paper presents a novel framework enabling multichain, an open-source blockchain platform. Components of the proposed framework include multiple blockchains running on CAVs. The hashing algorithm operates on their Basic Safety Messages (BSMs), inputted to it as blockchain transactions. Our findings reveal that this multichain framework eliminates reliance on cloud services by devising a fully decentralized security solution against stealthy FDIAs that jeopardize a CAV’s lane-changing. It provides an economy-building point for the CAV-metaverse by incentivizing the participating CAVs. Further, it manages transactions by employing multiple parallel blockchains for enhanced throughput. CAVs perform these security checks in as low as a few milliseconds compared to the existing centralized and computationally intensive frameworks.

Age of information (AoI) is an important metric of information timeliness, which determines digital twin (DT) consistency and energy management precision. However, AoI guarantee in the time-averaged sense is unreliable to avoid the occurrence of extreme event. In this paper, we propose a novel information timeliness metric named ultra-low AoI (ULAoI). Compared with AoI, ULAoI further considers the occurrence of extreme event and higher-order statistical characteristics of excess AoI value. Multi-dimensional resources of power internet of things (PIoT) are jointly allocated to achieve ULAoI guarantee from the perspective of sensing-communication-control integration. ULAoI-DT-Prioritized deep Q network (DQN) is proposed to achieve coordinated resource allocation by approximating unobservable information with the assistance of ULAoI-DT, and preventing DQN training from using samples with large AoI based on ULAoI-induced priority. Simulation results demonstrate the superior performance of the proposed algorithm in global loss function, ULAoI guarantee, and energy management optimality.

The rapid growth of electric vehicle (EV) penetration has led to more flexible and reliable vehicle-to-grid-enabled cyber-physical systems (V2G-CPSs). However, the increasing system complexity also makes them more vulnerable to cyber-physical threats. Coordinated cyber attacks (CCAs) have emerged as a major concern, requiring effective detection and mitigation strategies within V2G-CPSs. Digital twin (DT) technologies have shown promise in mitigating system complexity and providing diverse functionalities for complex tasks such as system monitoring, analysis, and optimal control. This paper presents a resilient and secure framework for CCA detection and mitigation in V2G-CPSs, leveraging a smart DT-enabled approach. The framework introduces a smarter DT orchestrator that utilizes long short-term memory (LSTM) based actor-critic deep reinforcement learning (LSTM-DRL) in the DT virtual replica. The LSTM algorithm estimates the system states, which are then used by the DRL network to detect CCAs and take appropriate actions to minimize their impact. To validate the effectiveness and practicality of the proposed smart DT framework, case studies are conducted on an IEEE 30 bus system-based V2G-CPS, considering different CCA types such as malicious V2G node or control command attacks. The results demonstrate that the framework is capable of accurately estimating system states, detecting various CCAs, and mitigating the impact of attacks within 5 seconds.

Recent advances in electronic devices and communication infrastructure have revolutionized the traditional healthcare system into a smart healthcare system by using internet of medical things (IoMT) devices. However, due to the centralized training approach of artificial intelligence (AI), mobile and wearable IoMT devices raise privacy issues concerning the information communicated between hospitals and end-users. The information conveyed by the IoMT devices is highly confidential and can be exposed to adversaries. In this regard, federated learning (FL), a distributive AI paradigm, has opened up new opportunities for privacy preservation in IoMT without accessing the confidential data of the participants. Further, FL provides privacy to end-users as only gradients are shared during training. For these specific properties of FL, in this paper, we present privacy-related issues in IoMT. Afterwards, we present the role of FL in IoMT networks for privacy preservation and introduce some advanced FL architectures by incorporating deep reinforcement learning (DRL), digital twin, and generative adversarial networks (GANs) for detecting privacy threats. Moreover, we present some practical opportunities for FL in IoMT. In the end, we conclude this survey by discussing open research issues and challenges while using FL in future smart healthcare systems.

