The emergence of Cooperative Intelligent Transportation Systems (C-ITS) has revolutionized urban mobility by enabling seamless collaboration among vehicles, infrastructure, and individuals to improve traffic management, safety, and efficiency. Deep Reinforcement Learning (DRL) has become a key technology in this ecosystem, empowering autonomous agents to make real-time decisions that optimize traffic flow, reduce congestion, and enhance road safety. Although many surveys on Intelligent Transportation Systems (ITS) either overlook cooperative aspects or primarily emphasize security, this paper bridges the gap by examining the diverse applications of DRL in C-ITS. It examines critical areas such as traffic signal control, AV coordination, route planning, and human-vehicle interaction. The study also traces the evolution of DRL algorithms, their adaptation to transportation challenges, and their integration with cutting-edge projects and standards. Additionally, the paper provides a comprehensive analysis of current research trends, identifying achievements, unresolved challenges, and future directions in the field. By synthesizing existing literature and highlighting the synergy between DRL and C-ITS, this survey serves as a valuable resource for researchers, policymakers, and industry professionals striving to develop intelligent, cooperative, and sustainable transportation systems. The insights offered aim to guide advancements in this rapidly growing domain, fostering innovation and practical implementation.

Federated learning is a pivotal technique in vehicular edge computing (VEC), which allows distributed machine learning across vehicles while preserving data privacy. However, it is critical to select the vehicles to participate in the learning process effectively. In this context, the problem related to finding optimized vehicles to participate in the learning task is discussed. An optimized vehicle selection mechanism is needed in vehicular networks, as traffic flow occurs in a real environment, influenced by different conditions such as security, vehicle capacities, data freshness, weather conditions, etc. The primary key contributions of this research are as follows: (i) formulation of vehicle selection in vehicular edge computing as an optimization problem, and (ii) the development of a new approach using the Tabu search algorithm named TS-EVS, specifically designed for the problem, as it is shown to be NP-hard. We evaluated TS-EVS using a Python implementation, considering the outcome of the proposal in two scenarios taking into account the MEC applications and the number of deployed vehicles. Compared to the untrusted version of the proposal, the numerical results demonstrate how the suggested approach significantly improves accuracy and reduces learning time.

O-RAN (Open Radio Access Network) is a set of open and interoperable radio access technologies, guided by the O-RAN Alliance, that, despite an open ecosystem, introduces significant security risks, expanding the threat surface in 6G networks. Traditional perimeter-based security approaches are inadequate for O-RAN’s highly distributed, multi-vendor environments, where Zero Trust Architecture (ZTA) becomes essential for robust security. To address these challenges, we propose a novel blockchain-based, decentralized Zero-Trust Framework specifically designed for O-RAN security. Our proposed framework comprises two key layers: the first layer utilizes Federated Learning (FL) and Transfer Learning (TL) for advanced attack detection, enabling distributed, privacy-preserving threat analysis across O-RAN nodes. The second layer enforces Zero Trust access control through a blockchain-based identity management system, ensuring tamper-resistant, real-time policy updates. This multi-layered framework provides adaptive threat detection and resilient access control, validated through simulations demonstrating high detection accuracy and robust access management with minimal impact on network performance, offering a scalable security solution for next-generation O-RAN deployments.

The Open Radio Access Network (O-RAN) architecture has enabled the integration of multi-vendor equipment, yielding a significant enhancement in the flexibility and interoperability of telecommunications networks. However, this openness has also introduced new security vulnerabilities, particularly in supply chain integrity. Malicious actors may exploit weaknesses at various stages of production, distribution, or integration, leading to critical threats such as data tampering, unauthorized access, and denial-of-service (DOS) attacks. To address these challenges, this paper proposes a novel blockchain-based framework designed to secure the O-RAN supply chain. The proposed solution leverages a private permissioned blockchain ledger and cryptographic firmware authentication to ensure the integrity and authenticity of network equipment throughout its lifecycle. Specifically, the framework consists of: (1) a decentralized architecture integrating blockchain network components, equipment node validators, and secure firmware authentication mechanisms; and (2) a consensus-based verification model to enhance trust and transparency within the supply chain. To the best of our knowledge, this is one of the first approaches to use blockchain for O-RAN supply chain security, and also addressing emerging security threats in a scalable and tamper-resistant manner. Experimental validation and security assessments demonstrate the effectiveness of the proposed framework in mitigating supply chain risks, making it a promising solution for ensuring trust and robustness in next-generation O-RAN ecosystems.

Mobile behavioural biometrics, leveraging touchscreen and background sensor data, have emerged as a promising solution for Continuous Authentication (CA) on mobile devices, enabling secure user authentication. In this paper, we introduce an enhanced CA framework named AI-MBBCA, that integrates a Genetic Algorithm (GA) for optimal training hyper-parameter selection and an Isolation Forest (IF) as a secondary layer for impostor attack detection. A hybrid Long Short-Term Memory (LSTM) network, trained using a triplet loss function and augmented with a regularisation method, effectively captures spatial and temporal patterns in user behaviour. Experimental evaluations on the BehavePassDB dataset demonstrate that AI-MBBCA significantly improves authentication accuracy and reduces error rates across multiple tasks, with notable improvements in the Area Under the Curve (AUC) compared to two other approaches from the literature. Integrating AI-Driven optimisation, including GA and IF-based anomaly detection, paves the way for more resilient and adaptive Behavioural Biometrics Continuous Authentication (BBCA) systems, addressing the challenges posed by sophisticated forgery scenarios in dynamic mobile environments.

In light of the ongoing transformation in the automotive industry, driven by the adoption of 5G and the proliferation of connected vehicles, network security has emerged as a critical concern. This is particularly true for the implementation of cutting-edge 5G services such as Network Slicing (NS), Software Defined Networking (SDN), and Multi-access Edge Computing (MEC). As these advanced services become more prevalent, they introduce new vulnerabilities that can be exploited by cyber attackers. Consequently, Network Intrusion Detection Systems (NIDSs) are pivotal in safeguarding vehicular networks against cyber threats. Still, their efficacy hinges on extensive data, which often contains sensitive and confidential information such as vehicle positions and owner’s behaviors, raising privacy concerns. To address this issue, we propose a Privacy-Preserving Self-Supervised Learning (SSL) based Intrusion Detection System for 5G-V2X networks. The majority of works in the literature relying on Federated Learning (FL) and often overlook data labeling on the end devices. Our methodology leverages SSL to pre-train NIDSs using unlabeled data. Post-training is then performed with a minimal amount of labeled data, which can be carefully crafted by an expert. This novel technique allows the training of NIDSs with huge datasets without compromising privacy, consequently enhancing the efficacy of cyber-attack protection. Our innovative SSL pre-training methodology has yielded remarkable results, demonstrating a substantial improvement of up to 9% in accuracy across a diverse range of training dataset sizes, including scenarios with as few as 200 data samples. Our approach highlights the potential to enhance automotive network security significantly, showcasing groundbreaking achievements that set a new standard in the field of automotive cybersecurity.

