International audience

Forecasting future trajectories of pedestrians and vehicles is necessary for safety and efficiency maximization in connected and autonomous vehicle (CAV) networks. Existing federated learning (FL) approaches face challenges related to scalability, communication overhead, and privacy preservation. To address these challenges, we introduce a multi-level Hierarchical Decentralized Federated Learning framework tailored for trajectory prediction.Our approach organizes clients into a layered hierarchy, where communication is restricted to parent and child nodes, and synchronization across layers is both controlled and periodic. This design reduces redundant message exchanges while maintaining model consistency. We evaluate our method on two real-world trajectory datasets, Intersection Drone Dataset (inD) and Highway Drone Dataset (highD), and show that it achieves prediction accuracy comparable to Centralized Federated Learning (CFL) while reducing communication costs by approximately 25%. Our results demonstrate that hierarchical structuring in decentralized FL offers a scalable, privacy-preserving, and communication-efficient solution for real-world trajectory forecasting.

One of the goals of a PKI (Public Key Infrastructure), which is ubiquitous in our systems and networks, is to be able to create a trusted association — represented by a certificate — between a public key and an entity; It is however, of the same importance, to be able to revoke this trust. A major challenge is to efficiently share the revocations that took place. Two existing and widely used methods are presented: certificate revocation lists (CRLs) and the Online Certificate Status Protocol (OCSP). Both mechanisms can be optimized but have limitations, especially due to their cumbersome nature. In this article, a new encoding scheme (LightyCoding) is proposed, which is no longer based on the historical ASN.1 standard, and which offers a lightweight structure and improved performance. We describe its structure and functioning before proceeding with tests. The results are a significant reduction in CRL size of around 50% for most uses and 30% for OCSP, but still containing the same useful data as an ASN.1-encoded revocation. We also describe techniques implemented in our encoding to ensure frontand backward-compatibility, facilitating integration and use.

Enforcing the forgetting (or unlearning) of specific portions of a neural network's (NN) memory is necessary for both security and ethical considerations. Moreover, targeted forgetting can enhance the network's performance by eliminating the learning derived from compromised data. Conventional approaches, such as retraining the model from scratch, are associated with significant time and energy costs, while alternative methods can degrade the neural network's performance in terms of complexity and predictive accuracy. To address these challenges, this work introduces two novel approaches that mitigate the drawbacks associated with traditional unlearning methods. Both approaches leverage the Long Short-Term Memory (LSTM) network, chosen for its superior learning quality and efficient processing time—crucial factors in such algorithms. The first approach involves modifying the LSTM architecture by coarse tune the weight matrix of the forget gate to facilitate controlled forgetting. The second approach follows the idea of intruders by inducing poluuted data to the system, and the idea is based on learning the model through corrupted/bad data, which causes the LSTM memory to be changed at specific time intervals that correspond to the data that should be forgotten. We present a performance evaluation of the second approach, with a future study planned for the performance assessment of the first approach. The evaluation demonstrates the superiority of the proposed solutions in terms of quality of service and implementation simplicity.

Offline Reinforcement Learning (RL) methods constrain the policy to align with the behaviour policy, mitigating extrapolation errors caused by out-of-distribution (OOD) actions. Implicit Q-Learning (IQL), a popular offline RL algorithm, leverages expectile regression and introduces an in-sample learning paradigm that enhances the policy evaluation stage without querying OOD actions. However, the crucial parameter$T$for expectile regression in IQL is fixed, limiting both its performance and flexibility across diverse datasets. In this paper, we propose Cos-IQL, an improved IQL approach based on cosine similarity, which optimizes the policy evaluation function by measuring the cosine similarity between the policy and the behaviour policy. Cos-IQL is essentially a multi-step offline RL algorithm but retains the advantages of in-sample learning, thus avoiding the risks of OOD actions. In addition, Cos-IQL can adaptively adjust parameter$T$without elaborate fine-tuning. We evaluate Cos-IQL on D4RL benchmark datasets and compare its performance against recent competitive offline RL algorithms. Experimental results show that Cos-IQL achieves state-of-the-art performance.

