Attention tracking in education can serve as a valuable tool for both students and teachers, particularly in the context of online learning. The objectives of our study were to establish the feasibility of developing a non-medical and low-cost dry-EEG neurofeedback system for the general public, usable in everyday life, out of the laboratory, with no need for further expert neurophysiological assistance, in order primarily to monitor and secondarily to optimize the attention levels of university students while watching e-learning videos. A neuromarker for attention was successfully determined using wearable electroencephalography (EEG) in real-life conditions. Assessing the pedagogical benefits of two types of multimodal neurofeedback, either personalized (for each student based on their individual attention level) or aggregate (identical for all students based on a previous cohort’s average attention level), we demonstrated that personalized neurofeedback significantly increased students’ attention levels following an attention drop. On the contrary, the aggregate neurofeedback yielded no positive impact on attention and was perceived as disruptive. This study underlines the feasibility and benefits of providing personalized feedback tailored to individual students during online learning in everyday life conditions, outside of the laboratory.

The evolution of Distributed Denial-of-Service (DDoS) attack techniques on the Internet of Things (IoT) domain presents ongoing challenges as attackers increasingly emulate legitimate traffic patterns. This necessitates the continual adaptation of deep learning-based anomaly detection systems. Furthermore, the high cost of recurrently retraining deep learning models from scratch highlights the demand for adaptive detection approaches that can respond effectively to shifting threats in IoT environments. This paper investigates a range of Federated Continual Learning (FCL) techniques for identifying DDoS attacks within IoT systems, utilizing diverse federated learning approaches such as Prioritized Experience Replay (PER), Learning Without Forgetting (LWF), and Clustered Federated Learning (CFL). Continuous learning techniques, including Elastic Weight Consolidation (EWC), Agnostic Model Update (AMU), and Federated Proximal (FedProx), are also applied. The effectiveness of these methods is assessed across configurations with 16, 32, and 64 clients. Results indicate that LWF performed optimally in smaller client configurations, especially with FedAvg and FedProx, while EWC was more effective in larger setups. FedAvg and FedProx were consistently reliable strategies, whereas AMU and CFL demonstrated variable performance. This study highlights the critical role of advanced machine learning techniques in enabling real-time DDoS detection for IoT applications.

In this paper, we propose a federated continual learning-based IoT system for real-time monitoring of surface water quality, named FCL-IWQMS. This system improves surface water monitoring management by integrating sensor networks and predictive analytics, addressing the challenges of climate change and urbanization. FCL-IWQMS enables collaboration by allowing Internet of Things (IoT) devices to send only updates from their local models to a central server, consolidating them to generate an improved prediction model. This approach ensures data privacy while enhancing the accuracy of water quality predictions. The framework utilizes methods such as Prioritized Experience Replay (PER), Learning Without Forgetting (LWF), and Elastic Weight Consolidation (EWC) to refine local models in response to new data. Local updates are periodically sent to aggregation nodes, where techniques like Federated Averaging (FedAvg), Federated Trimmed Mean (FedTM), and Agnostic Model Update (AMU) are applied to consolidate updates. Evaluations with 40 clients using publicly available datasets show that the FedAvg-PER model outperforms others in predicting dissolved oxygen (DO). At the same time, AMU-LWF excels in pH predictions, and FedTM-PER leads in electrical conductivity (EC).

Assuring the trustworthiness of AI-based systems, especially in video surveillance, is critical in smart cities today. Large Language Models have emerged as the strongest tool for analyzing videos by offering human-readable descriptions of complex scenes. However, their effectiveness in sensitive tasks like abnormal behavior detection depends heavily on trust and system reliability. This paper proposes a new approach for enhancing trustworthiness in LLMs using a QoE-based framework. We propose a system that couples these Vid-LLMs with a real-time feedback loop, which incorporates both user corrections and validations to improve accuracy and user trust. We show how such a system can be trained and evaluated using the UCA Crime database and demonstrate that it is able to describe abnormal events in a highly reliable way. Our results indicate that the QoE-based trust model significantly improves user satisfaction, serving as a valued approach in real-world surveillance applications or other similar use cases.

The emergence of 6G technology is set to revolutionize connected autonomous vehicles (CAVs) by enabling hyper-connectivity, ultra-reliable low-latency communication, and seamless integration with IoT systems. These advancements enhance CAV efficiency, intelligence, and real-time data exchange for safer navigation and decision-making. However, the interconnected nature of 6G-enabled CAVs introduces significant cybersecurity risks, including adversarial AI attacks and large-scale intrusions. Traditional security methods are inadequate for addressing the complexity and sophistication of emerging threats in this dynamic ecosystem. This article aims to address these critical challenges by proposing an innovative security framework tailored for 6G-enabled CAVs. By integrating blockchain technology, reinforcement learning, and collaborative intrusion detection systems, this framework aims to secure CAV communications against malicious intrusions and ensure the reliability of their AI-driven operations. The system was evaluated on a dataset containing 2D image representations of normal and malicious network traffic. The ensemble-based IDS demonstrated high detection accuracy (99%) with low false positive rates. The Q-learning agent effectively supported trust-based consensus by reliably selecting validators and isolating malicious nodes. The blockchain layer maintained stable validation and propagation times, confirming the framework’s scalability and low-latency performance.

The advent of 6G technology has paved the way for unprecedented advancements in the Internet of Things (IoT), ushering in an era of hyper-connectivity and ubiquitous communication. However, with the proliferation of interconnected devices in 6G-enabled IoT ecosystems, the risk of malicious intrusions and new cyber threats becomes more prominent. Furthermore, the incorporation of AI into 6G networks introduces additional security concerns, such as the risk of adversarial attacks on AI models and the potential misuse of AI for cyber threats. Consequently, securing the extensive and diverse array of connected devices poses a substantial challenge in the 6G environment and needs reconsideration of prior security traditional methods. This paper aims to address these challenges by proposing a novel collaborative intrusion detection system (CIDS) that relies on AI and blockchain technologies. The collaborative nature of the proposed CIDS fosters a collective defense approach, where nodes within the IoT network actively share threat intelligence, enabling rapid response and mitigation. The effectiveness of the proposed system is evaluated through comprehensive simulations and proof-of-concept experiments. The results demonstrate the system’s ability to effectively detect and mitigate falsified and zero-day attacks, thereby fortifying the security infrastructure of 6G -enabled IoT environments.

In the realm of IoT platforms, susceptibility to cyber-attacks is a pressing concern, necessitating the deployment of Intrusion Detection Systems (IDS). Constructing a scalable, accurate, and lightweight model without compromising data privacy poses a formidable challenge. This study assesses classical and novel approaches employing federated learning (FL) to train IDS models. Optimization through Knowledge Distillation (KD) techniques aims to enhance computational efficiency. Experimental results reveal the efficacy of federated learning, achieving an 84.5% accuracy for 15 attack types, and an impressive performance for binary network attack classification. Notably, these models exhibit shorter inference times compared to cutting-edge machine learning models trained on the Edge-IIoTset dataset, offering promising advancements in IoT security.

In the past decades, the use of urban rivers for recreational and sporting activities has gained increasing interest. However, bathing in urban surface waters is not without health risks due to short-term pollution of fecal origin, which may have an important impact on the overall population health within a region where bathing in water streams is possible. Therefore, EU member states are required to lower the contamination risk of such areas through active water quality management, as defined by the Bathing Water directory (BWD, 2006/7/EC). This paper develops and evaluates a cost-effective IoT-based water quality monitoring system, based on low-cost water quality sensors coupled with machine-learning approaches. By monitoring spatiotemporal dynamics of several physical and chemical parameters correlated with bacterial indicators, managers can more easily decide if the water quality of a bathing site is enough for usage. To determine the water suitability at particular river sites, the system employs a convolutional neural network (CNN) deep learning classifier, integrating federated learning (FL) with knowledge distillation (FedKD) to streamline model architecture, reduce communication costs, and preserve data privacy. The system is tested on the Seine and the Marne rivers (Paris area, France) and results demonstrate that FedKD outperforms centralized knowledge distillation (KD) and FL algorithms such as FedAvg and UFedAVG. Using the current features, it achieves a satisfactory average accuracy of 90.74% at Marne station.

Recently, the integration of Network Function Virtualization (NFV) with the blockchain has been gaining a lot of attention. This combination aims to avoid traditional NFV issues such as trust, payment, and security. Several works have been proposed to orchestrate, buy, execute, and manage the life cycle of a Virtual Network Function (VNF). Thus, they came as NFV marketplaces and orchestration platforms. In this paper, we provide a novel secure End-to-End NFV marketplace called “VNFO-DCSC”, that uses dynamic composite smart contracts. This platform provides full orchestration, management, execution, and monitoring of VNFs in a secure way. “VNFO-DCSC” is implemented following the European Telecommunications Standards Institute (ETSI) standards [1] for NFV management and it is available on GitHub.

In the multimedia field, the quality of experience (QoE) is rightfully seen as the center metric in research, around which each piece of the network is designed, especially for next-generation networks. Even if an increasing number of models using various data as inputs are now available, some major problems remain, such as the implementation of quality of experience measurement for real-time applications. The 'Human Factors' are the primary reason for the impossibility to correctly predict the QoE for real-time applications since these factors can't be measured easily and swiftly. For this reason, we present in this paper a Multi-Task model to predict multiple QoE influence factors at once from physiological data to save time in the training process and during the prediction. To test the model, we use a publicly available dataset named SoPMD, which contains recordings from an electroencephalogram (EEG), an electrocardiogram (ECG), and respiratory signals obtained during a quality assessment experiment, where QoE factors are gathered as labels. Our Multi-Task model has been tested using different features extracted from EEG and presents results up to 68.51% in accuracy. This model could be used in a real-time regulation loop to predict QoE factors faster than single-task models, for an enhanced QoE prediction, as this model can predict the five factors at the same time.

Server and route selection (SARS) optimization is a critical aspect of traffic engineering to allocate network resources to meet diverse service requirements effectively. Existing studies have primarily focused on finding profitable or optimal solutions for the SARS problem within current time steps, considering specific constraints. However, they often have failed to address the dynamic and uncertainty of future network states. To address this gap, this paper proposes an algorithm named GAL to optimize server costs and response time while accounting for future network dynamics. GAL combines a server selection inspired by the gambling theory and a network routing based on Long Short-Term Memory Networks (LSTM). The server selection method is formulated as a gambling problem and solved using the decision-making Tug-of-War (TOW) dynamic algorithm. The routing mechanism is optimized based on predictions of future network states made by LSTM neural networks, which excel in capturing long-term dependencies. We have implemented GAL through a distributed software-defined networking (SDN) system and obtained good evaluation results regarding average response time and server cost compared to benchmark methods. These results demonstrate that GAL can effectively tackle the SARS optimization problem by considering present constraints and future network dynamics. This study can advance traffic engineering and lays a foundation for more robust resource allocation strategies in dynamic network environments.

Software-defined networking (SDN) is a novel net-working paradigm for network management and autonomous systems. However, SDN has some challenges with scalability and quality of services (QoS) in distributed multi-domain scenarios due to the unprecedented growth of heterogeneous characteristics services. There is a current gap in a standard routing mechanism for satisfying various service requirements in distributed SDN. Most existing works design a homogeneous routing strategy for heterogeneous services, which might need to be more scalable and efficient for the future of rising heterogeneous online services. This study proposes a multi service-oriented routing mechanism for multi-domain SDN, which aims to help Internet service providers (ISPs) achieve high QoS and service-level agreements (SLAs). The mechanism utilizes a service classification (through a deep learning model) and optimizes network routing (using a new cost function containing both QoS and the server load). The mechanism has been integrated into the Knowledge-defined heterogeneous network architecture and tested on four prevalent considered services: E-commerce, Interactive Data, Video On-demand, and Bulk Data Transfer. The experimental results indicate that the proposed service-oriented routing mechanism outperforms the benchmark in terms of faster server response time while reducing up to 25% of the network congestion.

In the past, Quality of Service (QoS) was taken into account to evaluate the performance of multimedia services (e.g., video streaming, file transfer, etc.). However, it cannot reflect the user's perception, which is considered a crucial consideration by these services nowadays. Therefore, the emergence of Quality of Experience (QoE) is a potential solution. QoE can be measured via many parameters provided by Internet Service Providers (ISP), Application Service Providers (ASP), or end-users. However, privacy concerns hinder data sharing between the parties involved. To address these limitations, this paper proposes a QoE estimation mechanism that leverages Federated Learning. This mechanism aims to guarantee data privacy when no party needs to disclose their data to others. Moreover, the proposed mechanism incorporates the concept of a Decentralized Autonomous Organization (DAO) to mitigate the risk of a single point of failure in the centralized architecture of Federated Learning. It enables all participants to evaluate and select the model efficiently. The experimental results illustrate that the proposal surpasses the centralized solutions and guarantees data privacy.