Artificial intelligence (AI) has revolutionized many fields, including healthcare. The adoption of AI techniques in critical healthcare tasks, such as cancer diagnosis, holds great promise for revolutionizing the healthcare system. AI algorithms can be trained on vast datasets to recognize patterns, detect anomalies, and provide accurate assessments. However, the lack of realistic and up-to-date medical data poses a significant challenge to the widespread adoption of AI techniques. Additionally, privacy concerns surrounding sensitive medical data, particularly Patient Health Records (PHR), hinder data sharing among healthcare practitioners. This paper aims to address these challenges by proposing a novel framework, entitled SecureMed, that uses Federated Learning (FL) and Blockchain to preserve privacy in the healthcare system. In particular, SecureMed consists of (1) A novel distributed architecture that enables secure collaboration among multiple Mobile Edge Computing (MEC)-based Internet of Medical Things (IoMT) devices, while ensuring the privacy of healthcare systems; (2) A fairness-aware Federated Learning (FL) solution to ensure that model performance is balanced across all participating healthcare institutions, addressing the issue of imbalanced data contributions; (3) A Secure Multiparty Computation (SMPC) protocol to ensure secure aggregation of local model updates; and (4) A blockchain-based reputation model for collaborative FL training. The proposed framework leverages smart contracts to ensure trustworthiness, decentralization, and transparency in the FL process. The experimental results using the CIC IoMT dataset 2024 highlight the promising potential of SecureMed in revolutionizing healthcare systems.

Deep Reinforcement Learning (DRL) has become a fundamental element in advancing Autonomous Systems, significantly transforming fields like autonomous vehicles, robotics, and drones. This survey paper provides a comprehensive overview of the role of DRL in autonomous systems, focusing on recent advancements, applications, and challenges. Through a synthesis of existing literature and case studies, the paper elucidates key principles, methodologies, and implications of integrating DRL into autonomous systems. The systematic examination of selected papers reveals recurring patterns, emerging trends, and identifies gaps and opportunities for further research. By exploring the applications of DRL across different autonomous systems, commonalities, distinctions, and prevalent challenges are discussed, laying the groundwork for future advancements and practical implementations in this rapidly evolving field.

Efficient utilization of Big data in smart cities is crucial for smooth operation of urban environments. Machine learning-enabled big data analytics is essential for optimizing city operations, improving resource management, and enhancing the quality of urban life. By leveraging machine learning (ML) algorithms to process and analyze the vast amounts of data generated in smart cities, authorities can gain insights and make real-time data-driven decisions. This article provides a comprehensive survey of how ML techniques are applied to analyze the large volumes of data generated by smart cities to improve urban living. Various ML algorithms, such as supervised, unsupervised, and reinforcement learning (RL) are discussed by highlighting their roles in numerous applications. Moreover, their distinguishing features are examined, enabling the selection of the most suitable algorithms for various applications in smart cities. Finally, the survey explores various challenges and suggests numerous research directions.

Security and privacy are crucial in V2X networks due to sensitive user information. Public Key Infrastructure (PKI) is widely used in C-ITS to ensure security and privacy. However, the practical implementation of PKI faces challenges in achieving seamless communication across diverse ITS projects worldwide. The absence of interoperability between PKI systems and unre-solved issues in existing PKI standards hinder global adoption. Despite available security standardizations using centralized PKI technology for V2X, a universally adopted PKI-based security architecture is necessary. Furthermore, the progress made in 5G V2X technology has demonstrated significant potential for revolutionizing V2X communication in the future. Enhancing the level of trust through integration of the 5G Core Network (5GC) into the PKI security mechanism can lead to more secure and efficient V2X communication. To address these challenges, we propose a blockchain-based architecture that integrates the 5GC network with the PKI infrastructure, aiming to enhance privacy and security in 5G V2X communication. Our solution is designed to be distributed and interoperable, aligned with existing ETSI ITS PKI standard. By utilizing Hyperledger Fabric (HLF) platform, a permissioned blockchain framework, we present the architecture and conduct a comprehensive security analysis to ensure compliance with security and privacy requirements of V2X communications.

The emergence of Autonomous Vehicles has ushered in a new era of transportation efficacy and safety. Platooning, which involves vehicles traveling closely in sync, offers potential for mitigating traffic congestion, decreasing fuel usage, and improving road safety. However, realizing platooning’s full potential requires robust control strategies adaptable to various conditions. This study explores integrating Federated Deep Reinforcement Learning (FDRL) into AV platooning systems to enhance control and efficiency. It focuses on leveraging FDRL to optimize platoon behavior while considering AV’s distributed nature. Specifically, the proposed approach involves training Deep Reinforcement Learning (DRL) model locally on individual vehicles (Agents) within a platoon, allowing them to adapt and learn from local data and experiences. The trained model is then transferred to other platoons via 5 G infrastructure, improving overall performance. Simulation studies demonstrate the superiority of FDRL over other methods, suggesting its potential to advance AV platooning systems in future transportation landscapes.

Training without sharing data is one of the drivers that makes Federated Learning (FL) more attractive, compared to centralized approaches. However, requiring each learner to train the full model may not be efficient, particularly for devices with restricted resources, such as those available in Unmanned Aerial Vehicles (UAVs). To address this issue, a variation of FL technique, specifically Split Federated Learning (SFL), has recently been proposed. Unlike FL, the key concept of SFL is to divide the layers of the neural network among the involved learners. Therefore, each individual client will train only a segment of the model (submodel) rather than the entire model. Clearly, this technique, besides data privacy, optimizes the utilization of computational resources, reduces client-side training time, and enhances model privacy. However, there are questions that require answers: How should we split the model? Shall we systematically divide it in half, or is there a more optimal approach? In this line of thought, this paper provides a detailed analysis of possible splitting schemes of a power consumption prediction model for UAV s. First, the SFL-enabled model is presented. Second, an experimental analysis is conducted in which different splitting alternatives are made and numerically analyzed to examine the influence of network layering on split federated learning performance.

The Internet of Unmanned Aerial Vehicles (UAVs) envisions critical services like Collision detection and Avoidance among Vehicles (CAVs). These services are typically implemented at the Multi-access Edge Computing (MEC) to enable ultra-low latency communication, ensuring real-time reactions to prevent collisions. To ensure network coverage and optimal connection of UAVs to the nearest MEC host, the CAV must be deployed across all MEC hosts. However, this may impose additional demands on these hots’ available computational and memory resources. We introduce an Artificial Intelligence empowered framework to optimize virtualized resource allocation to the MEC hosts. The framework harnesses the capabilities of Deep Learning (DL) for twofold pivotal objectives: (i) Forecasting UAV Density: the framework predicts the UAV density that each MEC host must accommodate. This anticipatory insight guides resource allocation, adapting it to the anticipated demand dynamics. (ii) Precision in Virtual Resource Allotment: DL is further instrumental in calibrating the precise quantum of virtual resources requisite for the collision detection application to function optimally. This approach ensures the collision avoidance system’s peak efficiency without unduly taxing MEC host computational capacities. Validation of the proposed framework entails empirical analysis. The experimental outcomes underscore the precision of the prediction model and corroborate the resource allocation framework’s efficacy.