Space-assisted vehicular networks (SAVN) provide seamless coverage and on-demand data processing services for user vehicles (UVs). However, ultra-reliable and low-latency communication (URLLC) demands imposed by emerging vehicular applications are hard to be satisfied in SAVN by existing computation offloading techniques. Traditional deep reinforcement learning algorithms are unsuitable for highly dynamic SAVN due to the underutilization of environment observations. An AsynchronouS federaTed deep Q-learning (DQN)-basEd and URLLC-aware cOmputatIon offloaDing algorithm (ASTEROID) is presented in this paper to achieve throughput maximization considering the long-term URLLC constraints. Specifically, we first establish an extreme value theory-based URLLC constraint model. Second, the task offloading and computation resource allocation are decomposed by employing Lyapunov optimization. Finally, an asynchronous federated DQN-based (AF-DQN) algorithm is presented to address the UV-side task offloading problem. The server-side computation resource allocation is settled by an queue backlog-aware algorithm. Simulation results verify that ASTEROID achieves superior throughput and URLLC performances.

With the rapid growth of the Internet of Things (IoT) applications in Maritime Transportation Systems (MTS), cyber-attacks and challenges in data safety have also increased extensively. Meanwhile, the IoT devices are resource-constrained and cannot implement the existing security systems, making them susceptible to various types of debilitating cyber-attacks. The dynamics in the attack processes in IoT-enabled MTS networks keep changing, which makes a traditional offline or batch ML-based attack detection systems intractable to apply. This paper provides a novel approach of using an adaptive incremental passive-aggressive machine learning (AI-PAML) method to create a network attack detection system (NADS) to protect the IoT devices in an MTS environment. In this paper, we propose an NADS that utilizes a multi-access edge computing (MEC) platform to provide computational resources to execute the proposed model at a network end. Since online learning models face data saturation problems, we present an improved approximate linear dependence and a modified hybrid forgetting mechanism to filter the inefficient data and keep the detection model up-to-date. The proposed data filtering ensures that the model does not experience a rapid increase in unwarranted data, which affects the model's attack detection rate. A Markov transition probability is applied to control the MEC selection and data offloading process by the IoT devices. The performance of the NADS is verified using selected benchmark datasets and a realistic IoT environment. Experimental results demonstrate that AI-PAML achieves remarkable performance in the NADS design for an MTS environment.

With the growth of the Internet of Vehicles (IoV) in Intelligent Autonomous Transport Systems (IATS), a huge volume of data is exchanged between vehicles in these newly developed infrastructures. As a result, the requirements of securing data exchange between vehicles, autonomous or otherwise, have also increased tremendously. Securing data transfer and keeping a record of each transaction becomes a necessity in IoV/IATS. In this paper, we propose some optimized security algorithms using symmetric encryption for secure multimedia data transfer between vehicles. The main feature of these optimized algorithms is that they use a lower amount of data to generate fingerprints. The algorithms convert approximately$3.7 \times 10^{5}$samples of data into 3600 samples to generate the fingerprint. Fast Fourier Transform (FFT) is used to fetch the highest three peak values of the signal in the frequency domain. A centralized server authenticates the data transfer by comparing the$HASH$of the fingerprints and also keeps the transaction record. Through experimental analysis, the performance of proposed algorithms is confirmed by achieving reduced size samples to generate fingerprints and their authentication at the server-side.

The advent of Industry 4.0 facilitates the Int- ernet-of-Things-based-transactive energy system (IoTES), which enables innovative services with numerous independent distributed systems. These systems generate heterogeneous data in bulk, which become susceptible to cyber-attacks, particularly the stealthy false data injection attacks (FDIAs). The existing centralized FDIA detection algorithms often breach data privacy and fail to perform effectively in highly dynamic and distributed environments, such as IoTES. To resolve the issue, initially, a recurrent deep deterministic policy gradient is utilized to invent an experience-driven FDIA in a complex IoTES. The attacker intends to intelligently exploit the data integrity of smart energy meters with insufficient knowledge of the system. Subsequently, to countermove the stealth and enable independent clients to train a centralized model while keeping each client’s data privacy intact, a deep-federated-learning-based decentralized FDIA detection method using an attentive aggregation is exploited in this article. The proposed approach is capable of parallel computing and can reliably identify the stealthy FDIA on all the nodes simultaneously. Simulation results validate that the proposed scheme outperforms the state-of-the-art methods under a distributed environment with a significantly higher detection accuracy and lower computational complexity while keeping the data privacy intact.