Multipath scheduling has been a hot research topic in recent years thanks to the development of multipath transport protocols (MP-TCP and MP-QUIC) and the wide deployment of 5G infrastructures. These schedulers take advantage of multiple physical interfaces on end-user devices, thus improving performance and reliability. While Peekaboo, the state-of-the-art scheduler, seems to provide the best performance in some specific environments, some evidence is that other existing schedulers may outperform it in more realistic network conditions. Based on this observation, we proposed GADaM, stands for Generic Adaptive Deep-learning based Multipath scheduler selector. GADaM’s role is to select the most appropriate scheduler under specific network conditions dynamically. The proposed paradigm proved its effectiveness in simulations, but its behavior in more realistic (typically mobile) environments remains largely unknown. This paper presents an experimental evaluation of GaDAM in real-world scenarios performed in an urban area near Paris, France. We design and implement a framework to serve this purpose, which takes mobility and fairness into consideration. Our results confirm the advantage of GaDAM’s approach compared to the deterministic scheduler selection approach.

The communication at millimeter wave (mmWave) offers a very promising future for vehicular network in beyond fifth generation (B5G), where the high-throughput data exchange is required. However, due to the high mobility and channel attenuation in vehicular environment, it becomes more challenging to establish an efficient mmWave Vehicle-To-Everything (V2X) communication. To overcome the beam misalignment problem, it is necessary to employ fast and reliable beamforming methods at the transmitter and receiver sides to align the beams reliably and continuously. In this paper, we propose a new deep learning approach based on beam alignment that suggests a bidirectional long short term memory (BiLSTM) model followed by a fully connected layer, to predict the suitable beam pair in real time, i.e., the Angle of Departure (AoD) at the mmWave base station side and Angle of Arrival (AoA) at vehicle side (AoD/AoA) for which the received signal power is maximized. The BiLSTM-BPP is performed to identify automatically the strongest beam pair that connects the mmBS to the vehicle for each vehicle position. After a set of simulations, the obtained results showed that BiLSTM-BPP achieves the lowest beam prediction error between the predicted and the real AoD/AoA compared to existing traditional machine learning algorithms, including linear regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), decision tree, random forest. We evaluated the performance of our proposal in terms of Mean Squared Error (MSE), Mean Absolute Error (MAE), Median Absolute Error (MedAE) and Root Mean-Square-Error (RMSE).

An important source of information for ensuring public safety is control room video surveillance. A Decision-Support System (DSS) designed for the security task force is vital and necessary to take decisions rapidly using a sea of information. In case of mission-critical operation, Situational Awareness (SA) which consists of being aware of what is going on around you in real time plays a crucial role across a variety of industries and should be placed at the center of our system. In this paper, in order to satisfy the understanding and projection levels of SA in real time, we propose a method based on Reinforcement Learning (RL) using an Actor-Critic algorithm. This algorithm permits our DSS to first, keep SA knowledge up to date by performing online adaptive learning and second, develop a long-term vision and strategy by exploiting a non-myopic agent for real-time sequential decision-making. In contrast to other approaches, our results permit demonstrating the practical potential of our method in real-world scenarios by preventing abnormal situations in an ever-changing environment.

Multipath QUIC (MQ-QUIC) and Multipath TCP (MP-TCP), known as multipath protocols, introduced several certain advantages for the next internet generation, such as enabling bandwidth aggregation of links, preventing single-path failure, increasing Quality of Service (QoS), etc. Meanwhile, the pivotal point of the transport protocols is the scheduler. Various multipath schedulers have been proposed, and each of them usually outperforms the others in each specific scenario. To provide a generic approach with the best performance and stability, a novel one is introduced in this paper and aimed to fill this research gap. Indeed, the proposed GADaM prototype is a Generic Adaptive Deep-learning-based Multipath Scheduler Selector. The idea’s prototype is implemented for the MP-QUIC protocol. The extensive results show that our scheduler selector achieved over 95% accuracy on training and 91% accuracy on the testing set in the simulated environment.

International audience

Service Overlay Network (SON) is an efficient solution for ensuring the end-to-end Quality of Service (QoS) in different real-world applications, including Video-on-Demand, Voice over IP, and other value-added Internet-based services. Although SON offers many advantages, such as ease of deployment and resilience to the node failures, it has to face the challenge of overlay network configuration that needs to dynamically adjust to the change in communication requirements. In this paper, we propose a novel method for adaptive overlay topology configuration, called AOTC based on Software-Defined Networks, deep learning, and reinforcement learning. The intuitive motivation is to address the above challenge, maximize the QoS from two aspects of customer preference and network cost. The obtained experimental results demonstrate the superiority of AOTC. Such a method can significantly reduce network cost while providing an improvement of 50% and 60% in terms of average delay and packet loss rate as compared to other traditional approaches.

Nowadays, the rapid growth of the Internet makes network management more complex due to various and com-plicated network problems. In the past, network administrators implemented troubleshooting approaches (e.g., ping, traceroute, etc.) manually to identify the root cause of problems. However, it is not effective due to human intervention and an increase of network devices. Consequently, the root cause analysis is considered by the research community. There are existing studies for the root cause analysis without human intervention (e.g., statistical approaches, heuristic algorithms, etc.). However, these approaches show limited performance (e.g., due to complex threshold identifcation, etc.). The emerging of machine learning (ML) and deep learning is a potential solution to overcome this obstacle, offering an opportunity to develop an effective root cause analysis approach. Therefore, in this paper, we propose a root cause analysis approach using ML and time-series network parameters to identify the root cause of problems in the network. In this approach, we consider balancing the accuracy and the time complexity of ML algorithms to select an appropriate ML technique. Moreover, we contribute troubleshooting datasets to identify three kinds of root causes including link failure, switch failure and buffer overload. The experimental results show that the proposal can achieve approximately 97 percent of precision, recall and f1-score in considered scenarios and require less processing time (only require 0.00143 ms for a sample) in comparison with other ML algorithms.

Despite the huge development in the fifth generation (5G) vehicular networks, the data transmission is still suffering from the signal attenuation, especially when vehicles move. It is due to the limited 5G connectivity range where the frequency waves, named mmWaves, are only able to cross a short distance and are interrupted by physical obstacles like buildings, trees, and walls. These obstacles can obstruct, disrupt or absorb a part of the transmitted signal. To overcome this drawback, various beam management approaches were proposed in the literature to find the best transmission beam that increases the performance of 5G vehicular networks. In this paper, we propose a new simulated annealing algorithm that adjusts dynamically the direction of the beam according to the connected vehicle positioning, where the mmWave base station selects for each vehicle position the optimal angle that maximizes the Signal-to-Interference-plus-Noise Ratio (SINR) of the received signal. The results obtained showed the effectiveness of this proposal to establish an efficient communication between the mmWave BS and the connected vehicle compared to conventional method.

Traffic Matrix (TM) clearly describes the volume and the distribution of traffic flows inside a network. TM plays an important role in many network management fields, such as traffic accounting, short-time traffic scheduling or re-routing, network design, anomaly detection, etc. Hence, an accurate TM prediction strategy is essential to handle those tasks effectively. Fortunately, Artificial Intelligence (AI) has been developing very strongly, thanks to computer technology developments such as GPU and TPU. That offers an opportunity to apply AI to TM prediction methods. However, applying Machine Learning techniques in traditional networks encounters some issues due to the distributed control and restricted local view of network nodes. For this purpose, a centralized control architecture, e.g., Software-defined Network (SDN), is a promising candidate. In this paper, we apply Long Short-Term Memory (LSTM) and its two variants, Bidirectional LSTM (BiLSTM) and Gate Recurrent Unit (GRU), for TM prediction mechanisms of an SDN architecture network. The prediction models have been evaluated using two datasets: the popular GÉANT backbone network traffic data and our dataset generated through a testbed. The experimental results show that our approach yielded promising traffic prediction accuracy.

Arbitrary point-to-point (P2P) routing is becoming a necessity in a multitude of Internet-of-Things (IoT) applications, including building automation, smart cities, and smart manufacturing. For this reason, new P2P routing protocols such as lightweight on-demand ad hoc distance-vector routing protocol next generation (LOADng) and ad hoc on-demand distance vector routing-based RPL protocol (AODV-RPL) are being standardized. Both protocols are inspired by AODV, and hence, they might suffer from broadcast storms caused by flooding route requests (RREQs) and related issues. Thus, while AODV-RPL takes advantage of RPL mechanisms, LOADng uses blind flooding to forward RREQs. However, both lack effective techniques for avoiding unnecessary RREQ transmissions when routes are found. In this article, we first deploy stopping Trickle timers to ensure scalable, efficient, and reliable dissemination of RREQs. Second, we devise and present new techniques to suppress unnecessary RREQs with optimizations for radio duty-cycled networks. Finally, the two mechanisms are combined in a third proposal for better efficiency. These mechanisms provide individually and collectively great enhancements to P2P routing protocols, such as AODV-RPL and LOADng, while staying backward compatible with their base specifications. The performance of the proposed mechanisms when applied to LOADng has been validated using both extensive time-accurate simulations and large-scale public testbeds. The obtained results have shown the effectiveness of the proposed mechanisms with around 50% less overhead and savings in energy consumption, along with a 20% gain in route discovery ratio at the expense of an increase in discovery delays.

For the past decade, IP (Internet Protocol) routing approaches utilize TCAM (Ternary Content Addressable Memory) for the rule matching in the switches. These approaches are expensive and require more power consumption. Fortunately, the emerging of segment routing can resolve this drawback by encoding a routing path into the packet header to forward the packets to a destination. However, the standard segment routing algorithm has encountered a main problem. Using the shortest path to forward the packets can lead to a high traffic load on these paths and a performance reduction. It results in a decrease in user's perception and some negative economic impacts for ISPs (Internet Service Providers). Therefore, in this paper, we propose a novel service-centric segment routing mechanism using reinforcement learning in the context of encrypted traffic. Our proposal aims to help ISPs to decrease the influence of the network problems and meet the strict user's requirement related to QoE (Quality of Experience). The obtained results under the considered conditions demonstrate that our approach out-performs the standard segment routing algorithm and requires reasonable computational cost.

These days, the most current disruptive trend in the auto industry is not “electric engines” but specifically the data collection engine that many cars will be equipped with in the future. One of the most glamorous areas that present many challenges as we progress is transport data sources. As we know, data becomes more useful the more it's used, which is the exact opposite of what happens with the Basic Safety Messages (BSM) exist only temporarily, used locally and are never stored. However, this frequently generated data by connected vehicles can play a primordial role in providing transport data see credible and reliable information they contain. In this paper, we propose a data reuse model that retains collected BSMs, stores and processes them inside the vehicle to provide a continuous data source containing stored snapshots for every stretch of roadway. These continuous data could be sent to roadside DSRC units, streamed over digital cellular, Wi-Fi, or through a combination of all to provide broad-scale applications with needed information. The main novelty of our reusing model is its contribution to change the way BSM is treated, making it more valued, resulting in a reliable and useful data source. Moreover, given that our model relies on In-Vehicle Computing (IVC) paradigm, its strongest potential is, therefore, its capability of facilitates data processing at or near the source of data generation while optimizing bandwidth and reducing latency to rapidly provide data of value to drivers, pedestrians and transportation agencies.

In the context of large-scale Internet of Things (IoT), one of the main issues comes from the lack of an efficient routing protocol that could handle thousands of devices and provide a low-power forwarding mechanism for huge amounts of data. Furthermore, this routing protocol should cope with the intrinsic device-to-device communications paradigm of IoT, where nodes no longer need an intermediate station for communication and synchronizing, in order to exploit all options to deliver a better quality of service (QoS) for the network. Although many solutions have been proposed to meet QoS requirements for various applications based on IoT, they usually do not provide significant increase on a network performance when the number of nodes becomes too large. Therefore, in this work, we provide a new modelling paradigm, organized on a two-level control mechanism, to overcome this problem. For the first level, we propose a new Routing Protocol for Low-Power and Lossy Networks (RPL) approach based on multi-hop clustering technique (MHC-RPL). It is used as a local control to organize nodes in clusters, in order to reduce energy consumption in the IoT. The second level uses Software Defined Networking (SDN) with Q-routing algorithm for intelligent management of the global network. Our results show that the proposed model provides significant better results in terms of end-to-end delay, packet delivery ratio and energy-consumption than current state-of-the-art.