The emergence of 6G networks heralds a transformative era in network slicing, facilitating tailored service delivery and optimal resource utilization. Despite its promise, network slice optimization heavily relies on Deep Reinforcement Learning (DRL) models, often criticized for their black-box decision-making processes. This paper introduces a novel Composable eXplainable Reinforcement Learning (XRL) framework customized for distributed systems like 6G Network Slicing. The proposed framework leverages Large Language Models (LLMs) and Prompt Engineering techniques to elucidate DRL algorithms’ decision-making mechanisms, with a specific emphasis on user profiles. The latter transforms the inherently opaque nature of DRL into an interpretable textual format accessible not only to eXplainable AI (XAI) experts but also to diverse network slice provider stakeholders, engineers, leaders, and beyond. Experimental results underscore the efficacy of the proposed Composable XRL framework, showcasing substantial improvements in transparency and comprehensibility of DRL decisions within the context of 6G network slicing.

In this work, the adjustment of nodes’ sending rate in IPv6 over low-power wireless personal area networks (6LoWPAN) is investigated. 6LoWPAN enables low-power equipment connecting to the Internet via Internet of Things (IoT) network. In such network, nodes are competing to share the bandwidth, in order to deliver their sensed data as fast as possible, to a central node (access point, cloud server, aggregator, etc.). With the lack of an optimal sharing policy, such competitive behavior however may affect directly networks’ quality of service and degrade their performance in terms of nodes’ throughput (sending rate), latency of the network, and nodes’ energy consumption. To overcome this, we propose a new noncooperative game-based scheme, called DeepGame, where each IoT device is acted as a player, asking for a high data throughput. DeepGame enables to adjust nodes’ throughput based on four main criteria: 1) nodes’ preferences concerning the data rate; 2) nodes’ priorities in the IoT network; 3) the quality of nodes data; and 4) nodes’ remaining energy. Moreover, a multiagent deep reinforcement learning model is built in federated way, on top of our game model in order to enable nodes (agents) learning the optimal action at each step of the game, and hence reaching the Nash equilibrium (NE) state. We use the Cooja emulator on top of Contiki OS to implement our game-based model. We evaluate and validate the DeepGame scheme on top of two different medium access techniques, carrier-sense multiple access with collision avoidance and time-division medium access (TDMA). Numerical results, with a good confidence interval, illustrate the efficiency of our scheme when leveraging the TDMA access technique in not only quickly converging to NE situation but also improving the performances of the IoT network including, nodes’ energy consumption, nodes’ throughput, and network overhead, when compared to other schemes.

Current flow-based Network Intrusion Detection Systems (NIDSs) have the drawback of detecting attacks only once the flow has ended, resulting in potential delays in attack detection and increasing the risk of damage due to the infiltration of a greater number of malicious packets. Moreover, the delay provides attackers with an extended period of presence within the network, enabling them to execute subsequent attacks. To overcome this drawback, this work addresses the issue of early flow classification in NIDSs that incorporates a Deep Learning (DL) model. This model leverages Recurrent Neural Networks (RNNs), including Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), coupled with attention mechanisms. This strategic combination allows the system to harness the inherent sequential nature of packets within network flows, enhancing the efficiency of early flow classification. We conducted experiments on two up-to-date network intrusion datasets, namely CIC-IDS2017 and 5G-NIDD. Our findings demonstrate the effectiveness and accuracy of the proposed NIDS in classifying network flows. Additionally, our approach showcases its efficacy by promptly identifying and detecting attacks in their early stages without the need for flow termination. This results in a reduction in both the number of initial packets required for classification and the time needed for detection.

Intelligent Transportation Systems (ITSs) are transforming the global monitoring of road safety. These systems, including vehicular networks and transportation infrastructure, are vulnerable to several security issues, which could disrupt services and potentially cause harm to the users. It is crucial to establish robust security measures to protect against evolving attacks and ensure the safe and reliable operation of ITS. Artificial Intelligence (AI)-based Intrusion Detection Systems (IDS) are mainly used to enhance the security of ITS. The adoption of AI-based techniques to secure ITS against new emerging threats has been limited due to a lack of realistic and recent data on these types of attacks ($i.e.,$zero-day attacks). In this context, we introduce a novel Edge-based Framework that uses Federated Learning (FL) and blockchain to secure ITS against new emerging threats. In particular, our proposed framework consists of (1) a novel distributed Edge-based architecture that allows multiple Edge nodes to securely collaborate while preserving their privacy; and (2) a decentralized and secure reputation system based on blockchain technology to maintain the reliability and trustworthiness of the FL process within the ITS; This system manages reputation data for individual nodes (such as vehicles), guaranteeing the integrity of the FL training process. Experiment results using the UNSW-NB15 dataset show that our proposed framework achieves high accuracy and F1 score (99%) in detecting new threats while ensuring the privacy and reliability of the whole ITS. These results demonstrate the effectiveness of our proposed framework in securing ITS.

As the automotive industry grows, modern vehicles will be connected to 5G networks, creating a new Vehicular-to-Everything (V2X) ecosystem. Network Slicing (NS) supports this 5G-V2X ecosystem by enabling network operators to flexibly provide dedicated logical networks addressing use case specific-requirements on top of a shared physical infrastructure. Despite its benefits, NS is highly vulnerable to privacy and security threats, which can put Connected and Automated Vehicles (CAVs) in dangerous situations. Deep Learning-based Intrusion Detection Systems (DL-based IDSs) have been proposed as the first defense line to detect and report these attacks. However, current DL-based IDSs are processing and memory-consuming, increasing security costs and jeopardizing 5G-V2X acceptance. To this end, this paper proposes a lightweight intrusion detection scheme for 5G-V2X sliced networks. Our scheme leverages DL and Knowledge Distillation (KD) for training in the cloud and offloading knowledge to slice-tailored lightweight DL models running on CAVs. Our results show that our scheme provides an optimal trade-off between detection accuracy and security overhead. Specifically, it can reduce security overhead in computation and memory complexity to more than 50% while keeping almost the same performance as heavy DL-based IDSs.

Deploying Connected and Automated Vehicles (CAVs) on top of 5G and Beyond networks (5GB) makes them vulnerable to increasing vectors of security and privacy attacks. In this context, a wide range of advanced machine/deep learning-based solutions have been designed to accurately detect security attacks. Specifically, supervised learning techniques have been widely applied to train attack detection models. However, the main limitation of such solutions is their inability to detect attacks different from those seen during the training phase, or new attacks, also called zero-day attacks. Moreover, training the detection model requires significant data collection and labeling, which increases the communication overhead, and raises privacy concerns. To address the aforementioned limits, we propose in this paper a novel detection mechanism that leverages the ability of the deep auto-encoder method to detect attacks relying only on the benign network traffic pattern. Using federated learning, the proposed intrusion detection system can be trained with large and diverse benign network traffic, while preserving the CAVs' privacy, and minimizing the communication overhead. The in-depth experiment on a recent network traffic dataset shows that the proposed system achieved a high detection rate while minimizing the false positive rate, and the detection delay.