Digital twin (DT) provides accurate guidance for multidimensional resource scheduling in 5G edge computing-empowered distribution grids by establishing a digital representation of the physical entities. In this article, we address the critical challenges of DT construction and DT-assisted resource scheduling such as low accuracy, large iteration delay, and security threats. We propose a federated learning-based DT framework and present a Secure and lAtency-aware dIgital twin assisted resource scheduliNg algoriThm (SAINT). SAINT achieves low-latency, accurate, and secure DT by jointly optimizing its total iteration delay and loss function, and leveraging abnormal model recognition (AMR). SAINT enables intelligent resource scheduling by using DT to improve the learning performance of deep Q-learning. SAINT supports access priority and energy consumption awareness due to the consideration of long-term constraints. Compared with state-of-the-art algorithms, SAINT has superior performance in cumulative iteration delay, DT loss function, energy consumption, and access priority deficit.

Physiological signals are of great importance for clinical analysis but are prone to diverse interferences. To enable practical applications, biosignal quality issues, especially contaminants, need to be dealt with automated processes. For example, after processing surface electromyography (sEMG), fatigue analysis can be done by looking into muscle contraction and expansion for clinical diagnosis. Contaminants can make this diagnosis difficult for the clinician. In real scenarios, there is a possibility of the presence of multiple contaminants in a biosignal. However, most of the work done until now focuses on the presence of a single contaminant at a time. This paper proposes a new method for the identification and classification of contaminants in sEMG signals where multiple contaminants are present simultaneously. We train a 1D convolutional neural network (1D-CNN) to classify different contaminant types in sEMG signals without prior feature extraction. The network is trained on simulated and real sEMG signals to identify five types of contaminants. Additionally, we train and test 1D-CNN to identify multiple contaminants when present simultaneously. Furthermore, to securely and accurately transfer the data to the clinician, we also present experimental results to securely route the data in a proposed Internet of health things (IoHT) by using received signal strength indicators (RSSI) to generate link fingerprints (LFs). The results show higher accuracy of the classification system at low signal-to-noise ratios (SNR) and witness lightweight security of the IoHT.

Next-generation wireless communication and networking technologies, such as sixth-generation (6G) networks and software-defined Internet of Things (SDIoT), make cyber-physical systems (CPSs) more vulnerable to cyberattacks. In such massively connected CPSs, an intruder can trigger a cyberattack in the form of false data injection, which can lead to system instability. To address this issue, we propose a graphics-processing-unit-enabled adaptive robust state estimator. It comprises a deep learning algorithm, long short-term memory, and a nonlinear extended Kalman filter, and is called LSTMKF. Through an SDIoT controller, it provides an online parametric state estimate. The reliability is improved by performing two levels of online parametric state estimation for secure communication and load management. The CPS under study is a 6G and SDIoT-enabled smart grid, which is tested on IEEE 14, 30, and 118 bus systems. Compared to existing techniques, the proposed algorithm is able to estimate the state variables of the system even during or after a cyberattack, with lower time complexity and high accuracy.

For optimal utilization of power generation resources, load forecasting plays a vital role in balancing the load flow in a power distribution network. There are several drawbacks associated with existing forecasting techniques for load flow balancing. Neural network (NN) based forecasting techniques are unable to consider the actual states of a power system, while weighted least squares state estimation (WLS) fails to counter nonlinearity in the demand profile. In this article, a hybrid approach is proposed for short term load forecasting. The hybrid technique, comprised of a WLS, NN, and adaptive neuro-fuzzy inference system (ANFIS), is termed WLANFIS. ANFIS itself is the combination of an NN and fuzzy logic. It takes a refined data set obtained through NN and WLS, which helps in determining the optimal number and types of membership functions. It also helps in determining the effective fuzzy set ranges for an individual membership function that is used by the fuzzy system. WLS provides estimated states in the real-world scenario while the NN models the nonlinearity in the demand profile and is tested on IEEE 14 and 30 bus systems as well on real-world data sets. Results show that the proposed algorithm has a higher generalization capability and provides accurate forecasting results even in the case of medium-term load forecasting. It outperforms other methodologies by achieving a mean absolute percentage error as low as 2.66%.