Recently, autonomous vehicles navigation (AVN) attracted many researches trying to improve road traffic without the human intervention. One of the main challenges in AVN is allowing a vehicle to discover its moving trajectory with a reduced computational complexity. To cope with this issue, we propose in this paper a new simulated annealing algorithm to discover an optimal trajectory when the vehicle encounters an obstacle using LiDAR perception. The found trajectory is then sent to a roadside unit (RSU), which communicates this discovery to other nodes in the network for further use. During its navigation, the vehicle perceives the environment by a LiDAR sensor to detect an eventual obstacle and launches an optimal path discovery to reach the final destination in a reduced time. The results obtained showed the effectiveness of our proposal to find an optimal route compared to Dijkstra algorithm.

Unmanned Aerial Ad-hoc Networks (UAANETs) pushed up UAVs' cooperative tasks. For efficient cooperation, a fitting mobility pattern must be adopted, ensuring simple, flexible, and easy-manageable coordination. Indeed, UAANET faces an inescapable challenge due to the limited energy constraint, which significantly affects the tasks' productivity and efficiency. Different from the literature, which only studied the impact of two classical factors affecting energy consumption, namely, communication protocols and computation, we highlight the impact of the temporal and spatial correlation involved in mobility models. Indeed, we consider a transitive relationship taking place between temporal and spatial correlation and energy consumption. Those correlation forms do affect the data loss ratio that, in turn, augments energy consumption due to the increased rate of data re-transmission, route re-discovery and maintenance, etc. On this basis, we assume the temporal and spatial correlation impact on energy consumption, which has been demonstrated and analyzed through numerical simulations.

This paper addresses the knowledge dissemination problem in distributed SDN control by proposing an adaptive and continuous consistency model for the distributed SDN controllers in large-scale deployments. We put forward a scalable and intelligent replication strategy following Quorum-replicated consistency: It uses the read and write Quorum parameters as adjustable control knobs for a fine-grained consistency level tuning. The main purpose is to find, at runtime, appropriate partial Quorum configurations that achieve, under changing network and workload conditions, balanced trade-offs between the application's continuous performance and consistency requirements. Our approach was implemented for a CDN-like application that we designed on top of the ONOS controllers. When compared to ONOS's static consistency model, our model proved efficient in minimizing the application's inter-controller overhead while satisfying the SLA-style application requirements.

In the coming years, the development of the Internet of Things (IoT) will have relevance for transport, environment, health care, smart cities and also multimedia services (Multimedia Internet of Things (MIoT)). Nowadays, many ISP (Internet Service Provider) encrypt the data to make it secure during the transmission. However, it imposes some obstacles for the NSP (Network Service Provider) because of the lack of visibility for operators into network traffic. To resolve these issues, we proposed the Quality Estimation Framework for Encrypted Traffic (Q2ET) containing a classification module and a QoE assessment module. The first module inherited from our previous research works to classify the encrypted network traffic using CNN (Convolutional Neural Network). The second one applies the objective and subjective methods based on the statistical analysis and machine learning methods that combine application and network parameters to calculate user's QoE (Quality of Experience) in terms of MOS (Mean Opinion Score). The Q2ET allows the NSP to monitor the user's QoE to take the appropriate decisions when the QoE degradation happens in the network systems.

Communication security in Cluster-Based Wireless Sensor Network (CWSN) is considered as a challenging task facing this type of network. The dynamic nature of CWSN and its deployment in open areas making these networks vulnerable to different kinds of cyber-attacks that can adversely affect its own functioning. Moreover, the resource-constrained nature of sensor devices make it impractical to apply conventional security schemes in CWSN, which require high overhead of computation, communication and memory storage. To deal with this issue of communication security, we propose an efficient secure protocol in CWSN called IDentity-based Security Protocol (IDSP), which guarantees secure communication between Cluster Head (CH) and Base Station (BS), as well as communication between CH and Sensor Node (SN). IDSP is based on Identity-Based Cryptography (IBC) that doesn't require Public Key Infrastructure (PKI) or complicated certificate management. The cornerstone of our protocol is to provide a perfect trade-off between three key factors: (i) ensuring a good protection level, especially against various cyber-attacks that may target CWSN, (ii) proposing an efficient process regarding energy consumption and key storage, (iii) introducing a key exchange mechanism in IDSP which is lightweight and uncomplicated. Moreover, our protocol treats public key authentication problem. The proposed protocol is tested in Cooja network simulator with WiSMote platform, and the performance results showed that IDSP is efficient, lightweight and secure.

Device-to-Device (D2D) communications is a convenient technology for future cellular network. This type of communication helps offload network core and increases overall throughput. Among the many challenges facing D2D communication, we are interested in interference management. In order to decrease interferences and improve network throughput, we need to optimize resource allocation and power control for D2D communication. Therefore, we propose in this paper a new Bees Life Algorithm (BLA). This algorithm is considered as a bioinspired approach to optimize channel allocation and power control. BLA is responsible for finding the optimal solution via a diversified global search among all possible solutions. The purpose of all this is to escape a stagnation on local optimal by applying a biological process inspired by the bees' marriage behavior. Additionally, BLA performs an intensified local search to get the optimal solution. We consider a cellular network with a set of users, cellular users and D2D pairs that share resource blocks. A minimum signal to interference plus noise ratio (SINR) is considered for cellular users, and there is no limit to the number of D2D pairs that share the same resource block. The experimental study showed that BLA provides good results in terms of overall throughput after comparison against two other bio-inspired approaches namely Particle Swarm Optimization (PSO) and Genetic Algorithm (GA).

During recent years, a body area network is becoming an important tool to improve the healthcare by monitoring patient's health state at distance, at home, in work, or when traveling. This body sensor-based network is easy to use, and available with low cost into two types; the first one can be swallowed or implanted under the skin where the second type is wearable, these became available within the Internet of Things (IoT). Physiological sensor-based systems have been recently designed to detect the emotional stress. By this way, we propose in this paper, a new monitoring system for driver stress detection based on an enhanced random forest classification approach. This proposal analyses and monitors driver electrocardiogram (ECG) signal when driving in order to discover its stress state belonging to one of the following three levels namely, low, medium or high. This proposal could help to detect and diagnostic stress level and alert the driver, its family and the other road users to avoid accidents caused by high stress state. The proposed system suggests the integration of a simulated annealing algorithm to enhance the random forest classification method in order to reach the highest classification accuracy. According to various drivers' ECG acquired from MIT-BIH physioNet dataset, the experimental study showed that the proposed random forest algorithm outperforms support vector machine (SVM) classification method to detect driver stress levels in terms of recognition accuracy.

Logically-centralized but physically-distributed SDN controllers are mainly used in large-scale SDN networks for scalability, performance and reliability reasons. These controllers host various applications that have different requirements in terms of performance, availability and consistency. Current SDN controller platform designs employ conventional strong consistency models so that the SDN applications running on top of the distributed controllers can benefit from strong consistency guarantees for network state updates. However, in large-scale deployments, ensuring strong consistency is usually achieved at the cost of generating performance overheads and limiting system availability. That makes weaker optimistic consistency models such as the eventual consistency model more attractive for SDN controller platform applications with high-availability and scalability requirements. In this paper, we argue that the use of the standard eventual consistency models, though a necessity for efficient scalability in modern SDN systems, provides no bounds on the state inconsistencies tolerated by the SDN applications. To remedy that, we propose an adaptive consistency model for the distributed ONOS controllers following the notion of continuous and compulsory (per-controller) eventual consistency, where network application states adapt their eventual consistency level dynamically at runtime based on the observed state inconsistencies under changing network conditions. When compared to the ONOS approach to static eventual consistency, our approach proved efficient in minimizing state synchronization overheads while taking into account application state consistency SLAs and without compromising the application requirements of high-availability, in the context of large-scale SDN networks.

Nowadays, network traffic classification plays an important role in many fields including network management, intrusion detection system, malware detection system, etc. Most of the previous research works concentrate on features extracted in the non-encrypted network traffic. However, these features are not compatible with all kind of traffic characterization. Google's QUIC protocol (Quick UDP Internet Connection protocol) is implemented in many services of Google. Nevertheless, the emergence of this protocol imposes many obstacles for traffic classification due to the reduction of visibility for operators into network traffic, so the port and payload- based traditional methods cannot be applied to identify the QUIC- based services. To address this issue, we proposed a novel technique for traffic classification based on the convolutional neural network which combines the feature extraction and classification phase into one system. The proposed method uses the flow and packet-based features to improve the performance. In comparison with current methods, the proposed method can detect some kind of QUIC-based services such as Google Hangout Chat, Google Hangout Voice Call, YouTube, File transfer and Google play music. Besides, the proposed method can achieve the microaveraging F1-score of 99.24 percent.

Cardiac diseases are one of the foremost reasons of mortality in the worldwide. To cope with this issue, cardiology doctors insist on the early detection of cardiac diseases often with the use of an electrocardiogram (ECG) signal, providing timely and appropriate treatment for heart patients. In the literature, there are many efficient classification approaches like random forest method, conceived for ECG signal analysis to detect cardiac diseases. However, the execution of random forest requests introducing manually the number of trees as a parameter user, which is considered as a major drawback of this method, since often the user did not find the optimal tree value. In this paper, we propose to enhance the random forest method by suggesting a new simulated annealing (SA) algorithm to find the optimal number of trees where the accuracy of classifying the ECG signal is tackled as an objective function. The proposed system involves four main steps namely data collecting of ECG signal, pretreatment and denoising this data, feature extraction and classifying this signal using the enhanced random forest approach. To validate this proposal, a set of experiments was conducted on the well-known European Physionet ST-T and MIT/BIH databases as well as the USA Heart Disease Data Set and Arrhythmia Data Set of UCI machine learning repository. The results obtained showed that the enhanced random forest can reach 99.62% of classification accuracy according to the optimal found number of trees.

In the U.S, the Basic Safety Message (BSM), commonly known as heartbeat message, has been proposed as the primary message set used by the connected vehicles' safety applications to constantly exchange data within the vehicular ad hoc networks (VANETs). BSM is communicated around 10 times per second through Dedicated Short-Range Communications (DSRC) to be exclusively used in the safety context. Once the BSM is used, it becomes obsolete and is destroyed. Nevertheless, albeit the BSM has been primarily developed to be used in the safety context, it has a capacious field of use. Other connected vehicle non-safety applications, like efficiency, environment, weather and mobility, may also use the data in the message. A wide range of BSM data elements are required by an important bunch of non-safety applications. Leastwise, core data elements of the BSM part one if cached, grouped and sent otherwise, they can solely and adequately provide the vehicle-based information needed for broad-scale applications. In this paper, we propose an Application-Level Flextime Aggregation (ALFA) scheme, allowing BSMs to be cached on-board the vehicle, intelligently aggregated according to different contexts and then sent in new message containing stored snapshots for every stretch of roadway. These new messages could be sent to vehicles and infrastructures, via Wi-Fi, digital cellular, or over a combination of all to provide broad-scale applications with needed information. The main novelty of our ALFA scheme is its contribution to change the way active safety transportation data (BSM) is treated, making it more valued, resulting in reliable and useful data source, and an efficient transportation network scaling to large areas. After a study case relevant to the vehicles mobility, obtained results showed that ALFA enhances the BSM' usefulness and provide mobility applications with useful input data.

Quick UDP Internet Connections (QUIC) is a new transport protocol developed by Google in 2012. QUIC is considered as a combination of TCP, TLS and HTTP on the top of UDP with some advantages such as reducing connection establishment time, improving congestion control, multiplexing without heads of line blocking and connection migration. In video streaming, Dynamic Adaptive Streaming over HTTP (DASH) is tied with TCP in many years, but the video streaming using HTTP on TCP has some disadvantages in terms of head of line blocking, connection migration, etc. The emergence of QUIC resolves these drawbacks and provides some solutions to reduce the latency and improve the quality of network service with respect to QoE. Therefore, in this paper, we investigate and evaluate the performance of QUIC and traditional transport protocols in the context of video streaming using DASH services. Some QUIC parameters such as maximum congestion window, buffer size and number of emulated connections are considered to choose the appropriate parameters for video streaming. Besides, we compare the performance of QUIC with TCP in terms of some network parameters and some DASH parameters. The experimental results showed that the performance of QUIC with 2 emulated connections is not as good as TCP. When the number of emulated connections is set to 6, the number of changes in quality level and stalling events are lower than the figure for TCP. Consequently, the quality level of QUIC with 6 emulated connections is better than TCP. Moreover, the QoE score of QUIC with 6 emulated connections is higher than the figure for QUIC with 2 emulated connections and TCP.