The advancements in the field of the Internet of Things (IoT) have fueled technological advancements in remotely handling agricultural operations, as well as the successful implementation of Precision Agriculture (PA) around the world. In this paper, we present Cluster-based Routing using an Optimized framework for Precision agricultural monitoring (CROP) that uses the recently developed Sooty Tern Optimization Algorithm (STOA). CROP specifically aims to detect unauthenticated entry into the agricultural field and various other factors related to PA. We perform a simulation analysis of CROP, and the performance of CROP is overwhelming, as it not only enhances stability period and network longevity by 58.9% and 65.5% respectively, but also proves to be scalable as compared to the Fuzzy-C-Means (FCM) algorithm and other routing protocols pertaining to PA.

Fine-granular management of cloud-native computing resources is one of the key features sought by cloud and edge operators. It consists in giving the exact amount of computing resources needed by a microservice to avoid resource over-provisioning, which is, by default, the adopted solution to prevent service degradation. Fine-granular resource management guarantees better computing resource usage, which is critical to reducing energy consumption and resource wastage (vital in edge computing). In this paper, we propose a novel Zero-touch management (ZSM) framework featuring a fine-granular computing resource scaler in a cloud-native environment. The proposed scaler algorithm uses Artificial Intelligence (AI)/Machine Learning (ML) models to predict microservice performances; if a service degradation is detected, then a root-cause analysis is conducted using eXplainable AI (XAI). Based on the XAI output, the proposed framework scales only the needed (exact amount) resources (i.e., CPU or memory) to overcome the service degradation. The proposed framework and resource scheduler have been implemented on top of a cloud-native platform based on the well-known Kubernetes tool. The obtained results clearly indicate that the proposed scheduler with lesser resources achieves the same service quality as the default scheduler of Kubernetes.

Cooperative collision avoidance between inland waterway ships is among the envisioned services on the Internet of Ships. Such a service aims to support safe navigation while optimizing ships' trajectories. However, to deploy it, timely and accurate prediction of ships' positioning with real-time reactions is needed to anticipate collisions. In such a context, ships positions are usually predicted using advanced Machine Learning (ML) techniques. Traditionally, ML schemes require that the data be processed in a centralized way, e.g., a cloud data center managed by a third party. However, these schemes are not suitable for the collisions avoidance service due to the inaccessibility of ships' positioning data by this third party, and allowing connected ships to get access to sensitive information. Therefore, in this paper, we design a new cooperative collision avoidance system for inland ships, while ensuring data security and privacy. Our system is based on deep federated learning to collaboratively build a model of ship positioning prediction, while avoiding sharing their private data. In addition, it is deployed at multi-access edge computing (MEC) level to provide low-latency communication to ensure fast responses during collision detection. Furthermore, it relies on Blockchain and smart contracts to ensure trust and valid communications between ships and MEC nodes. We evaluate the proposed system using a generated dataset representing ships mobility in France. The results, which demonstrate the accuracy of our prediction model, prove the effectiveness of our cooperative collision avoidance system in ensuring timely and reliable communications and avoiding collisions between ships.

The zero Touch Management (ZSM) concept in 5G and Beyond networks (B5G) aims to automate the management and orchestration of running network slices. This requires heavy usage of advanced deep learning techniques in a closed-loop way to auto-build the suitable decisions, enabling to meet network slices’ requirements. In this context, Federated Learning (FL) is playing a vital role in training deep learning models in a collaborative way among thousands of network slice participants while ensuring their privacy and hence network slice isolation. Specifically, running network slices may share only their model parameters with a central entity, e.g., Inter Domain Slice Manager, to aggregate them and build a global model. Thus, the central entity does not directly access the training data. However, FL is vulnerable to poisoning attacks, where an insider participant may upload poisoning updates to the central entity so that it can cause a construction failure of the global model and thus affect its global performance. Therefore, it is crucial to design security means to detect and mitigate such threats. In this paper, we design a novel framework to automatically detect malicious participants in the FL process. In particular, our framework first uses a deep reinforcement algorithm to dynamically select a network slice as a trusted participant, based mainly on its reputation. The selected participant will then be in charge of identifying poisoning model updates by leveraging unsupervised machine learning. We demonstrate the feasibility of our framework on top of a real dataset that we generate using the 5G OpenAirInterface (OAI) platform. Evaluation results show the efficiency of our framework in dealing with poisoning attacks even with the presence of several malicious participants.

Unlike previous mobile networks, 5G and beyond (B5G) networks are expected to be the key enabler of various vertical industries such as eHealth, intelligent transportation, and Industrial IoT verticals. To support that, B5G networks enable to sharing of common physical resources (radio, computation, network) among different tenants, thanks to network slicing concept and network softwarization technologies, including Software Defined Networking (SDN) and Network Function Virtualization (NFV). Therefore, new research challenges related to B5G networks have emerged, such as resources management and orchestration, service chaining, security, and QoS management. However, there is a lack of a realistic platform enabling researchers to design and validate their solutions effectively, since B5G networks are still in their early stages. In this paper, we first discuss the different methods for deploying realistic B5G platforms for the V2X vertical, including the key B5G technologies. Then, we describe DRIVE-B5G, a novel platform that serves as an end-to-end test-bed to emulate a vehicular network environment, allowing researchers to provide proof of concept, validate, and evaluate their research approaches.

The emergent Zero touch Service and Management (ZSM) paradigm aims to automate the orchestration and management of running network slices, in Beyond 5G networks (B5G), with an unprecedented level of scalability. To achieve this vision, ZSM calls for a large usage of advanced deep learning algorithms, in order to dynamically build efficient decisions. In this context, Federated deep Learning (FL) proved their efficiency in not only building collaborative deep learning models, among several network slices, but also ensuring the privacy and isolation of such network slices. Indeed, FL-based solutions give “machine-centric” decisions about running network slices and their performance, which will be then executed/applied by managers, i.e., slice manager staff/module. However, FL-enabled solutions do not provide any details about why and how such decisions were made, and thus such decisions cannot be properly trusted/understood by slice managers. To alleviate this issue, we leverage eXplainable Artificial Intelligence (XAI) paradigm that aims to improve the transparency of black-box FL decision-making process. In particular, XAI helps to explain the FL-based decisions to make them interpretable/trustable by network slices managers. In this paper, we design a novel XAI-powered framework to explain FL-based decisions. We first build a deep learning model in federated way, to predict key performance indicators (KPI) of network slices. Our FL-based KPI prediction is useful for the configuration and the management of network slice lifecycle, especially for the Service Level Agreement (SLA) violation and the network slice re-configuration. Then, we develop several XAI models on the top of our FL-based model, such as SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), RuleFit, and Partial Dependence Plot (PDP), to enhance the level of trust, credibility (of the local data/model), transparency, and explanation of the FL-based decisions, while adhering the data privacy, to different B5G network stakeholders, such as slice managers. Experiments results show the efficiency of our XAI-powered framework, to explain FL-based decisions related to latency KPI predictions.