The traditional Internet architecture relies on the best-effort principle, which is not suitable for critical industrial Internet of Things (IIoT) applications such as healthcare systems with stringent quality-of-service (QoS) requirements. In this article, a software-defined network (SDN) based on an analytical parallel routing framework is proposed by using the massive processing power of a graphics processing unit (GPU) for dynamically optimizing multiconstrained QoS parameters in the IIoT. The framework considers three types of QoS applications for smart healthcare traffic: loss-sensitive, delay-sensitive, and jitter-sensitive. A QoS-enabled routing optimization problem is formulated as a max-flow min-cost problem, while a greedy heuristic that dispatches the path calculation task concurrently to the GPU for calculating optimal forwarding paths considering the QoS requirement of each flow is proposed. The results show that the proposed scheme efficiently utilizes the limited bandwidth cost in terms of energy and bandwidth while satisfying the QoS requirement of each flow with maximizing the network resources for future IIoT traffic flows. Comparative analysis of simulation results with shortest path delay, Lagrangian relaxation-based aggregated cost, and Sway schemes indicate a reduced violation in the service-level agreement by 17%, 19%, and 4%, respectively, by using the AttMpls topology, while it is 48%, 44%, and 7% when the Goodnet topology is used. Moreover, SEQOS is seen to be energy efficient and eight times faster than the benchmark algorithms in large IIoT networks.

Vehicle to vehicle (V2V) communication has gained importance in recent times because of the increasing number of traffic accidents and advancements in information sharing. A secure and reliable data transfer has become important to ensure the safety and trust of vehicular network users. Because of scalability of V2V communication, proposed solutions must have low computational complexities and free from latency issues. In this paper, we utilize the channel characteristics of wireless networks in V2V communication, which are used to generate link fingerprints. By using blockchain technology, data authentication among vehicles can be achieved in real time. The proposed algorithms are used to address the time complexity and delay issues in the Internet of Vehicles (IoV), which are lightweight and provide real time adversary detection within the network. Blockchain technology is used to generate blocks in which each hash is generated and shared with corresponding vehicles. The hash itself is not generated if an adversary affects the communication among vehicles. The Pearson Correlation Coefficient is calculated for each link and it is calculated as 0.9749 when there is no adversary and 0.1282 when an adversary is introduced into the network. The time complexity is computed as low asO(1) for the network.

The Cognitive Internet of Vehicles (CIoV) is an intelligent network that embeds the cognitive mechanism in the Internet of Vehicles (IoV) to sense the environment and observe the network states to learn the optimal policies adaptively. However, one of the key challenges in CIoV systems is to design a smart agent that can smartly schedule the packet transmission for ultra-reliable low latency communication (URLLC) under extreme random and noisy network conditions. We propose a software defined network (SDN) based scheduling algorithm that leverages generative adversarial network (GAN) based deep distributional Q-network (GAN-DDQN) for learning the action-value distribution for intelligent transmission scheduling. A reward-clipping technique is proposed for stabilizing the training of GAN-DDQN against the effect of broadly spanning utility values. The extensive simulation results verify that GAN-Scheduling achieves higher spectral efficiency (SE), service level agreement (SLA), system throughput, transmission packet rate with lower transmission delay, and power consumption compared to the existing reinforcement learning algorithms.

Smart meters (SMs) in Advanced Metering Infrastructure (AMI) are physically accessible due to which the protection against eavesdropping of AMI and energy theft control have gained utmost importance. A light-weight security solution is the requirement for AMI networks because of the small size and less computational capabilities of SMs. To address this problem, a light-weight security solution is proposed in this paper to detect any adversarial node in between two SMs. Through the proposed algorithms, adversarial node can be detected in AMI. Received Signal Strength Indicator (RSSI) is used to generate link fingerprints after every 60 seconds, which are sent to the Data Concentrator Unit (DCU). The DCU applies these algorithms on the received link fingerprints in order to detect any unwanted activity. MICAz motes are used as communication module of SM and adversary to generate RSSI values. These RSSI values are simulated in MATLAB in which it detects adversarial node or meter tempering with 100% accuracy by getting values other than 0 and 1 as the average of consecutive RSSI and distance between the RSSI of connected SMs.