Nowadays, the high interest of Android applications makes them the target of a huge number of malware. To detect this severe increase of Android malware and help end-users make a better evaluation of apps at install time, several approaches have been proposed such as statistic and dynamic approaches. However, these approaches cannot detect with high accuracy unfamiliar malware types. That inspired us to find a new approach for recognizing a malware basing on the anomalous set of permission it requests. To actualize that idea, we used the theory of frequent patterns, a data mining technique, for mining the frequent combination of requested permissions. We also compare the performance of the proposed system to other malware detection applications. Experimental results show that the proposed system yielded high accuracy with approximately 97 percent of normal applications and 86 percent of abnormal applications.

The decoupling of control and data planes in Software-Defined Networking (SDN) brings benefits in terms of logically centralized control and application programming. But, the single point of management in physically centralized SDN architectures is a potential point of failure and a bottleneck that compromises network reliability and performance. Such centralized designs may also face scalability challenges especially in networks with a large number of hosts (e.g. IoT-like networks). To avoid such concerns, SDN control architectures are usually designed as physically distributed systems. This raises practical challenges about the best approach to decentralizing the control plane while maintaining the logically centralized network view. In particular, determining the number of controllers and locating them in the network is a hard task that should be addressed appropriately. This paper proposes two novel strategies that cover different aspects of the controller placement problem with respect to performance and reliability criteria. These strategies use two types of heuristics that are compared and assessed on large-scale topologies to provide operators with guidelines on how to find their optimal controller placement that meets their specific needs.

We propose to augment the Trickle algorithm with contextual information freely and locally available in low-power wireless networking technologies. The aim is to equip Trickle with hints and heuristics allowing it to propagate updates faster using link indicators such as received signal strength and link quality indicators along with available neighbourhood and network state information. The proposed augmentations are carefully designed so to preserve Trickle strengths in terms of simplicity, reliability, scalability, and load balancing while minimising its latency. Extensive simulation evaluations, conducted under TinyOS, show that the resulting algorithm, dubbed Trickle++, propagates updates more than twice faster than Trickle. Obtained results also show that Trickle++ preserves Trickle performance regarding overhead, load balancing, and code footprint.

One of the most important source of WSN vulnerability is the forwarding process between the nodes. In fact, routing protocols are often based on clustering principle, where a set of clusters represented by a Cluster Head (CH) for each cluster, is conceived to rely fundamentally data packets between the network nodes. These protocols are vulnerable to several attacks affecting different routing processes such as hello flooding, selective forwarding, replay process. These attacks are more damaging if the CH is corrupted by a malicious node playing CH role. This paper proposes a new secure protocol based on the well-known LEACH routing protocol named Hybrid Cryptography-Based Scheme for secure data communication in cluster-based WSN (HCBS). As a multi-constrained criteria approach, HCBS is built on a combination of the cryptography technique based on Elliptic Curves to exchange keys that uses symmetric keys for data encryption and MAC operations. After a set of tests on TOSSIM simulator, the results obtained showed that our proposal achieves good performances in terms of energy consumption, loss rate and end-to-end delay. In addition, HCBS guaranties a high level of security.

Content-Centric Networking (CCN) is a promising implementation of the Information-Centric Networking architecture that was introduced to address recent needs related to the proliferation of multimedia traffic in the Internet. One of the fundamental features of CCN is in-network caching that aims to reduce delays, optimize bandwidth, and resource usage. Designing better in-network caching strategies along with optimal replacement policies is a challenging research issue in CCN. Moreover, the lack of a common comparison framework has obfuscated the real performance of these strategies when compared with each other. Based on realistic assumptions and a common environment, this paper gives a comprehensive view on performance comparison of popular caching strategies and replacement policies employed in CCN, while considering different forwarding strategies and multiple network topologies.

This paper proposes a new QoS-aware forwarding strategy for Named Data Networking. Borrowing techniques from the ant colony optimization, the proposed strategy, which is called Ant colony based QoS-aware forwarding strategy (AC-QoS-FS), makes full use of both forward and backward ants to rank interfaces. Forward and backward ants (Interest and Data packets) probe realtime network QoS parameters to update the interfaces ranking in order to select the best one for forwarding the incoming Interests. The effectiveness of AC-QoS-FS is validated through ndnSIM simulation.

It is a critical requirement of the future 5G communication networks to provide high speed and significantly reduce the network energy consumption. Energy efficient networks along with an energy saving strategy in mobile devices play a vital role in the mobile revolution. The new strategies should not only focus on wireless base stations, which consumes most of the power, but also considers the other power consumption elements for future mobile communication networks, including User Equipment (UE). In this paper, we have proposed a method that calculates the power consumption of a 5G network by considering its main elements based on current vision of 5G network infrastructure. Our proposed model uses the component based methodology that simplifies the process by taking into account the different high power consuming elements. The proposed method is evaluated by considering the three UE's DRX models and Virtual Base Station (VBS) with respect to different DRX timer in terms of Power Saving (PS) and delay as performance parameters.

Research and development on video streaming over vehicular ad hoc networks (VANETs) have expanded rapidly in the last few years. In order to improve road safety and to satisfy road users requirements, video streaming has been proposed to disseminate continuously, an accurate video data, concerning traffic circumstance, travel information, divertissement, etc. High quality video streaming in vehicular environment is very challenging due to the very high dynamic of VANET topology and its intermittent connection, stringent requirements of video transmission such as reduced propagation delay and decreased signal to noise ratio. In this paper, we propose a new protocol called Enhanced User Datagram Protocol (EUDP) for video streaming in VANET. Unlike User Datagram Protocol (UDP) which did not consider any recovery mechanism of erroneous packets, EUDP uses Sub-Packet Forward Error Correction (SPFEC), and adopts the unequal protection of video frame types (i.e. I, P, B) to improve the video streaming quality. After a set of simulations and comparisons with UDP and EUDP without unequal protection of video frame types (EUDP-E), our proposal showed a significant improvement in terms of error recovery rate, PSNR and MOS of transmitted video.

Video streaming has become a main contributor in an ever increasing Internet traffic, and meets the users expectation is a challenging task for both the Network service Provider (NsP) and Content service Provider (CsP). In this context, a new metric called: Quality of Experience (QoE) is evolved to measure the user satisfaction using video service, and it becomes a key driver for achieving the business goal of NsP and CsP. In this perspective, we have proposed a novel framework that considers the user QoE to adapt the video quality, named Optimized Quality of DASH (OQD). The objective of the proposed OQD framework is to optimize users experience, and maximize the bandwidth usage. A Machine Learning (ML) approach based on GRadient Boosting (GRB) method is implemented to predict the user QoE that considers three important network and application QoE Influence Factors (QoE IFs). We use the Reinforcement Learning (RL) approach to select the optimal video quality segment, which improves the user QoE. The performance of the proposed method is evaluated and compared against Greedy adaptive bit-rate method in terms of re-buffering, bandwidth utilization, average MOS, and standard deviation MOS. The results clearly show that proposed method performs well, as it considers the user’s perceived video quality as a regulator to optimize the overall video delivery network.

Advancements in communications technologies are spurring a revolution within the United States transportation network. Short-range dedicated radio allows vehicles to communicate with each other within VANET. Up to date, tremendous efforts from government, academia and industry have made progress in designing and implementing several vehicular safety applications. Therefore, significant efforts have been made in designing lower-layer communication protocols for VANET. Also, Connected Vehicles (CV) concept is moving rapidly from the experimental phase into real-world deployments. Nevertheless, since all vehicles in range are shown as destination nodes, safety applications in VANET critically need an optimized way for effectively transmitting information to surrounding vehicles. To respond to this need, we propose in this paper a new Request-To-Receive (RTR) approach as a crucial step in the Basic Safety Messages (BSM) transmission process among vehicles incubating multiple safety applications. A new Data Element is proposed to be added to the basic safety messages data dictionary. Simulation results showed that RTR reduces the average number of transmitted Data Element when compared to the current situation.

Spectrum sensing security in cooperative cognitive radio networks with continuously mobile secondary users becomes a critical challenge. Thus, we propose a trust game-based model to ensure the spectrum detection while the mobility of the SUs is taken into account. Our proposal ensures both the attacks detection and the punishment of mobile malicious users launching the Spectrum Sensing Data Falsification (SSDF) attacks. Extensive simulations prove that the proposed model outperforms the AND-rule, OR-rule and Game-Based Secure Sensing (GSS) models in terms of correct decision probability, throughput and error probability with the random and linear mobility models and under four types of SSDF attacks.

When several networks (e.g., Wi-Fi, UMTS, and LTE) cover the same region, the mobile terminals that are equipped with multiple network interfaces provide the possibility for mobile end-users to select their believed best network. This is known as the network selection problem, which is a decision making problem with multiple criteria (network conditions, service requirements, terminal characteristics, and user needs). Many network selection solutions using different mathematical theories have been proposed in the literature to allow the best connectivity for applications, users, and terminals. Unfortunately, most approaches for the network selection do not make effective selection decisions, since they are vulnerable to the uncertainty and imprecision related to network state information. In this paper, we investigate the belief functions theory to devise an efficient lightweight uncertainty- aware network interface selection scheme. We provide analytical studies and simulation experiments to demonstrate the efficiency of the proposed solution.

Quality of Experience (QoE) becomes a topic of utmost eminence for service providers and the major factor in the success of multimedia services. Thus, it is challenging to investigate thoroughly the human side of QoE in order to find out the impact of factors that affect user satisfaction. In this paper, we provide a structured way to build an accurate and objective QoE model. In order to serve this purpose, Principal Component Analysis (PCA) and Analytic Hierarchy Process (AHP) approaches are combined and used to select the factors which have a significant impact on user satisfaction and essential for predicting QoE. Random Forest technique is used as a machine learning method to classify original datasets based on real environment, collected in the form of subjective scores. The results show an efficient estimation of QoE with respect to the five most influencing factors (frame rate, video size, audio rate, resolution and mean bit rate).

Video streaming over vehicular ad hoc network (VANET) provides accurate information about road traffic situation, digital services requested by drivers and passengers, compared to textual messages. Video dissemination in VANET is considered as a hard task because of high dynamic topology of vehicles, stringent requirements of video like real time transmission and the volatility of wireless medium channels. In this paper, we propose a new video streaming scheme called enhanced adaptive sub-packet forward error correction (EASP-FEC) aiming to improve video transmission quality in VANET. Unlike existing packet forward error correction (PFEC) mechanisms proposed for video streaming in VANET, which generate redundant packets for each block of original packets, EASP-FEC divides a packet into a set of original sub-packets, then it generates redundant sub-packets for each packet, to enhance the error recovery rate and video streaming quality. EASP-FEC also avoids the network congestion problem compared to sub-packet forward error correction (SPFEC) mechanism. We propose to apply EASP-FEC at the sender and relay vehicles, where the calculation process of redundant sub-packets take in consideration the traffic condition, the traffic load and the importance of video frame types (I, P, B). A set of simulations proved that EASP-FEC provides better error recovery rate than PFEC and avoids network congestion against SPFEC.

The user satisfaction measurement has gained high attention from Network Operators (NOs) and Service Providers (SPs) because their businesses are highly dependent on the user's satisfaction. Generally, the traditional strategies to measure the user's perception are based on Quality of Service (QoS), which is not sufficient to reflect the real user's perceived quality. Therefore, NOs and SPs start to develop new strategies based on the Quality of Experience (QoE) metric to analyze the relationship between the user's satisfaction and influence factors (QoE IFs). In this paper, a new method to build a predictive model to estimate user's satisfaction in terms of Mean Opinion Score (MOS) is proposed. The proposed method uses the dataset collected using the controlled testbed based on the YouTube video service. In the proposed model, the correlation matrix is used to develop a new heuristic method that used back-jumping technique to select the most beneficial factors to predict the optimal user's satisfaction.