Intrusion detection systems (IDS) have already demonstrated their effectiveness in detecting various attacks in cellular vehicle-to-everything (C-V2X) networks, especially when using machine learning (ML) techniques. However, it has been shown that generating ML-based models in a centralized way consumes a massive quantity of network resources, such as CPU/memory and bandwidth, which may represent a critical issue in such networks. To avoid this problem, the new concept of Federated Learning (FL) emerged to build ML-based models in a distributed and collaborative way. In such an approach, the set of nodes, e.g., vehicles or gNodeB, collaborate to create a global ML model trained across these multiple decentralized nodes; each one with its respective data samples that are not shared with any other nodes. In this way, FL enables, on the one hand, data privacy since sharing data with a central location is not always feasible and, on the other hand, network overhead reduction. This paper designs a new IDS for C-V2X networks based on FL. It leverages edge computing to not only build a prediction model in a distributed way, but also to enable low latency intrusion detection. Moreover, we build our FL-based IDS on top of well-know CIC-IDS2018 dataset, that includes the main network attacks. Noting that, we first perform a feature engineering on the dataset using the ANOVA method to consider only the most informative features. Simulation results show the efficiency of our system compared to the existing solutions in terms of attack detection accuracy while reducing the network resource consumption.

New Radio Vehicle-to-Everything (NR-V2X) distributed communication mode utilizes a semi-persistent scheduling (SPS) scheme, in which a reserved radio resource is used for a certain duration. However, attackers can exploit the predictability of SPS’s resource assignment to cause packet dropping, by selecting already reserved resources. In this paper, we first develop a feedback-based attack detection strategy then devise the optimal evasion policy based on a fuzzy inference system that dynamically adapts the resource reservation time. Simulation results show the effectiveness of our scheme in greatly reducing packet dropping-based attacks, and also in improving the packet reception ratio within the network.

With the rapid growth of inland shipping and the increased number of inland ships required to convey the freight, the ultimate goal is to design an intelligent shipping system to make inland shipping safer and more efficient. Cooperative ships safety systems are an emerging approach to supporting reliable collision detection. Two critical requirements of cooperative safety applications are position accuracy and ultra-low communication latency. Therefore, this paper proposes a new collision detection system for inland ships based on Federated Deep Learning, which is expected to provide a robust positioning prediction model. In addition, it guarantees collaborative learning among all ships while preserving ships' privacy. Furthermore, our safety system is deployed at Multi-access Edge Computing (MEC) nodes to ensure low latency communication and guarantee real-time reaction to avoid collisions between ships. Extensive simulation results show the system's accuracy and, hence, the efficiency of the collision detection system to ensure timely and trusted communications and avoid collisions between ships.

Software-defined network (SDN) is widely deployed on Smart Grid (SG) systems. It consists in decoupling control and data planes, to automate the monitoring and management of the communication network, and thus enabling zero touch management of SG systems. However, SDN-based SG is prone to several security threats and varios type of new attacks. To alleviate these issues, various Machine/Deep learning (ML/DL)-based intrusion detection systems (IDS) were designed to improve the detection accuracy of conventional IDS. However, they suffer from high variance and/or bias, which may lead to an inaccurate security threat detection. In this context, ensemble learning is an emerging ML technique that aims at combining several ML models; the objective is to generate less data-sensitive (i.e., less variance) and more flexible (i.e., less bias) machine learning models. In this paper, we design a novel framework, called BoostIDS, that leverages ensemble learning to efficiently detect and mitigate security threats in SDN-based SG system. BoostIDS comprises two main modules: (1) A data monitoring and feature selection module that makes use of an efficient Boosting Feature Selection Algorithm to select the best/relevant SG-based features; and (2) An ensemble learning-based threats detection moel that implements a Lightweight Boosting Algorithm (LBA) to timely and effectively detects SG-based attacks in a SDN environment. We conduct extensive experiments to validate BoostIDS on top of multiple real attacks; the obtained results using NSL-KDD and UNSW-NB15 datasets, confirm that BoostIDS can effectively detect/mitigate security threats in SDN-based SG systems, while optimizing training/test time complexity.

Attacks against the IoT network are increasing rapidly, leading to an exponential growth in the number of unsecured IoT devices. Existing security mechanisms are facing several issues due to the lack of real-time decisions, high energy consumption, and high time delays. In this context, we propose a novel Low-Latency Fog-based Framework, called FogFed, to secure IoT applications using Fog computing and Federated Learning (FL). The fog brings security mechanisms near IoT devices reducing delays in communication, while FL enables a privacy-aware collaborative learning between IoT while preserving their privacy. FogFed combines two levels of detection, Fog-based IoT attack detection using a binary FL classifier and cloud-based IoT attack detection using a Multiclass FL classifier. The in-depth experiments results with well-known IoT attack/malware using, the UNSW-NB15 datastet, show the significant accuracy (99%) and detection rate (99%), which outperforms centralized ML/DL models, while significantly reducing delays and preserving the privacy.

Connected and Automated Vehicles (CAVs) represent one of the main verticals of 5G to provide road safety, road traffic efficiency, and user convenience. As a key enabler of 5G, Network Slicing (NS) aims to create Vehicle-to-Everything (V2X) network slices with different network requirements on a shared and programmable physical infrastructure. However, NS has generated new network threats that might target CAVs leading to road hazards. More specifically, such attacks may target either the inner functioning of each V2X-NS (intra-slice) or break the NS isolation. In this paper, we aim to deal with the raised question of how to detect intra-slice V2X attacks. To do so, we leverage both Virtual Security as a Service (VSaS) concept and deep learning (DL) to deploy a set of DL-empowered security Virtual Network Functions (sVNFs) within V2X-NSs. These sVNFs are in charge of detecting such attacks, thanks to a DL model that we also build in this work. The proposed DL model is trained, validated, and tested using a publicly available dataset. The results show the efficiency and accuracy of our scheme to detect intra-slice V2X attacks.

Industry 4.0 is based on machine learning and advanced digital technologies, such as Industrial-Internet-of-Things and Cyber-Physical-Production-Systems, to collect and process data coming from manufacturing systems. Thus, several industrial issues may be further investigated including, flows disruptions, machines’ breakdowns, quality crisis, and so on. In this context, traditional machine learning techniques require the data to be stored and processed in a central entity, e.g., a cloud server. However, these techniques are not suitable for all manufacturing use cases, due to the inaccessibility of private data such as resources’ localization in real time, which cannot be shared at the cloud level as they contain personal and sensitive information. Therefore, there is a critical need to go toward decentralized learning solutions to handle efficiently distributed private sub-datasets of manufacturing systems. In this article, we design a new monitoring tool for system disruption related to the localization of mobile resources. Our tool may identify mobile resources (human operators) that are in unexpected locations, and hence has a high probability to disturb production planning. To do so, we use federated deep learning, as distributed learning technique, to build a prediction model of resources locations in manufacturing systems. Our prediction model is generated based on resources locations defined in the initial tasks schedule. Thus, system disruptions are detected, in real time, when comparing predicted locations to the real ones, that is collected through the IoT network. In addition, our monitoring tool is deployed at Fog computing level that provides local data processing support with low latency. Furthermore, once a system disruption is detected, we develop a dynamic rescheduling module that assigns each task to the nearest available resource while improving the execution accuracy and reducing the execution delay. Therefore, we formulate an optimization problem of tasks rescheduling, before solving it using the meta-heuristic Tabu search. The numerical results show the efficiency of our schemes in terms of prediction accuracy when compared to other machine learning algorithms, in addition to their ability to detect and resolve system disruption in real time.