Balancing sustainable energy with cellular deployment can be challenging. However, multi-user MIMO antennas for dynamic positioning can benefit both objectives. This study presents an optimization algorithm leveraging dynamic drone deployment to alleviate cellular communication congestion in densely populated areas. Two deployment strategies are examined: prioritizing energy efficiency by minimizing antenna footprint, and optimizing service quality by placing serving offloading drones. A novel Voronoi planning tool models both approaches, aiding in estimating energy consumption across various scenarios, particularly in the context of modern multi-user massive MIMO and beamforming techniques. A comparative energy analysis for different techniques is conducted, along with establishing a theoretical minimal coverage antenna footprint.

Interest in applying Reinforcement Learning (RL) to Autonomous Vehicles (AVs) is experiencing a rapid and substantial expansion. Proximal Policy Optimization (PPO), a well-known RL algorithm with two versions, is simple to implement and has a high level of generality. In this paper, we first analyze the issues in each of the original PPO versions: asymmetric penalty in the Adaptive KL Penalty Coefficient PPO version, gradient loss and pessimistic estimate in the Clipped PPO version. Therefore, we propose three improved PPO algorithms: Adaptive JS Penalty Coefficient PPO, Leaky PPO, and Parametric PPO. To validate the effectiveness of the proposed algorithm, we generated three autonomous driving scenarios in the Metadrive simulator. Experimental results demonstrate that Leaky PPO outperforms the other five PPO variant algorithms in various autonomous driving simulation scenarios. Furthermore, we demonstrate that the Leaky PPO outperforms other popular RL algorithms and achieves state-of-the-art performance.

Our main objective in this work is to address the challenge of enhancing the forecasting of agents trajectories for Connected and Autonomous Vehicles (CAVs) while prioritizing privacy. We introduce an innovative approach to Federated Learning tailored to the contextual aspects of trajectory prediction. We employ the Siamese Neural Network (SNN) to capture context similarities between clients’ environments. Subsequent cluster formation employs SNN to group clients with similar static contexts for federated training, enhancing learning efficiency.Results of our experiments on real-world datasets collected from the highway drone dataset (highD) and the intersection drone dataset (inD) combination, quantified by utilizing wellestablished metrics such as Average Displacement Error (ADE) and Final Displacement Error (FDE), validate the effectiveness of our approach, obtaining superior trajectory prediction capabilities, showcasing the successful alignment of Federated learning with the intricate challenges of trajectory forecasting, all while prioritizing privacy.

Trajectory prediction has been identified as a challenging critical task for achieving full autonomy of the connected and autonomous vehicles (CAVs). Despite the advancement of communication technologies, only few studies include the connectivity and data exchange aspects. Thus, we introduce a novel Edge-Assisted clustering architecture that takes advantage of recent deep learning models and the evolution of edge technologies to achieve better forecasting. First, the historical positions of the target vehicles are fed into the base models of all CAVs in the scene, resulting in multiple generated predictions. Then, each prediction is transmitted to an edge server where trajectories clustering is performed using DBSCAN algorithm to obtain multiple partitions with similar trajectories. The largest cluster is averaged then broadcast back to all CAVs in the scene. Our proposed method surpasses state-of-the-art results on the real world trajectory prediction nuScenes vehicles dataset, obtaining better predictions up to 21%. We also demonstrate the robustness of our method against single-agent system failures, succeeding to get very satisfactory results due to our ability to detect outliers. System practicality is studied under the current 5G/6G capabilities.

In the context of densifying the mobile network in urbanized areas, it is a common practice to increase the capacity by updating existing cell sectors. This paper studies upgrades consisting in adding new cellular frequencies on existing sectors. Using historical data aggregated at sector level spanning over 18 months, we proposed methods to i) following a sector upgrade, evaluate the trending growth rates of resource availability and of the proportion of resource usage per user of already existing cells, ii) use machine learning to predict this trend given the sector existing frequencies, planned frequencies to be added, previous performance indicators and urban fabrics, iii) prioritize cell deployments by computing a predictive score based on the previous predictions. To evaluate the efficiency of machine learning methods, gradient boosting, random forest and SVM models were compared with a baseline, using several metrics. The baseline model was designed to predict the traffic activity evolution as the mean evolution of the same added and existing configurations seen in the training set. This baseline was beaten by all the models trained with our methods. The ranking made by the best ML models had an average precision higher than the baseline by 0.19, a reciprocal rank higher by 0.11 and normalized discounted cumulative gain higher by 0.12.