Information-Centric Networking (ICN) is a novel paradigm for future Internet architectures. The aim of ICN is to accommodate content distribution within the Internet infrastructure. Named Data Networking (NDN) is one of the most popular ICN proposal. This paper presents a design of QoS-FS, a new NDN's adaptive forwarding strategy with quality of service (QoS). At each node of the network, QoS-FS monitors, in real-time, ingoing and outgoing networks' link to estimate the QoS parameters and integrate them into the different decisions taken to determine when and which interface to use to forward an Interest. Therefore, making forwarding decision adaptive to network conditions and user's preferences. We provide simulation experiments to demonstrate the efficiency of the proposed solution.

In Heterogeneous Wireless Networks (HWNs), the mobile terminals are equipped with multiple access network interfaces (GSM, UMTS, LTE, WiFi, Bluetooth, etc.), to provide the possibility for mobile end-users to rank the networks and dynamically select the best one at anytime and anywhere, which is well known as Always Best Connected (ABC). In such environment, the major issue is network interface selection, which is a decision making problem with multiple alternatives (networks) and attributes (network characteristics, application requirements, terminal capacities, and user needs). In this context, many approaches have been proposed. Multi Attribute Decision Making (MADM) algorithms present a promising solution for multi-criteria decision making problems. Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is one of MADM algorithms, which is widely adopted. TOPSIS ranks the available networks based on their scores, with the highest being the best. TOPSIS suffers from couple limitations. First is the ranking abnormality, e.g. if a low ranking network is disconnected then the order of higher ranking networks changes, which results in the selection of a less desirable network. Second is the selection strategy, where TOPSIS simply selects the network with highest score regardless of whether or not it satisfies the user and/or application needs. In this paper, we propose a new strategy based on utility function to remedy these shortcomings. The effectiveness of our strategy is evaluated through simulations. Obtained results show clearly that our strategy eliminates the rank reversal (ranking abnormality) phenomenon, and enhances the ranking quality by considering application and/or user needs.

The 4G standard Long Term Evolution-Advanced (LTE-A) has been deployed in many countries. Now, technology is evolving towards the 5G standard since it is expecting to start its service in 2020. The 5G cellular networks will mainly contain in cloud computing and primarily Quality of Service (QoS) parameters (e.g. delay, loss rate, etc.) influence the cloud network performance. The impact of user perceived Quality of Experience (QoE) using multimedia services, and application significantly relies on the QoS parameters. The key challenge of 5G technology is to reduce the delay less than one millisecond. In this paper, we have described a method that minimizes the overall network delay for multimedia services; which are constant bit rate (VoIP) and variable bit rate (video) traffic model. We also proposed a method that measures the user's QoE for video streaming traffic using the network QoS parameters, i.e. delay and packet loss rate. The performance of proposed QoE method is compared with QoV method, and our proposed QoE method performs best by carefully handle the impact of QoS parameters. The results show that our described method successfully reduces the overall network delays, which result to maximize the user's QoE.

In Heterogeneous Wireless Networks, mobile users use a terminal with multiple access interfaces for non-real-time or real-time applications (services). In such environment, the major issue is Always Best Connected (ABC), which means that the mobile nodes rank the network interfaces and select the best one at anytime and anywhere. To meet the ABC requirements, many network interface selection strategies have been proposed in the literature, using various technologies. This paper surveys existing approaches and discusses their advantages and limitations. The paper also highlights open issues in this area of research and proposes a new QoE-based approach for interface selection based on TOPSIS algorithm for e-Health use case. The effectiveness of our approach is evaluated through simulations. Obtained results show clearly that our approach ensures the best QoE for user, and eliminates a major inconvenient due to rank reversal (ranking abnormality).

HTTP video streaming becomes a main contributor in the ever increasing Internet traffic. It is not an easy task for the network service provider to guarantee the best user's Quality of Experience (QoE) in diverse networks with different access technologies. This requires an adaptive method that dynamically adapts the video quality service over HTTP according to time varying network conditions. In this paper, a client-based rate adaptive method is proposed that dynamically selects the appropriate video quality according to network conditions and user's device properties. The proposed method considers three important Quality of Service (QoS) factors that regulate the user's QoE for video streaming over HTTP, which are: Bandwidth, Buffer, and dropped Frame rate (BBF). The network bandwidth significantly affects the video service, as it directly reduces the client buffering that may result in pausing or stalling during video streaming. The proposed BBF method efficiently deals with sudden drop of network bandwidth by using the new bandwidth metric, and reduces its impact on the buffer level of the end user. The buffer length plays a vital role to handle the dynamic change in bandwidth. The dropped frame rate (fps) is another influential factor that minimizes the user's QoE. The proposed BBF algorithm is evaluated with different buffer length, and it is compared to Adobe's OSMF adaptive method.

Traditionally, companies host their own services, platforms and infrastructures on their own servers. This policy results in high costs in terms of material and human resources. It may also be inadequate to the real needs of the company. In this context, one solution is to use cloud computing to outsource their services. The latter is defined by making available to the customer high-performance servers and high bandwidth. The cloud is also defined by renting software and hardware infrastructure to customers according to their needs. Cloud computing is made possible by the improvement of computer networks infrastructures. Indeed, broadband connections have reduced latency and thus enabled the use of remote resources. The success of cloud computing has led to a significant increase in the providers number offering many and varied cloud services. While the access to these services is made possible through a simple subscription, no technique is currently available to select the cloud provider that best fits their needs. Selecting a provider is an optimization problem that has been studied in several areas. Given the large number of parameters and actors in the cloud, this problem is known as NP-complete one. In this work, we propose a new developed platform which plays the role of a broker between clients and cloud providers. Based on a set of benchmark tasks on provider services, it performs an adaptive cloud provider selection in accordance with the client needs. The experimental results show that the proposed approach gives benefits to subscribers in terms of QoE.

In this paper, we address the survivable batch-embedding virtual network problem within Cloud's backbone. In fact, the batch mapping of virtual networks will enhance the cumulative Cloud provider's revenue thanks to the global view of the incoming requests during a predefined time slot. Hence, the differentiation between requests can be performed and the arrival order of requests is ignored. The embedding of one virtual network is NP-hard. Adding the batch processing of the requests will further increase the complexity of the problem. In order to skirt the exponential complexity, we formulate the problem as building and researching problems within a decision tree. To resolve it, we propose a novel reliable batch-embedding virtual network strategy denoted by BR-VNE. It is based on Monte-Carlo Tree Search optimization method in which the upper confidence bounds can be reached in polynomial time. Based on extensive simulations, the results obtained show that BR-VNE outperforms the related work in terms of i) acceptance rate of virtual network requests, ii) Cloud provider's revenue and iii) rate of requests impacted by physical failures within the Cloud's backbone.

International audience

The tremendous growth in video services, specially in the context of mobile usage, creates new challenges for network service providers: How to enhance the user's Quality of Experience (QoE) in dynamic wireless networks (UMTS, HSPA, LTE/LTE-A). The network operators use different methods to predict the user's QoE. Generally to predict the user's QoE, methods are based on collecting subjective QoE scores given by users. Basically, these approaches need a large dataset to predict a good perceived quality of the service. In this paper, we setup an experimental test based on crowdsourcing approach and we build a large dataset in order to predict the user's QoE in mobile environment in term of Mean Opinion Score (MOS). The main objective of this study is to measure the individual/global impact of QoE Influence Factors (QoE IFs) in a real environment. Based on the collective dataset, we perform 5 testing scenarios to compare 2 estimation methods (SVM and ANFIS) to study the impact of the number of the considered parameters on the estimation. It became clear that using more parameters without any weighing mechanisms can produce bad results.

Fault diagnosis is a critical task for operators in the context of e-TOM (enhanced Telecom Operations Map) assurance process. Its purpose is to reduce network maintenance costs and to improve availability, reliability and performance of network services. Although necessary, this operation is complex and requires significant involvement of human expertise. The study of the fundamental properties of fault diagnosis shows that the diagnosis process complexity needs to be addressed using more intelligent and efficient approaches. In this paper, we present a hybrid approach that combines Bayesian networks and case-based reasoning in order to overcome the usual limits of fault diagnosis techniques and to reduce human intervention in this process. The proposed mechanism allows the identification of the root cause with a finer precision and a higher reliability. At the same time, it helps to reduce computation time while taking into account the network dynamicity. Furthermore, a study case is presented to show the feasibility and performance of the proposed approach based on a real-world use case: a virtual private network topology.

Abstract Vehicular ad hoc networks (VANETs) are witnessing in recent years a rapid development for road transmissions and are considered as one of the most important types of next generation networks, in which drivers can have access anywhere and anytime to information. However, vehicles have to deal with many challenges such as the links failures due to their frequent mobility as well as limited degrees of freedom in their mobility patterns. In this paper, we propose a new quality of service multicast and multipath routing protocol for VANETs, based on the paradigm of bee's communication, called multicast quality of service swarm bee routing for VANETs (MQBV). The MQBV finds and maintains robust routes between the source node and all multicast group members. Therefore, the average end‐to‐end delay and the normalized overhead load should be reduced, while at the same time increasing the average bandwidth and the packet delivery ratio. Extensive simulation results were obtained using ns‐2 simulator in a realistic VANET settings and demonstrated the efficiency of the proposed protocol. Copyright © 2013 John Wiley & Sons, Ltd.

The 4G standard Long Term Evolution (LTE) has been developed for high-bandwidth mobile access for today's data-heavy applications, consequently, a better experience for the end user. Since cellular communication is ready available, LTE communication has been designed to work at high speeds for vehicular communication. The challenge is that the protocols in LTE/LTE-Advanced should not only provide good packet delivery but also adapt to changes in the network topology due to vehicle volume and vehicular mobility. It is a critical requirement to ensure a seamless quality of experience ranging from safety to relieving congestion as deployment of LTE/LTE-Advanced become common. This requires learning how to improve the LTE/LTE-Advanced model to better appeal to a wider base and move toward additional solutions. In this paper we present a feasibility analysis for performing vehicular communication via a queueing theory approach based on a multi-server queue using real LTE traffic. A M/M/m model is employed to evaluate the probability that a vehicle finds all channels busy, as well as to derive the expected waiting times and the expected number of channel switches. Also, when a base station (eNB) becomes overloaded with a single-hop, a multi-hop rerouting optimization approach is presented.

The quality assessment of multimedia services as perceived by the end-user is a challenging task. In a controlled environment, it is easy to measure the user's Quality of Experience (QoE) against the influence of controlled network parameters. However, in an uncontrolled environment, it is difficult to measure the Quality of Service (QoS) perceived by end-users, due to the unpredictable behaviour of networks. Crowd-sourcing is an emerging technique that can be employed to measure the QoE at the end user, but in an uncontrolled environment. In this paper, we present a tool implementing a crowd-sourcing framework, that measures the QoE of online video streaming, as perceived by end-users. The tool also measures important QoS network parameters in real-time (packet loss, delay, jitter and throughput), retrieves system information (memory, processing power etc.), and other properties of the end-user's system. The proposed approach provides the opportunity to explore the user's quality perception in a wider domain.

In multimedia services, user's perceived quality of service is very important as compared to other end-to-end network factors. With the growth of emerging technologies, it becomes necessary for network service providers (both in the wired and wireless domains) to consider all aspects of network elements, not only to offer a better Quality of Service (QoS) but also to achieve higher end-users satisfaction. The analysis of users' profile provides vital information, which can help service providers in managing their resources efficiently, by analyzing users' behavior and expectation. In this paper, we setup a testbed to investigate the various factors that contribute to the Quality of Experience (QoE), in the context of video streaming delivery over wireless and wired networks. The comprehensive study of users profile provides significant insights on all metrics that influence the QoE (network parameters and video characteristics). Wireless and wired networks have different infrastructure aspects (reliability, availability etc.) but the analysis and evaluations of users' profile are equally important for both networks. Our analytical study gives an opportunity for network service providers to obtain high user satisfaction by providing a service level that matches customers' usage patterns and expectations.