Industry 5.0 is rapidly growing as the next industrial evolution, aiming to improve production efficiency in the 21stcentury. This evolution relies mainly on advanced digital technologies, including Industrial Internet of Things (IIoT), by deploying multiple IIoT devices within industrial systems. Such a setup increases the possibility of threats, especially with the emergence of IIoT botnets. This can provide attackers with more sophisticated tools to conduct devastating IIoT attacks. Besides, machine learning (ML) and deep learning (DL) are considered as powerful techniques to efficiently detect IIoT attacks. However, the centralized way in building learning models and the lack of up-to-date datasets that contain the main attacks are still ongoing challenges. In this context, multiaccess edge computing (MEC) and federated learning (FL) are two promising complementary technologies. MEC brings computing capabilities at the edge of the industrial systems, while FL leverages the edge resources to enable a privacy-aware collaborative learning, especially in multiindustrial systems context. In this article, we design a novel MEC-based framework to secure IIoT applications leveraging FL, called FedGame. Specifically, FedGame enables multiple MEC domains to collaborate securely to deal with an IIoT attack, while preserving the privacy of IIoT devices. Moreover, a noncooperative game is formulated on the top of FedGame, to enable MEC nodes acquiring the needed virtual resources from the centralized MEC orchestrator, to deal with each type of IIoT attacks. We evaluate FedGame using real-world IIoT attacks; the experimental results show not only the accuracy of FedGame against centralized ML/DL schemes while preserving the privacy of Industrial systems but also its efficiency in providing required MECs resources and, thus, dealing with IIoT attacks.

It is well established that 5G will impact not only the end-users by allowing several new services, but also the vertical industry and network operators business. 5G will open the business market to new stakeholders with the introduction of Network Slicing, namely the vertical or tenant, the network slice provider, and the infrastructure provider. The Network Slice provider sells end-to-end network slices (virtual end-to- end mobile network) to the vertical while leasing virtual and physical resources from Infrastructure Providers to enforce these end-to-end network slices. Accordingly, there is a need to establish Service Level Agreement (SLA) among these actors to ensure: (1) that the service is well-delivered to the vertical and (2) the infrastructure providers are respecting their involvement with the network slice provider. To fill this gap, in this paper, we propose a trust architecture to automatically manage the SLAs and apply penalties and compensations if the SLAs are not respected by one of the involved actors.

Multi-access Edge Computing (MEC) is one of the key enablers in 5G, where the objective is to bring computation very close to the end users. MEC, as defined by ETSI, introduces several services that can be exposed to MEC applications regarding the mobile users, such as the Radio Network Information Service (RNIS) and the Location Service, which provide low-level information on mobile users (e.g., Channel Quality Indicator - CQI), allowing the development of context-aware edge applications. In this paper, we address the challenging question of where to deploy a set of MEC applications on a federated edge infrastructure so as to meet the applications' requirements in terms of computing resources and latency, while ensuring that the MEC platform services required by each application are available at the selected edge locations. We formulate this service placement problem as an Integer Linear Program, which aims at balancing the computing load between available Mobile Edge Platforms (MEP), while respecting application latency and MEP service availability constraints. This problem is shown to be NP-hard. To solve it computationally efficiently, we propose an algorithm based on the Tabu-Search (TS) meta-heuristic. Via simulation, we demonstrate the efficiency of our scheme in balancing computational load among available MEPs and its ability to optimize service placement.

To achieve the vision of Zero Touch Management (ZSM) of network slices in 5G, it is important to monitor and predict the performances of the running network slices, or their Key Performance Indicator (KPI). KPIs are usually monitored, but also with the advance of Machine Learning (ML) techniques are predicted, aiming at proactively reacting to any service degradation of running network slices. While network- and computation-oriented KPIs can be easily monitored and predicted, service-oriented KPIs are difficult to obtain due to the privacy issue, as they disclose critical information on the performance of services. To tackle this issue, in this paper, we propose to use a new ML technique, known as Federated Learning (FL), which consists of keeping raw data where it is generated, while sending only users' local trained models to the centralized entity for aggregation. Hence, making FL as an adequate candidate to be used for predicting slices' service-oriented KPIs.

The 5th generation of the cellular mobile communication system (5G) is in the meantime stepwise being deployed in mobile carriers' infrastructure. Various standardization tracks as well as research activity are investigating the exploitation of the very flexible 5G system architecture for customized deployments, meeting requirements of the vertical industry, such as for automotive, factory, or smart city. A very common base is a cloud-native development and decentralized deployment of the 5G system along with services in distributed resources per the Multi-Access Edge Computing (MEC) architecture to locate services topologically close to (mobile) users, e.g. along public roads, and to enable low-latency communication with local services. Automated management of such a distributed deployment in an agile environment is a prerequisite. This paper investigates the use of Recurrent Neural Networks (RNN) for accurate user mobility prediction in an automotive scenario. By the use of simulated vehicular traffic, a suitable RNN configuration using Long Short-Term Memory (LSTM) has been found, which provides accurate prediction results. Proof of value has been accomplished by an experimental decision algorithm, which balances the use of available distributed resources through service scale, migration or replication decisions while meeting mobile users' expectation on the experienced service quality.

Vehicular cloud (VC) is a promising environment, where intelligent transport applications can be developed relying on mobile vehicles, which can be both cloud users and cloud service providers. It enables vehicles that have sufficient resources to act as mobile cloud servers by offering a variety of services to users' vehicles. In this context, to consume a cloud service on the move, a user vehicle must first identify the most stable vehicles, relative to his/her motion, which are able to provide the service, and then select the most suitable service according to his/her preferences, while both provider vehicles and their services are described by attributes or quality constraints. Therefore, we introduce a generic relative motion model, as a generic link stability metric, upon which vehicles can form a stable cloud, and we address the VC service selection by using linguistic quantifiers and fuzzy quantified propositions, to define our flexible quantified service selection (FQSS) scheme, which aggregates efficiently both user preferences and service constraints and ranks service providers from the most to the least satisfactory. To break ties among the top-ranked service providers, we make use of our parameters for ranking refinement, called least satisfactory proportion (lsp) and greatest satisfactory proportion (gsp). The simulation results show that our link stability achieves generic motion, by modeling a wider range of vehicle motion types, and our FQSS scheme allows a good successful service consumption rate while reducing latency.