The real implementation of a recurrent neural network (RNN) in a low complexity IoT device is evaluated in order to predict the time series of power consumption in tertiary buildings. The RNN type long short-term memory (LSTM) algorithm is adapted for a 32-bit microcontroller unit (MCU) and the backpropagation (BP) algorithm is implemented in-house. We therefore demonstrate that Intelligent IoT (IIoT) devices, such as the Espressif ESP32 MCU, not only implement neural networks (NNs), but also learn on their own. The resulting IIoT architecture has been proven to operate efficiently and compared to the traditional computer-based learning platform. The selected results confirm that stand-alone IoT devices are a truly efficient solution that adds flexibility to the architecture, reduces storage and computation costs, and is more energy-friendly. As a conclusion, it is practically more efficient to exploit low-power and processing-time IIoT for our prediction use case rather than relying on server based distributed systems.

Two models are proposed to optimize unmanned aerial vehicles (UAVs) traffic offloading in cellular networks. The first model optimizes the realtime traffic service, while delaying non-realtime traffic in the cell buffers (BS and the currently serving drone). Delayed traffic is then transmitted later when free resources are available and has a maximum service delay limit. The proposed model provides a heuristic solution to minimize the losses in non-realtime traffic based on the maximum delay and the size of the cell buffers. The second model completes the work by providing an optimal Integer Linear Programming solution to minimize the number of needed UAV assuming no data loss and buffering availability. It is also parameterized with the same delay limits as the first model. The performance of the proposed models is studied using the call detail record (CDR) dataset of the city of Milan cellular network provided by Telecom Italia. The two models showed great QoS performance based on the maximum delay of non-realtime traffic and cell buffer size compared to models that do not include the buffering and the delay limits.

Base station (BS) capacity for cellular networks is fixed and therefore cannot be easily adapted to support temporary high demands due to unusual traffic (demonstration, sales, competitions, etc.). Unmanned Ariel Vehicle (UAV)/drone can be used as an additional temporary bandwidth (BW) provider capable of covering multiple cells.Two placement approaches are investigated to optimize UAV deployment for this purpose. The first adopts a rule based approach without cooperation: we place UAVs in the cells where the exceeding demand is the highest, allowing each UAV to only serve a single cell at a time. In the second algorithm, relying on the Knapsack problem, we design a solution where UAVs cooperate by sharing a portion of their available BW with neighbouring cells in order to cover all the demand with the lowest possible amount of drones. Their performance is compared using two months of real dataset from the Milan Cellular Network provided by Telecom Italia.

Due to the rapid increase of connected devices and network traffic, the data transport from end-user devices to destination (connected device, cloud, edge servers, etc) can be interrupted because of obstacles and problems. In this paper, we propose to integrate edge servers with the intelligent reflecting surface (IRS) in a vehicular edge computing (VEC) environment. The IRS is deployed in fixed places inside the city (fixed IRS-Edge Nodes) and in taxis and buses (mobile IRS-Edge Nodes), where it is used for both reflecting signals and executing the different client vehicles' tasks. We propose an Optimal IRS-Edge Selection (OIES) model to select the optimal IRS-Edge Node(s) that satisfy the client vehicles' requirements. Moreover, we propose an Efficient IRS-Edge Selection (EIES) algorithm to deal with the high number of client vehicles in dense networks. The numerical results demonstrate the efficiency and the feasibility of the proposed solution.

Cellular deployment of new generations faces a coverage challenge due to the non-line-of-sight (NLOS) between clients' devices and base station (BS). Therefore, relaying on using the emerging technology; intelligent reflective surface (IRS) to reconfigure wireless signal propagation is considered the best solution that can address the mentioned challenge. Additionally, choosing the position of the IRS is not an easy task as the clients are mobile. Hence, there is a need for an efficient model to elect the best positions of the IRSs for a better network performance. In this work, two fold model is proposed to provide an automated solution to optimize IRS positions. The first one is the mixed integer linear programming (MILP) that solves the IRS positions problem in a classical way. Whereas the second one is based on the reinforcement learning optimization (RLO) with complex encoder and decoder network architecture to provide fast learning of the MILP results with a low mean square error. The proposed RLO model's validity is studied using 10 days of mobile dataset and actual cellular BSs' positions in the city of Rome (Italy). This study is based on the use of long short term memory (LSTM) and gated recurrent unit (GRU). The results show a significant performance of the proposed model based on LSTM compared to GRU.