In this paper, we propose a new survivable virtual network mapping strategy within Cloud's backbone enhancing the Cloud Provider's revenue and dealing with physical failures of routers and links. In order to skirt the exponential complexity of the mapping, we propose a new reliable embedding strategy, denoted by CG-VNE, based on coordination game framework. To do so, we have formulated the problem as two interleaved coordination games. The first game addresses the virtual routers' mapping. In fact, the actions of each virtual router player strongly depend on the mapping of its attached virtual links. Hence, the second game is launched to embed the virtual links. Note that with both games, fictitious players cooperate to reach Nash Equilibrium of which we have proven the existence and it corresponds to a social optimum. CG-VNE aims to maximise the Cloud's provider revenue by maximising the acceptance rate of clients, as well as minimise the blackout rate of virtual networks caused by the outage of substrate routers and/or links. Based on extensive simulations, the results obtained show that CG-VNE has the best performance in terms of i) rejection rate of new clients, ii) Cloud's revenue and iii) rate of clients impacted by physical failures.

Emerging multimedia services are spreading significantly thanks to the availability of high speed wireless networks. Network operators are facing the challenges to accommodate these services (e.g. Skype, interactive gaming, and other multimedia applications) with high user satisfaction. This paper presents a Quality of Experience (QoE) driven approach to allocate the radio resources in Long Term Evolution (LTE) wireless networks, in order to get higher user satisfaction. The main objective is to enhance the user experience while using the multimedia services such as VoIP, by jointly considering the user QoE and available wireless radio resources in the LTE-Advanced (LTE-A) network. Specifically, we propose a new downlink scheduling algorithm known as “QoE Scheme” for multimedia VoIP service in LTE-A networks. The main advantage of the proposed QoE Scheme is its measurement of user satisfaction and its feedback mechanism to the scheduler at evolving NodeB (eNodeB) in order to make the scheduling decision.

Network lifetime has become the key characteristic for evaluating sensor networks in an application-specific way. In this paper, we focus on Mobile Wireless Sensor Networks, which are specific opportunistic networks because of their poor connectivity among the mobile sensors, and thus it is difficult to form a well connected mesh network for transmitting data through end-to-end connections from the sensors to the sink. We propose EXLIOSE (Novel approach to EXtending network LIfetime in Opportunistic SEnsor Networks), a routing protocol that focuses on maximizing network lifetime while keeping high delivery statistics. EXLIOSE is based on a novel routing metric that uses the history of encounters between nodes, and the nodal residual energy. Simulation results show that our approach is able to extend network lifetime and achieve good delivery statistics, as compared to state-of-the-art solutions.

As current server capacity and network bandwidth become increasingly overloaded by the rapid growth of high quality emerging multimedia services such as mobile online gaming, social networking or IPTV, a critical factor of success of these multimedia services becomes the end-user perception of quality while them using the service. As a result, user-centered approaches that consider quality of experience (QoE) constitute the current design trend for network systems of content providers and network operators. A content distribution network (CDN) that replicates the content from original servers to the replicated servers close to end users is actually an effective solution to improve network quality. We propose a QoE-based server selection algorithm in the context of a CDN architecture. Using realistic characteristics of the server selection process, we formalize our selection model as a sequential decision problem solved by the multi-armed bandit (MAB) paradigm. By using realistic experiments, we demonstrate that our approach yields significant improvements in term of user perception compared to traditional methods (such as Fastest, Closest and Round Robin).

One of the fundamental services provided by a wireless sensor network (WSN) is the monitoring of a specified region of interest (RoI). Considering the fact that emergence of holes in the RoI is unavoidable due to the inner nature of WSNs, random deployment, environmental factors, and external attacks, assuring that the RoI is completely and continuously covered is very important. This paper seeks to address the problem of hole detection and healing in mobile WSNs. We discuss the main drawbacks of existing solutions and we identify four key elements that are critical for ensuring effective coverage in mobile WSNs: 1) determining the boundary of the RoI, 2) detecting coverage holes and estimating their characteristics, 3) determining the best target locations to relocate mobile nodes to repair holes, and 4) dispatching mobile nodes to the target locations while minimizing the moving and messaging cost. We propose a lightweight and comprehensive solution, called holes detection and healing (HEAL), that addresses all of the aforementioned aspects. The computation complexity of HEAL is O(v2) , where v is the average number of 1-hop neighbors. HEAL is a distributed and localized algorithm that operates in two distinct phases. The first identifies the boundary nodes and discovers holes using a lightweight localized protocol over the Gabriel graph of the network. The second treats the hole healing, with novel concept, hole healing area. We propose a distributed virtual forces-based local healing approach where only the nodes located at an appropriate distance from the hole will be involved in the healing process. Through extensive simulations we show that HEAL deals with holes of various forms and sizes, and provides a cost-effective and an accurate solution for hole detection and healing.

In this paper, we propose a new preventive reliable virtual network embedding algorithm denoted by PR-VNE within the Cloud's backbone network. The proposal does not allocate any backup resources and takes into consideration the ageing of the hardware backbone network. The main objective is to maximise the number of hosted virtual networks while minimising the rate of crashed virtual networks impacted by physical (i.e., routers or links) failures. The problem is a multi-objective non-linear optimisation and classified as NP-hard. To overcome its complexity, PR-VNE is based on the artificial bee colony metaheuristic. Moreover, it makes use of a multi commodity flow algorithm in order to maximise the load balancing of bandwidth usage within the physical network. Based on extensive simulations, the performance obtained is better than the related strategies found in literature in terms of reject and blackout rates of virtual networks.

A main objective of an Information Centric Network (ICN) is to improve the network by placing the knowledge in center of the network design. This vision of the network needs an efficient distributed and decentralized knowledge plane. So, an important amount of knowledge should be disseminated over the supervised network, which remains an open problem. Indeed, the dissemination infrastructure must be able to ensure the transport of all information types including knowledge information, throughout the network, and guarantee its freshness. Another crucial aspect of the problem is related to the network robustness with respect to network failures. In this paper, we propose a new model of knowledge dissemination based on super peers architecture. We formalize the super peer selection problem as a K-medoids clustering task. Furthermore, to handle the dynamicity of the network and especially the changes of the end-user network topology, we improved the selection mechanism by adding an adaptive mechanism based on the Page-Hinkley statistical test. Experimental results show that the proposed approach significantly improves performances compared to other current approaches.

The capability to diagnose the root cause of an observed problem precisely and quickly is a desirable feature for large communication networks. However, the design of a technique that is at the same time fast, scalable and accurate is a challenging task. In this paper, we propose a novel method based on inter-cluster inference to overcome the usual limits of fault diagnosis techniques. The approach is based on two important concepts: a cluster decomposition of the dependency graph in order to ensure scalability, and the introduction of duplicated nodes aiming at preserving the end-to-end network view. The evaluation of the proposed approach has demonstrated a significant reduction in the complexity and the computation time of the root cause analysis, since it is based on a set of small-scale dependency graphs.

The 4G standard Long Term Evolution (LTE) has been developed for high-bandwidth mobile access for today's data-heavy applications. However, these data-heavy applications require lots of battery power on the user equipment. To extend the user equipment battery lifetime, plus further support various services and large amount of data transmissions, the 3GPP standards for LTE/LTE-Advanced has adopted discontinuous reception (DRX). In this paper, we take an overview of various static/fixed DRX cycles of the LTE/LTE-Advanced power saving mechanisms, by modelling the system with bursty packet data traffic using a semi-Markov process. Based on the analytical model, we will show the trade-off relationship between the power saving and wake-up delay performance. This work will help to select the best parameters when LTE/LTE-Advanced DRX is implemented depending on the protocols and desired outcome of the traffic.

Vehicular ad-hoc networks (VANETs) can be considered as complex dynamic systems where simulation modeling plays a crucial role in conducting research due to the difficulties in the realization of such a network, like high costs, risks and dangers. During the last decade, the results of VANET simulations were considered successful and acceptable however, most prior VANET simulators were based on non realistic mobility when describing node positions, distribution, frequency and movement, model paths, traffic signals etc. To deal with this challenge, we propose in this paper a Markov-History based modeling for realistic mobility of vehicles in VANETs. It starts with a geographic area digitization, followed by a vehicle positions initialization. The proposed model predicts directions of the vehicles using a Markov chain, as well as it predicts the vehicle velocities using a History-based sub-model. Moreover, the density of the network is updated according to the peak or off-peak hours. The emerged model can be used as mobility model to simulate VANET scenarios. To validate our proposal, a concrete mobility model has been designed using the proposed model that represents the downtown of Biskra City located in Algeria. The performances of the resulting network have been proved against the others obtained using Random Waypoint as a standard mobility model in terms of packet delivery ratio, network overhead, average end-to-end delay, and dropped packets.

This article proposes a state-dependent routing algorithm based on a global optimization cost function whose parameters are learned from the real-time state of the network with no a priori model. The proposed approach samples, estimates, and builds the model of pertinent and important aspects of the network environment such as type of traffic, QoS policies, resources, etc. It is based on the trial/error paradigm combined with swarm-adaptive approaches. The global system uses a model that combines both a stochastic planned prenavigation for the exploration phase with a deterministic approach for the backward phase. We conducted a performance analysis of the proposed algorithm using OPNET based on several topologies such as the Nippon telephone and telegraph network. The simulation results obtained demonstrate substantial performance improvements over traditional routing approaches as well as the benefits of learning approaches for networks with dynamically changing traffic.

The Quality of Experience (QoE) determines the user satisfaction degree of communication services. Quantifying the relationship between User QoE and Network Quality of Service (QoS) enables the services providers to estimate the contribution of network performance in overall user satisfaction. Based on the Multiple Linear Regression (MLR) and the exponential hypothesis, we propose in this paper a global correlation model between QoE and QoS. The main contribution of our proposal is the use of a combination of more than one QoS parameter in the model. The proposed method is validated for Video on Demand services where the QoE considers the quality of video and the QoS is impacted with two parameters (delay and loss ratio). According to the experimental results, we obtained a composite correlation model with a good correlation coefficient.

Cloud computing is known as services delivery such as shared resources, platforms, software and data, in the interest of end-users. They are located in distributed datacenters over a network such as the Internet. In this paper a new cloud computing model called ITS-Cloud applied to the Intelligent Transportation Systems (ITS) is proposed to improve transport outcomes such as road safety, transport productivity, travel reliability, informed travel choices, environment protection, and traffic resilience. It consists of two sub-models: the statistic and the dynamic cloud sub-models. In the former, vehicles benefit of the conventional cloud advantages however; the dynamic one which is a temporary cloud is formed by the vehicles themselves which represent the cloud datacenters. To validate our proposal, a simulation study is performed to deal with the load balancing as a NP-Complete problem. The reached results are obtained using Bees Life Algorithm (BLA) applied to ITS-Cloud and compared with those reached by (BLA) applied only to the conventional Cloud.

A Wireless Sensor Network (WSN) consists of many sensors that are densely deployed to monitor a field. The sensor-positions can be predetermined to guarantee the quality of surveillance provided by the WSN. In remote or hostile sensor field, randomized sensor placement often becomes the only option. In this paper, we survey existing stochastic node placement strategies. We categorize stochastic placement strategies into simple and compound. A simulation study has been carried out yielding a detailed analysis of random deployment intrinsic properties, such as coverage, connectivity, fault-tolerance and network lifespan. The obtained results can give helpful design guidelines in using stochastic deployment strategies, and allow engineers to choose the deployment strategy appropriate to the situation and the goals.

Autonomic computing is a new paradigm inspired by the biological world. It aims at making a network independent of any human monitoring. To reach such autonomy, knowledge should be disseminated over the network, which remains an open problem. Our solution consists in proposing a new model of knowledge dissemination based on three key ideas: a hierarchical architecture, a specific-service overlay network (SSON) and a multi-criteria selection of a subset of nodes responsible for knowledge management. The simulation results show that the proposed approach significantly improves performances compared to other approaches.

Mobile ad hoc network (MANET) is a wireless network that consists of a large number of mobile and heterogeneous nodes interconnected by wireless links which move in an arbitrary direction with random velocity. It is characterized by the absence of any pre-existing infrastructure. This makes the transmission more difficult especially, in the case of multicast mode. Some of the most important applications that use the MANETs are the multimedia and real time systems. They require a very high level of quality of service (QoS) to make the network useful. In this paper, we propose a new QoS multicast routing protocol called MQBM for MANETs inspired by the bees' communication. It allows finding routes between the source and the head of multicast group responsible to communicate the packet toward the group members. Each node is allowed to transmit data only if the average end-to-end delay and the average bandwidth satisfy the QoS requirements. Extensive simulation results obtained using NS2 simulator, demonstrate the efficiency and the performance of the proposed protocol after comparisons against MAODV in terms of the average end-to-end delay and the average bandwidth as QoS metrics.