Vehicular Cloud (VC) has gained popularity today allowing mobile users to access a variety of on demand resources while on the move using low cost Vehicular Network. VC enables vehicles with sufficient resources to act as mobile cloud servers and provide their computing, communication and caching resources to nearby vehicles. However, due to high mobility and intermittent connectivity, it is challenging for mobile users to efficiently discover providers' services before request targeted services from them. Therefore, service advertising is of great interest with which offered services by Provider Vehicles (PVs) in the vehicular cloud can be fast propagated into the network. Given PVs' limited budget for renting advertiser vehicles, how to achieve the maximum service advertising coverage within a given period of time for a given budget requirements is NP-hard. This work aims to propose a new Centrality-based approach, PUBLISH, for PVs' services advertising in the vehicular cloud. We exploit the centrality score of both services and vehicles to find the best set of 'appropriate' vehicles as services advertisers. Results from scalable simulations show that PUBLISH efficiently identify the best services advertisers in comparison to other schemes in the literature.

Industry 4.0 revolution aims to satisfy the manufacturing systems need to deal with the unexpected customers behaviour and market variation. Thanks to Internet of Things (IoT) technology, Industry 4.0 enables to collect and analyze real-time data about Cyber Physical System (CPS) components and hence to detect and react to emergent disruptive situations as quick as possible. In such context, tasks rescheduling becomes a crucial research topic, which aims to revise the initial schedule in cost-effective way. In this paper, we focus on system disruption related to resources unavailability of a resource, or when it is in an unexpected location. We propose a new tasks rescheduling module based on a reference schedule generated by an Initial Planning and Scheduling system (IPS). Our module considers the main schedule objective and aims to assign tasks to the nearest resources while improving the execution accuracy. To do so, we formulate an optimization problem of tasks rescheduling, before solving it using the meta-heuristic Tabu-search. The experimental results show the efficiency of our module to optimize the tasks rescheduling when considering both localization and accuracy information, in addition to the ability of Tabu-Search algorithm finding an optimal solution.

The proliferation of cloud-based applications in smart systems has made the cloud data center a vital and critical part for ensuring a connected world. Due to their energy-hungry servers and huge power facilities, cloud data centers tend to consume a lot of power. In fact, the data centers use about 1.4% of all the power generated on the planet. On one hand, this has a negative impact on the power grid and may cause blackouts. On the other hand, it has a negative impact on the environment and it is mainly involved in global warming. Thus, one of the most important challenges in cloud data centers is power consumption minimization. In this paper, we propose a microgrid-cloud based architecture and study the grid power dispatching problem to cloud data centers. At first, we model the power quantity demand between the data centers and smart microgrids as a non-cooperative game, due to their non-cooperative power demands behavior. Then, we try to allocate the optimal quantity of power to each data center according to its green power consumption, network bandwidth usage and its network equipment power usage. Second, we formulate the game payoff function as a non-linear optimization problem and solve it using Lagrange multipliers and KarushKuhnTucker (KKT) conditions. Finally, we compare the performance of our approach with two power allocation algorithms and showed that our game is more effective and reduces power load with a rate of 40.5%. Furthermore, our scheme incites data centers to use green energy and significantly reduces dioxide carbon emission.

Fog computing has becoming an attractive solution to face the low responsiveness existing in cloud-based networks. With the rapid emerging of Internet of Things (IoT), more and more terminal nodes are offloading their tasks to nearby fog nodes, located at the network edge, in order to reduce the processing delay. However, this tasks offloading requires an efficient scheduling mechanism that considers both user preferences and fog-cloud requirements. Existing research works for task scheduling in fog-cloud computing networks have mainly focused on reducing task delay and the overall energy consumption, without considering user preferences regarding the fog nodes' constraints. In this work, we present a ranking based task scheduling method that aggregates both user preferences and fog nodes features using linguistic and fuzzy quantified proposition to rank fog nodes from the most to the least satisfactory one. Moreover, we used two parameters called least satisfactory proportion (lsp) and greatest satisfactory proportion (gsp) in order to distinguish the similarities. Experimental results show that our approach satisfies the user preferences, and provides a compromising solution between the average user satisfaction, execution delay and energy consumption.

Occupants' thermal comfort assessment is becoming a crucial research topic since it aims not only at improving indoor thermal comfort but also to save energy in both commercial and residential buildings. Hence, it makes buildings more sustainable. Predicted Mean Vote (PMV) model is considered as the most recognized in thermal comfort standards and was widely used to estimate thermal sensation of occupants. However, few works are dealing with the assessment and control of occupants' thermal comfort in real time and most of them do not provide mechanisms to improve occupants' comfort in case of detecting indoor thermal discomfort. In this paper, we propose ThermCont a novel machine learning based tool to predict and control occupants' thermal comfort through the PMV model, in real time. Our tool uses multiple linear regression algorithm and is based on findings from a one-year longitudinal case study of occupants' thermal comfort in office building. Moreover, we also propose a new genetic algorithm based scheme to optimize parameters values of thermal comfort, when observing occupants' thermal discomfort, and hence to improve the indoor thermal comfort. The experimental results show the efficiency of ThermCont in terms of prediction accuracy and time complexity when compared to other machine learning algorithms, in addition to its ability to control and improve occupants' thermal comfort in real time.

Vehicular Cloud Computing (VCC) exploits resources at vehicles, such as computing, storage and internet connectivity to provide services for applications supporting different ITS (Intelligent Transportation System) services. Current Vehicular Cloud (VC) systems allow Consumer Vehicles (CVs) to discover and consume offered services by nearby mobile cloud servers (vehicles). However, to consume the required services, the CVs must first select the most suitable service provider, given that each of providers is characterized by specific features, limitations and prices. To the best of our knowledge, no work to date addresses the critical question of how to select the best provider fitting the quality of services and costs requirements of the consumer vehicles. Similarly, Provider Vehicles (PVs) should adjust the provided services' features and prices under certain conditions such as the rate of consumers' requests which makes this issue even harder. In this paper, we propose GSS-VC as a new distributed game theory-based approach to manage the service provisioning in vehicular cloud. Our approach takes into account the benefit of each player and allows the CVs to find the most suitable PV based on the probability interaction between them. Simulation results are carried out using urban mobility model and illustrate the effectiveness of the proposed approach to answer the raised questions: what is the best condition under which the CVs may request the PVs for services? and how to select the best service with respect to the CV preferences? Results from extensive simulations on up to 1, 500 vehicles show that GSS-VC is a an efficient and reliable service selection scheme while achieving high QoS.

Indoor thermal comfort monitoring is becoming a crucial research topic to improve not only the occupants' comfort but also the energy consumption, and thus the building sustainability. Existing works focus on real time thermal comfort assessment of people that are performing some activities and able to answer a questionnaire. However, few works deal with thermal comfort for people with physical disabilities which may have different thermal requirements from those without physical disability, due to the disability itself. Furthermore, the remote and constant monitoring amenities are not established yet, properly. To overcome this, Internet of Things (IoT) can be used, which would introduce more flexibility to monitor residential building of these population from anywhere. As a first step, we aim to provide remote availability of thermal comfort information from A.P.E.I buildings of Troyes city11A.P.E.I stands for Association des Parents d'Enfants Inadapts, is an association of parents of in-adapted children and people with physical disabilities., located in east of France, in order to enable remote monitoring and assessment of thermal comfort in these residential buildings. To do so, a complete IoT architecture is proposed. This architecture is based on sensor devices and permits to collect data, to be transferred and processed in the Cloud infrastructure for an adequate decision-making. Moreover, we optimize sensors deployment in addition to the data collection process while ensuring high data collection accuracy. Numerical results show the efficiency and the reliability of our schemes.