The development of vehicular technologies and infrastructures leads to development in mobility handling for wireless communications. Improving connectivity establishment and reliability became an issue, especially for vehicles that may move out of antenna coverage during connection establishment. This paper focuses on improving LoRaWAN connectivity for roaming devices by combining a machine learning predictor and DNS prefetching to gather information necessary for connection establishment before the device comes under coverage, thus reducing the overall latency for connection establishment. The paper also relates to other issues by comparing the solution with other approaches and studying antenna occupation.

Several reinforcement techniques are compared to take control of Unmanned Aerial Vehicles (UAVs) and optimize communication offloading in cellular networks. Navigation actions are calculated to send the drones to the required position and turn them back when not needed. First, a use case is expressed and solved in form of a linear programming problem (ILP). Then, a Q learning algorithm is designed and evaluated to solve the same problem. Finally, a deep neural network based on Long Short Term Memory recurrent networks is used. The results of the three approaches are obtained with a real dataset extracted from the CDRs (Call Detail Records) in Milan city, Italy. It is shown that Q learning needs long convergence times to succeed to approach the ILP optimal results. Also, we demonstrate that deep neural network techniques learn much faster and mimic the ILP with very high scores.

Many studies have shown how to process mobile network data with machine learning algorithms to infer land uses or predict mobile traffic behavior. However, there are few, if any, machine learning applications to help deploy new cells. Current forecasting models are designed to predict the traffic of existing cells based on the historical data they produced. In a previous work, we have proposed a method to predict the class activity of a future cell, given its modeled area, demographic and geographic features. In this paper, we extend it by estimating static hour-by-hour median weekly activity aggregated at base station level, based on the same static inputs. We tested several machine learning models including transformers, compared their results and showed that our method beats simple baselines.

An AI based energy management system (EMS) for microgrids is proposed. It is composed of three modules: a strategy based module, a deep learning (DL) and a reinforcement learning module (RL). This framework determines heuristically the optimal actions for the microgrid system under different time-dependent environmental conditions. In essence, a main innovation is applied to the EMS. Our deep learning algorithm uses recurrent neural networks (RNNs) instead of the habitual State Action Reward (SAR) approach (whether classical or deep). Learning is hence guided by successful actions rather than by blind exploration. A large improvement in learning rates is hence observed when compared to classical Q-learning on real datasets that present a large diversity in energy consumption profiles, acquired in French premises over a long period. It leads to question about the best appropriate reinforcement policies to adopt when solving large state environments.

High Dynamic Unmanned Aerial Vehicles (UAVs) are introduced to assist V2X networking and communication that requires ultra low latency and safety requirements (ULLC). In this paper, we propose a Follow Me UAV (FMU) architecture that aids Vehicular Edge Computing for service offering. Then, a communication protocol is proposed and associated with placement, routing, and optimization algorithms in small and dense networks (OFMU and AFMU). We use deep learning techniques (LSTM and GRU) to predict the connected vehicles trajectory, then the results are used to feed the optimization models. Then, we clarify through Reinforcement Learning based implementations autonomous UAV path planning. Optimization approaches are implemented and evaluated under different quality and computing scenarios. Then, the models are quantified under UAV selection time and energy cost. Results prove the feasibility of the optimization algorithms and suggest the use of mobile UAV as low latency edge servers for service offering.

Transfer learning (TL) is a useful technique that enables the wide spreading of neural networks after re-adaptation of their weights. In ths paper, two methods are introduced for transfer learning of recurrent neural networks: D-LSTM (Long Short Term Memory with deep layers) and CNN-1D (Convolutional Neural Network of One Dimension). The first is used to improve the prediction of time series when datasets are too small to obtain satisfactory results. The second enables personalizing and hence re-adaptation of an already-trained network to a new class of time series. In fact, the CNN-1D classification is applied to those real datasets to classify different behaviors in a large city. We show that our architecture drastically improves prediction when transfer learning is used in the same class of behavior but also on different classes of behaviors.