The 4G standard Long Term Evolution (LTE) has been developed for high-bandwidth mobile access for today's data-heavy applications, consequently, a better experience for the end user. To extend the user equipment battery lifetime, plus further support various services and large amount of data transmissions, the 3GPP standards for LTE/LTE-Advanced has adopted discontinuous reception (DRX). However, there is a need to optimize the DRX parameters, so as to maximize power saving without incurring network re-entry and packet delays. In this paper, we provide an overview of the fixed frame DRX cycle and compare it against an adjustable DRX cycle of the LTE/LTE-Advanced power saving mechanism, by modelling the system with bursty packet data traffic using a semi-Markov process. Based on the analytical model, we will show the trade-off relationship between the power saving and wake-up delay performance.

Autonomic Networks represent a concept inspired by the biological world that aims at making a network independent of any human monitoring. To reach such autonomy, knowledge should be disseminated over the network, which remains an open problem. In fact, disseminating the knowledge over all nodes leads to a big overhead. That is why we need to select a subset of nodes in charge of knowledge management. A single criterion-based selection mechanism has been proposed in a previous work but such a mechanism seems to be very simplistic. In this paper, we present a new multi-criteria selection mechanism based on Pareto. The simulation results show that the proposed approach significantly improves performances compared to single criterion-based selection mechanism.

For years, wireless network systems have been trying to satisfy end-users and support high quality multimedia applications such as Mobile TV, VoIP, etc. Combining wireless networks with multimedia content distribution needs efficient routing protocols. We develop in this paper a new routing protocol, namely DOQAR (Dynamic Optimized QoE Adaptive Routing), to improve the user perception and optimize the usage of network resources. In our end-to-end model, smartphone users connect to content servers in a wired network across a wireless access network. In order to evaluate the QoE, we use a Multi-Layer Perception-based (MLP) method. Experimental results show a significant performance against other traditional routing protocols.

Fault diagnosis is one of the most important tasks in fault management. The main objective of the fault management system is to detect and localize failures as soon as they occur to minimize their effects on the network performance and therefore on the service quality perceived by users. In this paper, we present a new hybrid approach that combines Bayesian Networks and Case-Based Reasoning to overcome the usual limits of fault diagnosis techniques and reduce human intervention in this process. The proposed mechanism allows identifying the root cause failure with a finer precision and high reliability while reducing the process computation time and taking into account the network dynamicity.

Deployment is a fundamental issue in wireless sensor networks. Usually the sensor locations are precomputed based on a ”perfect” sensor coverage model, whereas sensors may not always provide reliable information, either due to operational tolerance levels or environmental factors. Therefore, it is imperative to have practical considerations at the design stage to anticipate this sensing behavior. In this paper, we address four different forms of static wireless sensor networks deployment while considering an evidence-based sensor coverage model. The four problems are formalized as combinatorial optimization problems, which are NP-complete. We propose, E2BDA (Efficient Evidence-Based sensor Deployment Algorithm), a polynomial-time uncertainty-aware deployment algorithm based on a dynamic programming approach. E2BDA is able to determine the minimum number of sensors and their locations to achieve both coverage and connectivity. We compare our proposal to the state-of-the-art deployment strategies, the obtained results show that E2BDA obtains the best performances.

HTTP has been the most popular internet protocol for 30 years. Until recently, its role has been limited to a traditional transfer of hypertext documents. However, its flexibility and interoperability cause it to be progressively involved in a much wider range of applications, from video and audio streaming to email, chat and documents editing. Understanding the behavior of modern Web applications is a crucial step to apply QoS or security policies on this traffic. This paper studies 20 popular, Web applications that are representative of 12 application types. We describe a method to isolate and capture browser-generated traffic and plot time series with an RRDTool database. We show that modern Web applications present very diverse traffic patterns, and propose a description and classification of these patterns.

In this paper, we address the issue of handling uncertainty and information fusion for an efficient WSN deployment. We present a flexible framework for collaborative target detection within the transferable belief model. Using the developed framework, we propose an uncertainty-aware deployment algorithm that is able to determine the minimum number of sensors and their locations such that full area coverage is achieved. The issues of connectivity, obstacles, preferential coverage, challenging environments and sensor reliability are also discussed. Experimental results are provided to demonstrate the ability of our approach to achieve an efficient sensor deployment by exploiting a collaborative target detection scheme.

Research and industries are recently more interesting and attracting to the Vehicular Ad hoc Networks (VANETs) development domain. They contribute to safer and more efficient roads by providing timely and accuracy information to drivers and authorities. Thus, the definition of a quality of service routing protocol for VANETs is one of their challenges. In this paper, we propose QoSBeeVanet, a new quality of service multipath routing protocol adapted for the vehicular ad hoc networks. It is based on ideas of the autonomic bee communication. Simulation results taken with NS2 in realist urban settings were shown that QoSBeeVanet outperforms DSDV and AODV two of the current state-of-the-art protocols, in terms of end-to-end delay, packet delivery ratio, and normalized overhead load.

International audience

Sensor network lifetime strongly depends on the used routing protocol. Using several definitions of lifetime and a common evaluation framework, we have analyzed the lifetime of some representative flat and hierarchical sensor network routing protocols, namely: DIRECT, FLOODING, GOSSIPING, LEACH and HEED. Extensive simulations have been carried out yielding a detailed analysis of lifetimes. Through this study, we propose a new technique to increase HEEDs' lifetime. The resulting protocol EHEED is compared to other protocols. Experimental results show that EHEED can be very effective for long-lived sensor network.

Driven by the demographic variation in population and degradation of health care quality, we have witnessed in the recent years the explosion of healthcare applications market in order to provide high quality care. Wireless Sensor Networks (WSN) seem to be an attractive technology to deploy this type of applications thanks to their advantages of simplicity of deployment, safe of use and reduced installation cost. In this paper we present a specific medical application on which we work in collaboration with the Henri Mondor University Hospital Center in France. This application aims to monitor patients' physiological parameters and track their localizations within the hospital. We describe in this paper tests performed in our lab and analyze the first results of implementation of a sensor network platform.

Computing constrained shortest paths is fundamental to some important network functions such as QoS routing and traffic engineering. This paper introduces a polynomial time approximation Quality of Service (QoS) routing algorithm and constructs dynamic state-dependent routing policies. The proposed algorithm uses a bio-inspired approach based on the trial/error paradigm combined with swarm adaptive approaches to optimize three QoS different criteria: static cumulative cost path, dynamic residual bandwidth, and end-to-end delay. The approach uses a model that combines both a stochastic planned pre-navigation for the exploration phase and a deterministic approach for the backward phase. In this paper, we adopt the unified framework of online learning to consider a global cost function. Numerical results obtained with OPNET simulator for different levels of traffic's load show that the new added module improves clearly performances of our earlier KOQRA.

Designing a QoS-aware, yet energy-saving routing protocol for WSNs is a notoriously hard problem. However, the outstanding interest for this technology, and the growing number of envisioned applications, motivate the need to introduce the notion of Quality of Service (QoS) in these networks. This paper introduces EDEAR (Energy and Delay Efficient Adaptive Routing), an adaptive routing algorithm based on route exploration and reinforcement learning. We evaluate EDEAR with simulations, under various network mobility conditions. Our results show that EDEAR outperforms any other routing protocol, delivering packets with the shortest delay, while reducing energy consumption. As a result, EDEAR's features allow to increase the network lifetime by 9-18%.

In the few last years, there is an increasing need of QoS guarantees for multimedia and real time applications in mobile ad hoc networks. While several QoS routing protocols were proposed, adaptive routing has not be enough exploited. We propose in this paper a new delay oriented adaptive routing protocol for mobile ad hoc networks. We integrate a mean delay estimation model at each node in our protocol in order to avoid synchronization problem. Adaptive mean delay routing (AMDR) protocol proposed in this paper uses two kinds of exploration packets having the task of gathering delay information of available paths and updating probabilistic routing tables. To reduce the overhead generated by AMDR protocol, we propose the use of a new MPR selection algorithm called Flooding Optimization Algorithm (FOA) based on mean delay.

The service composition aims to provide a variety of high level services. Recent approaches cannot fully satisfy the requirement raised by ubiquitous environment. In this paper, we propose a layered design framework which aims at being flexible and robust to failure service composition. It adopts an abstract way of generating plan using rule-based techniques in order to adapt to the changes occurring on the services and the context of use. The approach optimizes the number of services and the recomposition time in large-scale environment by removing the phase of rediscovery. The framework for service composition and monitoring includes learning mechanism for the service selection, based on an estimation of the reputation for abstract services and the quality (QoS) for concrete services. The proposed approach is tested, under USARSim simulator, on a set of ubiquitous services for assisting elderly or dependant person in a residential environment. The obtained results show the feasibility and the scalability of the approach and a better reactivity to the dynamic and uncertain nature of the ubiquitous environment.

With the wide emergence of real time applications in mobile ad hoc networks, delay guarantees become increasingly required. Many routing protocols are proposed, in the few last years, for improving the overall delay in mobile ad hoc networks. In this paper, we propose an extension of our earlier QoS routing protocol called “AMDR” (Adaptive Mean Delay Routing) which is based on an adaptive approach using mean delay estimated proactively by each node. AMDR is built around two modules: Delay Estimation Module and Adaptive Routing Module. The first one calculates proactively mean delay at each node without any packets exchange. The second one will then exploit mean delay value. It uses two exploration agents to discover best available routes between a given pair of nodes. Numerical results obtained with NS simulator for different levels of traffic's load show that AMDR improves clearly performances compared to other approaches.

Africa has witnessed an incredible boom in the number of mobile subscribers in mobile networks across Africa. With the rise in demand for capacity in cellular networks, greater pressure is being placed on the network planner. Customer segmentation has been traditionally used in cellular network planning to better understand customer demands and needs. By developing more accurate profiling methods, operators are in a better position to market products and forecast future demand more accurately. This work looks at the extraction of frequency patterns from traffic signals originating from a typical mobile network using multi-scale analysis. By studying the features extracted, the classification of typical subscribers in the network can be conducted more efficiently and with greater granularity.

Wireless Sensor Networks (WSN) represent actually one of the challenging type of Delay-tolerant networks due their sparse connectivity and hard coverage. In addition, the emergence of applications with different types of traffic in these networks, assurance of Quality of Service (QoS) becomes more and more important. In recent years, lot of research has been conducted to improve the QoS in WSN. In this article, we introduce a Quality of Service (QoS) routing algorithm based on dynamic state-dependent policies. The proposed algorithm uses a bio-inspired approach based on trial/error paradigm to optimize two QoS different criteria: Energy and end-to-end delay. Our proposal, called EDEAR "Energy and Delay Efficient Adaptive Routing", is based on explorer agent who is responsible for collecting information in terms of energy and delay by using continuous learning parameters on the network and update routing maintained at each node of the network. The exploration of routes has been optimized by proposing a new algorithm based on multipoint relay for energy consumption, thus reducing the overhead generated by the packets exploration. Numerical results obtained with NS simulator for different levels of traffic's load and mobility show that EDEAR gives better performances compared to traditional approaches.

International audience

Fault-tolerance is an important function in target tracking application using wireless sensor networks. We propose in this paper, an efficient fault-tolerant approach for target tracking that prevents the loss of the target. Instead of using a single prediction mechanism, our approach uses a multi-level incremental prediction technique that adjusts the prediction precision of the target movement. The responsible node of target detection uses multiple historical information pieces to calculate multi-level predictions which have different precision levels according to the number of information pieces used. Thanks to our parametric prediction model, our approach increases the prediction success rate and decreases the target loss frequency compared to basic approaches that use simple prediction models.

This paper introduces a polynomial time approximation quality of service (QoS) routing algorithm and constructs dynamic state-dependent routing policies. The proposed algorithm uses an inductive approach based on trial/error paradigm combined with swarm adaptive approaches to optimize the end-to-end delay packet transmission. The algorithm presented here is based on our earlier adaptive routing system and uses a model combining both a stochastic planned pre-navigation for the exploration phase and a deterministic approach for the backward phase. Numerical results obtained with OPNET simulator for different levels of traffic's load show good performances of our approach compared the classical non adaptive algorithms in a high dynamic environment.