Internet of Things (IoT) is an emerging paradigm that aims at making objects in the world to be connected through Internet. IPv6 over Low-power Wireless Personal Area Networks (6LoWPAN) is considered as one of the common protocol stack suite for IoT applications. The 6LoWPAN network is implemented on the top of IEEE 802.15.4 standard in order to alleviate the challenges of connecting resource constrained objects to the Internet. In such a network, nodes are competing to send their sensed data as high as possible in a selfish way. However, high network data traffic degrades network performance and quality of service aspects, e.g., data sending rate, network latency and reliability and energy consumption. In this paper, we formulate the sending rate adjustments as a non-cooperative game where each node is modeled as a player in the game and demands high data sending rate in a selfish way. The basic idea of our scheme is to adjust the data sending rate according to the preferences of nodes to send high data rate, the quality of data in terms of similarity and nodes priorities in the targeted IoT application. We then prove the existence and uniqueness of Nash equilibrium before computing the optimal sending rate using Lagrange multipliers and KarushKuhnTucker (KKT) conditions. We called our game-based scheme ThingsGame. We validate and evaluate ThingsGame scheme in the IoT operating system Contiki OS using Cooja simulator. Simulation results show that ThingsGame improves significantly network performance in terms of overall throughput, energy consumption, number of lost packets, as compared to the Selfish way scheme.

The emergence of smart systems based on Internet of Things (IoT) and new technologies has led to use more cloud computing services. This incentivizes to build more geographically distributed data centers. However, the data centers consume a tremendous amount of electricity which significantly increases load on power grid. There are broad concerns about the impact that this huge consumption may cause to the power grid. Moreover, the data centers are competing to get the maximum of power from the smart grid in a selfish way, which also has a negative impact on both the smart grid and the other data centers. In this paper, we model the power allocation problem between the smart grid and cloud data centers as a non-cooperative game. The basic idea of our approach is to determine the optimal quantity of power that will be assigned to each data center, in order to have a fair power allocation. To do so, we consider the data center priority in terms of number of active servers, state of energy charge and number of running critical applications. Moreover, we prove the existence and uniqueness of Nash equilibrium, and compute the optimal quantity of power using Lagrange multipliers and KarushKuhnTucker (KKT) conditions. Simulation results confirm the effectiveness of the proposed approach, and show that our scheme can reduce the load on the power grid up to 80%.

Vehicular Cloud (VC) is an emerging paradigm where vehicles having sufficient resources act as mobile cloud servers by offering a variety of services to user vehicles. To consume a cloud service on the move, a user vehicle must first identify the most stable vehicles, relatively to its motion, capable of providing the service, then select the most suitable service according to its preferences and service provider quality or constraints. In this paper, we introduce a link stability metric based on a generic relative motion model among vehicles to form a stable cloud and address vehicular cloud service selection by using linguistic quantifiers and fuzzy quantified propositions aggregating efficiently both user preferences and service constraints to rank service providers from the most to the least satisfactory. To break ties, we also define new parameters, called least satisfactory proportion (lsp) and greatest satisfactory proportion (gsp). Simulation results show that the link stability achieves generic motion and the selection approach allows a good successful service consumption rate while reducing latency.

Vehicular Cloud (VC) is a new concept which enables vehicles to offer and rent out their advanced on-board resources to other vehicles. So, individual vehicles can be both service providers and cloud users. Vehicles users need to discover vehicles' services and request targeted services from them. To achieve this, a cloud directory must be used in which provider vehicles register their services and from which vehicle users discover offered services in order to consume them. In a previous work [1], we have designed a new protocol in VC, named Discovering and Consuming Cloud Services in Vehicular Cloud (DCCS-VC). Due to their predictability of time and space in urban scenarios, DCCS-VC was based on public buses as a cloud directory in order to form a dynamic index of provider vehicles. However, DCCS-VC provides a low efficiency of both registration and discovering operations, given the introduced high waiting time of vehicles to perform these operations. In this paper, we extend our previous protocol to minimize the provider and user vehicles' waiting time. To do so, we allow vehicles to exploit the providing real time bus information in order to discover existing public buses in the vicinity. In addition, we introduce an optimization technique which enables provider vehicles to select the most adequate public bus as a service registration node. We illustrate the superiority of this enhancement throughout the results obtained from simulation experiments, using an urban mobility model.

Abstract An important application in wireless networks is data collection. It aims to gather and deliver specific data for concerned authorities. Many researchers invest in vehicular ad hoc networks for that purpose to acquire data from different sources on the roads as from its vicinity. A vehicle is considered as a mobile data collector, it gathers real‐time or delay‐tolerant data such as road traffic, environmental information, and event advertisements. In a previous work, we have proposed a novel clustered data gathering protocol (CDGP) for vehicular ad hoc network, which improves the collection performance by implementing a new space division multiple access technique called dynamic space division multiple access and a retransmission mechanism in case of errors. However, CDGP supports only delay‐tolerant data as it does not use any aggregation technique. In this paper, we propose an enhancement of this protocol by extending it to support: (i) both real‐time and delay‐tolerant applications; (ii) multiple types of data; and (iii) aggregation of collected data prior to sending them to the initiator. We present the plausible analytical complexity of the extended CDGP, as we illustrate the superiority of its performance throughout the results obtained from simulation experiments, using a Freeway mobility model. Copyright © 2015 John Wiley & Sons, Ltd.

The advanced on-board vehicles' resources have given birth to the Vehicular Cloud (VC) concept. The VC is an emerging paradigm where individual mobile vehicles can be both cloud users and service providers, it enables vehicles that have sufficient resources to act as mobile cloud servers and rent out them to other vehicles. However, and with the high mobility of vehicles, user vehicles need to discover vehicle providers, know their services, and request targeted services from them. In this paper, we propose a new protocol that enables user vehicles to discover and rent providers' services in VANet using public buses. Due to the predictability of time and space of these buses in urban scenarios, our protocol use them as cloud directories with which provider vehicles register and from which user vehicles discover all offered services. Hence, they hold a dynamic index of services' providers. We demonstrate the efficiency of our protocol, in terms of service discovery and consuming delays, by conducting an extensive set of simulation experiments using OMNet++ network simulator.

By adopting different detection technologies, vehicles in Vehicular Ad-hoc Networks (VANets) are able to collect various kinds of information, like road traffic and environmental information, then, to transmit them to interested entities. Data collection in VANets is considered as an interesting application which aims at providing a safer, more efficient and more comfortable driving. In a previous study [8] we have proposed a Robust Clustered Data Gathering Protocol (CDGP), by using a Dynamic Space Division Multiple Access (D-SDMA) technique with a retransmission mechanism. However, CDGP provides a low collection efficiency given the large number of unused slots, which are wasted in a vehicle-to-vehicle communication (V2V). In this paper, we propose a new data collection protocol, which improves the data collection efficiency by using an enhanced Dynamic SDMA technique. Through simulation results we show that our new protocol enhances data collection efficiency and provides a reliable data collection.