Service Function Chains (SFC) orchestration is necessary to optimize the use of computing resources and improve the performance of the overall virtualized functions in terms of system resources cost reduction and high quality. It requires intelligent joint chaining and placement algorithm due to the evident huge amount of traffic to be delivered to end customers of the network. In this paper, a global SFC architecture and an exact approach for finding the optimal SFC components instantiation(s) (OPC) are proposed. Then, a deep reinforcement learning (DRL) approach is formulated to deal with a huge number of SFC instances. Moreover, several scenarios are considered to quantify the behavior of OPC and DRL approaches. We compare their efficiency in terms of processing cost and orchestration time. Then, different deployment flavors are implemented and assessed. To study the algorithm’s behavior and to quantify the impact of the system, novel use cases are considered. Results prove the feasibility of the exact approaches in small network scale. Still, the DRL techniques act as an heuristic approaches for chain placement in dense networks.

The emergence of new vehicles generation such as connected and autonomous vehicles led to new challenges in the vehicular networking and computing managements to provide efficient services and guarantee the quality of service. The edge computing facility allows the decentralization of processing from the cloud to the edge of the network. In this paper, we design and propose an end-to-end, reliable and low latency communication architecture that allows the allocation of compute-intensive autonomous driving services, in particular autopilot, to shared resources on edge computing servers and improve the level of performance for autonomous vehicles. The reference architecture is used to design an Advanced Autonomous Driving (AAD) communication protocol between autonomous vehicles, edge computing servers, and the centralized cloud. Then, a mathematical programming approach using Integer Linear Programming (ILP) is formulated to model the autopilot chain resources Offloading at the network edge. Further, a deep reinforcement learning (DRL) approach is proposed to deal with dense Internet of Autonomous Vehicle (IoAV) networks. Moreover, several scenarios are considered to quantify the behavior of the optimization approaches. We compare their efficiency in terms of Total Edge Servers Utilization, Total Edge Servers Allocation Time, and Successfully Allocated Edge Autopilots.

Strong spatial relationships exist between call volume and human activities. In this paper, we show machine learning models can classify base station coverage areas into classes of mobile call profile based on areas geographic and demographic properties. We propose the novel approach of taking clustered Call Detail Records (CDR) based time series as ground truth, and passing heterogeneous features as inputs. These features were land use and points of interest retrieved from OpenStreetMap database, and demographic data provided Facebook Research. Together, they allowed the creation of a representation of urban fabric. CDR clusters were then characterized by these features through SHAP model interpretation. Three models were tested in the region of Dakar with CDR coming from D4D-Senegal Challenge. Results exceeded the accuracy of systematic most common class classification and the accuracy of models trained only on population dataset. Additionally, models generalization capacity were evaluated in Thies, with results equalling those of the baseline.

LPWANs are networks characterized by the scarcity of their radio resources and their limited payload size. To extend the efficiency of the data transmission by decreasing the traffic sent from sensors, this paper proposes a lossy compression method using known ML techniques. We embedded a pre-trained neural network directly on constrained LoRaWAN devices and we tested the trade-off between compression ratio and accuracy of the compression algorithm. This paper studies multiple aspects of the system - energy consumption, error rate due to the lossy compression, compression ratio and the impact of LSTM parameter quantization - to measure the possible strengths and weaknesses of using a dual prediction system in order to reduce transmission costs. Surprisingly, machine learning used in this context does not consume a lot of energy and it even leads to energy saving in the very constrained devices which are the sensors.

Unusual Spatio-Temporal fluctuations in cellular network traffic may lead to drastic network management misbehaviors and at least abnormal drops in quality of experience. It is also expected that the management of future cellular networks will mostly rely on machine learning and automation. In this article, we present a dynamic on-line data mining technique to detect these network anomalies allowing, network operators to pro-actively monitor and control a variety of real-world phenomena with less damage to the overall experience. To overcome the network performance degradation that can occur in real time, the network manager must imperatively and instantly identify abnormalities and hence provide a better continuous quality of service for the subscribers. Based on real cellular communication traces, we propose an automated framework, called STAD, ensuring spatio-temporal detection outliers using a combination of machine learning techniques including One-class SVM (OCSVM), Support Vector Regression (SVR) and recurrent neural networks, Long Short-Term Memory (LSTM). STAD is double checked with two real datasets of CDRs where results show high accuracy compared to the Isolation Forest and Auto-Regressive Integrated Moving Average (ARIMA) models.

Maximum Concurrent Flow techniques try to combine a maximum flow graph resolution and the satisfaction of queries on this graph. They are proven to give better performance over classical heuristic data-source placement methods combined with greedy query resolution. A new version of the MCF approach is proposed and examined. It is tailored to provide MCF properties for large IoT networks. The results found from evaluation and comparison with other algorithms show that it has high efficiency and outperforms many recent solutions.