Due to reliability issues involved with the renewable energy integration and the random deviation of demand response profile from the generation response pattern, balancing of load flow and an assessment of transients stability become challenging research issues in super smart grids (SSGs). They are even more challenging, when an unexpected outage occurs due to occurrence of three phase (L-L-L) faults (TPFs), which also causes significant power quality disturbances in power systems. To address this problem, probabilistic and deterministic analysis based on super smart node (SSN), vehicle to grid (V2G) and continuous spinning reserve (CSR) are formulated to address the randomness complexity in terms of balancing load flow and an assessment of transient stability in SSGs. Through these techniques, future contingencies can be easily predicted in SSGs. Numerical results show that V2G probabilistic modeling provides better results for balancing of load flow and an enhancement in transients stability as compared to CSR deterministic modeling in SSGs. This observation is also validated by simulation results.

In this paper, we investigate how to achieve reliable content distribution in device-to-device (D2D) based cooperative vehicular networks by combining big data based vehicle trajectory prediction with coalition formation game based resource allocation. Firstly, vehicle trajectory is predicted based on global positioning system (GPS) and geographic information system (GIS) data, which is critical for finding reliable and longlasting vehicle connections. Then, the determination of content distribution groups with different lifetimes is formulated as a coalition formation game. We model the utility function based on the minimization of average network delay to guarantee the end-to-end quality of service (QoS), which is transferable to the individual payoff of each coalition member according to its contribution. The merge and split process is implemented iteratively based on preference relations, and the final partition is proved to converge to a Nash- stable equilibrium. Finally, we evaluate the proposed algorithm based on real-world map and realistic vehicular traffic.

In the previous work, a single antenna interference cancellation (SAIC) algorithm named least mean square-blind joint maximum likelihood sequence estimation (LMS-BJMLSE) has been proposed. However, LMS-BJMLSE requires a long training sequence (TS) for channel estimation, which reduces the transmission efficiency. In another work, in order to solve this problem, a subcarrier identification and interpolation algorithm was proposed, in which the slowly converging subcarriers are identified by exploiting the correlation between the mean-square error (MSE) produced by LMS and the mean-square deviation (MSD) of the desired channel estimate. However, this correlation relationship was only found based on simulation results and no clear mathematical proof was given. The performance of the algorithm was only evaluated for the case of single interference. In this paper, the mathematical proof of the correlation relationship between MSE and MSD is given. Furthermore, we generalize LMS-BJMLSE from single antenna to receiver diversity, which is shown to provide a huge improvement over single antenna. The performance of LMS-BJMLSE is also evaluated for the case of dual interference.

Mobile Sensor Networks (MSN) are used for network load balancing, prolonging network lifetime, and improving network coverage by monitoring critical areas where manual sensor deployment cannot be performed. Addressing the problem of how to achieve maximum network coverage and network uniformity, after deploying sensors in critical areas randomly, is of significant importance recently. In this paper, we design an energy efficient distributed self-deployment algorithm, which is based on the diffusion of mobile sensors in the Region of Interest (ROI). Mobile sensors are diffused from denser sensors area to lesser or uncovered area in ROI, on the basis of localized information. Our algorithm considers ROI with the absence as well as presence of obstacles. Resemblance in the numerical and simulation analysis confirms the concreteness of our algorithm.

In orthogonal frequency division multiplexing (OFDM) based cellular systems, co-channel interference (CCI) would greatly degrade the bit error rate (BER) performance of cell-border users. Joint maximum likelihood sequence estimation (JMLSE) based single antenna interference cancellation (SAIC) algorithms have been under intense research. In this paper, both the upper and lower error probability bounds for JMLSE are extended to MQAM-OFDM systems based on a genie-aided receiver. The derived upper and lower bounds are valid for any MQAM and an arbitrary number of interferers. A tighter lower bound is derived by replacing the genie with a less generous one. We prove that this new lower bound is much tighter compared to the conventional lower bound.