This paper describes an approach which uses a machine learning model in a packet scheduling problem to improve the end-to-end delay. A good Packet scheduling discipline allows to achieve QoS differentiation and to optimize the queuing delay. In a dynamically changing environment this discipline should be also adaptive to the new traffic conditions. We model this problem as a multi-agent system which consists of a whole of autonomous learning agents that interact with the environment. We define the learning problem as a decentralized process using a general mathematical framework, namely Markovian Decision Processes which are an effective tool in the modelling of the decision-making in uncertain dynamic environments. Coordination between agents occurs through communication governed by an ant colony model.

To bypass voids in sensor networks, most existing geographic routing protocols tend to route packets along the boundary nodes. Generally, a packet will be either forwarded along a void boundary by the right-hand rule or pushed back to find another route when it encounters the void. The two techniques consume more energy of boundary nodes, drop many packets and may incur data collisions if multiple communication sessions share the same boundary nodes. We propose in this paper an alternative and efficient void avoidance scheme. The proposed on-demand scheme consists of void discovery, void announce and packet rerouting steps. After discovering a void, a sender node inside the void's announce-area reroutes all data packets to get around the void in advance by selecting one appropriate forwarding side. The double objective of our scheme is to prevent data packets from traveling along the boundaries of voids and to avoid them the concave zones of voids. By achieving this objective we can reduce the energy consumption of boundary nodes and data collisions in these nodes. We can also reduce the packets rerouting overhead and the number of packets dropped by nodes on the boundaries of voids. Simulation showed the efficiency of our scheme.

Abstract Reactive routing protocols for mobile ad hoc networks reduce the routing cost in high mobility environments where link failures are frequent. However, route discovery in these protocols is typically performedvianetwork‐wide flooding, which consumes a substantial amount of bandwidth and causes a significant latency to data packets. To improve the dynamic source routing (DSR) protocol and overcome these limitations, we propose two optimization techniques,viz. generalized salvaging mechanism and cache maintenance using a distributed topology discovery mechanism through mobile ant‐agents. We show, by simulations, that our contributions improve the DSR performance, and particularly in large scale networks with high mobility and heavy load that cause frequent link failures. Copyright © 2008 John Wiley & Sons, Ltd.

Communication voids (i.e. holes) have negative impact on real-time routing protocols. To decrease both routing distance and energy consumption in large-scale sensor networks for real time applications, we propose in this paper a novel routing mechanism to make data packets avoid meeting voids in advance. After discovering boundary nodes of a void, our mechanism calculates and announces the center of the void to all nodes inside a circular area around the void. A sender node inside the announce area, at n-hops far from the boundary nodes, uses this information to obtain the appropriate forwarding region and starts countering the void in advance. For that, the sender node selects its forwarding candidate neighbors according to its already obtained forwarding region. The proposed mechanism is fairly simple to implement and saves sensor network resources.

To avoid the negative impact of void areas on real-time routing efficiency, we propose in this paper an oriented void avoidance scheme for wireless sensor networks. To select the forwarding region around a void (either clockwise or anticlockwise), the proposed scheme is guided by the target location with respect to the center of the void. Our scheme uses the right-hand rule to discover boundary nodes of the void and geometric formulas to obtain the forwarding region of a sender node located at 1-hop near the void. This node reduces its set of forwarding candidate nodes according to its already obtained forwarding region. Proposed approach is simple to implement, economic and could incorporate various other optimizations studies. Simulation showed the importance of this module and gives better performance compared to traditional schemes.

The packet scheduling in routing base station plays an important role in the sense to achieve QoS differentiation and to optimize the queuing delay, in particular when this optimization is accomplished on all base stations of a path between source and destination. In a dynamically wireless changing environment, a good scheduling discipline should be also adaptive to the dynamic traffic conditions. To solve this problem we use a multi-agent system in which each agent tries to optimize its own behaviour and communicate with other agents to make global coordination possible. This communication is done by mobile agents. In this paper, we adopt the framework of Markov Decision Processes applied to multi-agent system and present a pheromone-Q learning approach which combines the standard Q-learning technique with a synthetic pheromone that acts as a communication medium speeding up the learning process of cooperating agents.

In the last decade, due to emerging real-time and multimedia applications, there has been much interest for developing mechanisms to take into account the quality of service required by these applications. One of these mechanisms consists to integrate simultaneously many criteria of quality of service (QoS) in routing decision. Efficient routing of information packets in dynamically changing communication network requires that as the load levels, traffic patterns and topology of the network change, the routing policy also adapts. We propose in this paper an approach used an adaptive algorithm for packet routing using reinforcement learning called AV-BW Delay Q- Routing. This approach is based on earlier developed K-Optimal path Q-Routing Algorithm (KOQRA) which optimizes simultaneously two additive QoS criteria: cumulative cost path and end-to-end delay. The approach developed here adds a third criterion to KOQRA regarding residual bandwidth. This proposed technique uses an inductive approach based on trial/error paradigm combined with swarm adaptive approaches. The whole algorithm uses a model combining both a stochastic planned pre-navigation for the exploration phase and a deterministic approach for the backward phase. Numerical results obtained with OPNET simulator for different levels of traffic's load show that AV-BW Delay Q-Routing improves clearly performances of our earlier KOQRA.

High speed modern communication networks are required to integrate and support multimedia application which requires differentiated Quality-of-Service (QoS) guarantees. Routing mechanism is a key to success of future communication networking. However, it is often complicated by the notion of guaranteed QOS, which can either be related to time, cost, packet loss or bandwidth requirements. Communication network requires that as the load levels, traffic patterns and topology of the network change, the routing policy also adapts. In this paper, we present a QoS based routing to construct dynamic state-dependent routing policies. The proposed algorithm used a reinforcement learning paradigm to optimize two QoS criteria: cumulative cost path based on hop count and end-to-end delay. Multiple paths are searched in parallel to find the N best qualified ones. In order to improve the overall network performance, a load balancing policy is defined and depends on a dynamical traffic path probability distribution function. The performance of our algorithm for different levels of traffic’s load is compared experimentally with standard optimal path routing algorithms for the same problem.

QoS routing in a wireless sensor network is difficult because the network topology may change constantly, and the available state information for routing is inherently imprecise. Ever more complex sensors have become available to create and maintain situational awareness during missions. Choosing the most suited sensor for the execution of a sensor function is based on sensor capabilities and function attributes. To increase performance of the entire sensor network, the total set of sensors should be scheduled in a single system. This paper puts forward for scheduling prioritised tasks in sensor networks. Use a reinforcement learning formalism to optimise the set of schedules. In this paper, node actively infer the state of other nodes, using a reinforcement learning based more particularly Q-learning, thereby achieving high throughput by improving the delay for a wide range of traffic conditions.

The goals of QoS routing are in general twofold: selecting routes with satisfied QoS requirement, and achieving global efficiency in resource utilization. The prediction of these goals in real time is quite difficult, making the effectiveness of "traditional" protocols based on analytical models questionable. In this paper we first discuss some key design considerations in providing QoS routing support, and present a review of previous work addressing the problem of route selection in interaction with QoS constraints. We then devise a solution based on swarm intelligence paradigm based on reinforcement learning approach that we find more adapted for this kind of problems. Finally, we discuss some possible future directions for providing efficient QoS routing mechanisms in wireless ad hoc networks.

In the few last years, there is an increasing need of QoS guaranties for multimedia applications in mobile ad hoc networks. Therefore, routing protocols designed for mobile ad hoc networks must be adapted to support such needs. While several QoS routing protocols were proposed, adaptive routing has not be enough exploited. We focus in this paper on delay oriented adaptive routing in mobile ad hoc networks. Our solution does not assume that network is synchronized. We integrate a mean delay estimation model at each node in our protocol. Adaptive mean delay routing (AMDR) protocol proposed in this paper uses two kinds of exploration packets having the task of gathering delay information of available paths and updating probabilistic routing tables. To reduce the overhead of our approach we introduce the use of a new MPR mechanism based on delay.

As routing mechanism is a key to success of future communication networking, computing constrained shortest paths is fundamental to some important network functions such as QoS routing or traffic engineering. The problem is to And feasible paths satisfying QoS requirements and optimizing resource usage and degrading gracefully during periods of heavy load. This paper introduces a Quality of Service (QoS) routing protocol aimed to offload congested links while optimizing end-to-end delay. The proposed algorithm, called NOPAR "N-best Optimal Paths Ant Routing", extends the earlier N best Optimal path Q Routing Algorithm (NOQRA) by integrating the exploration and reinforcement function inspired by Ant Colony Optimization approaches. NOPAR uses a model combining both a stochastic planned pre-navigation for the exploration phase (forward ant) and a deterministic approach for the backward phase (backward ant). The introduced algorithm is compared with earlier version of NOQRA and the well-known routing algorithms such as SPF or OSPF. The performance analysis under simulation environment using OPNET demonstrates that NOPAR performs better than the classical approach especially over load high networks or link failures conditions.

Routing is a relevant issue for maintaining good performance and successfully operating in a network. We focused in this paper on neuro-dynamic programming to construct dynamic state-dependent routing policies which offer several advantages, including a stochastic modelization of the environment, learning and evaluation are assumed to happen continually, multi-paths routing and minimizing state overhead. This paper describe an adaptive algorithm for high speed irregular packet routing using reinforcement learning called N Q-routing Optimal Shortest Paths (NQOSP). In contrast with other algorithms that are also based on Reinforcement Learning methods, NQOSP is based on a multi-paths routing technique combined with the Q-Routing algorithm. In this case, the exploration space is limited to N-Optimal non loop paths in term of hops number (number of routers in a path) leading to a substantial reduction of convergence time. We propose here a framework to describe our algorithm and focus to improve scalability, robustness of our approach. We also integrate a module to compute dynamically a probability in order to better distribute traffic on best paths. The performance of NQOSP is evaluated experimentally with OPNET simulator for different levels of traffic’s load and compared to standard shortest path and Q-routing algorithms on large interconnected network. Our approach prove superior to a classical algorithms and is able to route efficiently in large networks even when critical aspects, such as the link broken network, are allowed to vary dynamically.

We present a neural prediction system for on-line writer-independent character recognition as a first step towards a word recognition system. The input feature vectors contain the pen trajectory information, recorded by a digitizing tablet. Each letter is modeled by a variable number of predictive neural networks, depending on its length. Successive parts of a letter are modeled by different multilayer neural networks, only transitions from each one to itself or to its right neighbors being permitted. To deal with the great variability of cursive handwriting, we introduce a holistic approach for both learning and recognition, combining neural networks and dynamic programming techniques. Our system is able to recognize strongly distorted and truncated letters, obtained by automatic segmentation of 10000 words from 10 different writers. Even on such databases, inappropriate to character recognition (letters in it were not recorded as handwritten isolated characters), quite good recognition rates are obtained.

We describe a general formalism for training neural predictive systems. We then introduce discrimination at the frame level and show how it relates to maximum mutual information training. Finally, we propose an approach for performing discrimination in predictive systems at the sequence level, it makes use of N-best sequence selection. The performance for acoustic-phonetic decoding showed a 77.4% phone accuracy on the 1988 version of the TIMIT database.

The authors present a neural predictive system for on-line writer-independent character recognition. The data collection of each letter contains the pen trajectory information recorded by a digitizing tablet. Each letter is modeled by a fixed number of predictive neural networks (NN), so that a different multilayer NN models successive parts of a letter. The topology of each letter-model only permits transitions from each NN to itself or to its neighbors. In order to deal with the great variability proper to cursive handwriting in the omni-scriptor framework, they implement a holistic approach during both learning and recognition by performing adaptive segmentation. Also, the recognition step implements interactive recognition and segmentation. The approach compares neural techniques combined with dynamic programming to its extension to the hidden Markov model (HMM) framework. The first system gives quite good recognition rates on letter databases obtained from 10 different writers, and results improve considerably when one considers the extension of the first system to the durational HMM framework.

Presents improvements to neural predictive systems for acoustic-phonetic decoding. They allow to raise the performances of these systems close to the state of the art. Important increases have been obtained through carefully selected discriminant criteria.>

Using two speech recognition tasks, the authors compared the performance and behavior of time delay neural networks (NN), learning vector quantization, and a modular architecture. This set of experiments makes it possible to investigate the capabilities of the models and demonstrate some of their weaknesses. Good performance was obtained through the use of sophisticated architectures which encompass the limitations of more basic NN models. This is particularly clear for a phoneme experiment where it was possible to increase the performances until they were far better than those of traditional classifiers. This improvement was obtained in successive steps by using modified cost functions or algorithms and building a combined architecture. These results illustrate that current NN algorithms can be greatly improved. Modular architectures like the one used are a promising way to do this.>