We propose to utilize rideshare taxis as infrastructure for both communication and computation. Rideshare overlays become hence Mobile Edge Nodes. End-users utilize near rideshare taxis as edge servers to receive video chunks for live video streaming. The set cover problem (SCP) is used to formulate the rideshare taxis coverage optimization inside the city. It provides the maximum number of rideshare taxis that cover end-users routes which guarantee the efficiency of communication services. Simulation results show that the proposed architecture dramatically enhances the quality of service and the overall communication performance in terms of execution time and energy consumption.

This paper presents a framework based on the data analysis concept to automate the management of resources in cellular networks. Three processes are defined: identifying and detecting anomalies, analyzing the causes, and triggering adequate recovery actions. First, the proposed solution executes Deep Learning algorithms to forecast the normal behavior of the network and defines dynamic thresholds. Then, it identifies cells with peak demands and raises alarms if the measured real-time data exceeds the threshold values. Second, we define QoS optimization methods to proceed with suitable design for resource allocation as well as fault detection and avoidance. Hence, we distinguish three cases and define two classes of data: Real-time and non-real-time traffic. This solution is applied to a pre-analyzed semi-synthetic real dataset extracted from the CDRs (Call Detail Records) in Milan city, Italy. This dataset contains the Internet activity records of two months in three areas. The preliminary results elucidate the feasibility and preeminence of our proposed anomaly detection framework.

With the emergence of the Internet of Things (IoT) applications, a huge amount of information is generated to help the optimization of operational cellular networks, smart transportation, and energy management systems. Applying Artificial Intelligence approaches to exploit this data seems to be promising. In this paper, we propose a dual deep neural network architecture. It is used to classify time series and to predict future data. It is essentially based on Long Short Term Memory (LSTM) algorithms for accurate time series prediction and on deep neural network, classifiers to classify input streams. It is shown to work on different domains (cellular, energy management, and transportation systems). Cloud architecture is used for IoT data collection and our algorithm is applied on real-time energy data for accurate energy classification and prediction.

The emerging of the internet of things (IoT) led to increasing the computation resources required to satisfy a large number of requests from the connected devices, for this the Cloud Computing (CC) allows the processing of requests in the cloud to guarantee the efficiency of services for end-users. The main problem of the current CC architecture is the latency in real-time applications such as video streaming, which require a distributed architecture to support the future generation of applications. The Mobile Edge Computing (MEC) provides a fully distributed architecture where a part of processing executed in the edge of network which supports the requirements of IoT applications. In this paper, we propose to use the connected devices as on-demand virtual edge servers to provide computation services close to endusers where each submitted task is divided into a set of sub-tasks, each one can be executed by any other device which is a part of the virtual edge server according to the available resources in the selected device. In this context, we have formulated the partitioned and the offloading problem in MEC environment using linear programming techniques. Optimal Partitioned and Offloading (OPO) algorithm that allocates network, storage and computing resources to user application sub-tasks with respect to MEC constraints and user quality requirements is modeled, implemented, and evaluated. Results show the feasibility and efficiency of the proposed algorithms.

The Internet of Things (IoT) is a network of billion of objects. Data streaming over IoT network is a tedious task that requires intelligent flow management and steering. In this paper, we propose a Distributed Maximum Concurrent Flow (DMCF) algorithm to solve the problem of distributing massive IoT video/data to large consumers over IP/data-centric networks. We propose two approaches based on graph theories, and using reinforcement learning techniques. The proposed approaches are implemented and evaluated over different complex graphs. Results show that in large graphs, reinforcement learning methods outperform classical graph theoretic ones.

The need to integrate flexible and intelligent mechanisms for energy management becomes a necessity. In this paper, we are considering a microgrid with infrastructures having production capacities and consumption needs. Several data and constraints related to the microgrid consumption have been collected, in addition to data concerning the production of renewable energy from Photovoltaic panels (PV). Data history is used as input to a neural network to predict one day ahead of consumption and production. Then, a prioritized scheduling family of algorithms is presented. First, we introduce a mathematical formulation to our problem. Then, we propose various scenarios that go from an exact solution to heuristic-based use cases, including scheduling of several energy classes with a maximum scheduling time lapse. Results show that prioritized scheduling, including time lapse based on predictions, can give more reliable results than scheduling based on bin packing.

The emergence of a new generation of applications led to the appearance of new challenges that represent improvements in current communication technologies. For this, a new network paradigm's including edge computing that allows the process of data at the edge of the network. And the 5G network slicing that represents a new generation of communication increases the capacity of mobile networks by supporting the slicing technology that allows virtual “cutting” of a telecommunications network in several slices that provide high performance in terms of bandwidth and latency. Slice allocation and placement is an important networking optimization task that still painstakingly tune heuristics to get a sufficient solution. These algorithms use data as input and outputs near-optimal solutions. Thus, we are motivated by replacing this tedious process with the recent deep reinforcement learning algorithms. In this paper, we propose three approaches for Virtual Network Functions (VNFs) slices placement in edge computing (Integer linear programming (ILP), reinforcement learning (RL), and deep reinforcement learning (DRL)). Then they are implemented and evaluated. Several scenarios are considered to study the behavior of the algorithms and to quantify the impact of network size. The results show the feasibility and efficiency of the proposed techniques in terms of server utilization, placement time, and energy consumption.

Drone-cell technology is emerging as a solution to support and backup the cellular network architecture. cell-drones are flexible and provide a more dynamic solution for resource allocation in both scales: spatial and geographic. They allow to increase the bandwidth availability anytime and everywhere according the continuous rate demands. Their fast deployment provide network operators with a reliable solution to face sudden network overload or peak data demands during mass events, without interrupting services and guaranteeing better QoS for users. With these advantages, drone-cell network management is still a complex task. We propose in this paper, a multiagent reinforcement learning approach for dynamic drones-cells management. Our approach is based on an enhanced joint action selection. Results show that our model speed up network learning and provide better network performance.

Stimulated by the emerging Internet of Things (IoT) applications and their massive generated data, the cellular providers are introducing various IoT functionalities into their networks architecture. They should integrate intelligent and autonomous mechanisms that are able to detect sudden and anomalous behavior issues. In this paper, we present an adaptive anomaly detection approach in cellular networks consisting of two parts: the detection of overloaded base-stations using machine learning algorithm (LSTM - Long Short-Term Memory) and the deployment of drones as mobile base-stations that support and back up the overloaded cells. The proposed approach is validated using real dataset extracted from the CDR of Milan combined with semi-synthetic eHealth data. Initially, The LSTM algorithm analyzes the impact of eHealth applications on cellular networks and identifies cells with peak demands. Then, drones are deployed to collect the requested data from these cells. The obtained results show that the use of drones improves the quality of service and provides a better network performance.

We propose a solution for Electric Vehicles (EVs) energy management in smart cities, where a deep learning approach is used to enhance the energy consumption of electric vehicles by trajectory and delay predictions. Two Recurrent Neural Networks are adapted and trained on 60 days of urban traffic. The trained networks show precise prediction of trajectory and delay, even for long prediction intervals. An algorithm is designed and applied on well known energy models for traction and air conditioning. We show how it can prevent from a battery exhaustion. Experimental results combining both RNN and energy models demonstrate the efficiency of the proposed solution in terms of route trajectory and delay prediction, enhancing the energy management.

Electrical vehicular (EV) energy management is a promising trend. Forecasting vehicular trajectories and delay is crucial for EV energy management. The presented work is devoted to the study and the application of deep learning techniques on specific road trajectories. First, exhaustive deep learning algorithms are considered. Second, road traces are converted to time series. Then, delays and road trajectories are analyzed. In fact, we consider two Recurrent Neural Networks (RNN): LSTM (Long Short Term Memory) and GRU (Gated Recurrent Units). Neural Networks are adapted and trained on 60 days of real urban traffic of Rome in Italy. We calculate the Loss function for both machine learning techniques which is defined by mean square error (MSE) and Root mean square error (RMSE). Experimental results demonstrate that both LSTM and GRU are adequate for the context of EV in terms of route trajectory and delay prediction.

Vehicular Ad Hoc Network has attracted both research and industrial community due to its benefits in facilitating human life and enhancing the security and comfort. However, various issues have been faced in such networks such as information security, routing reliability, dynamic high mobility of vehicles, that influence the stability of communication. To overcome this issue, it is necessary to increase the routing protocols performances, by keeping only the stable path during the communication. The effective solutions that have been investigated in the literature are based on the link prediction to avoid broken links. In this paper, we propose a new solution based on machine learning concept for link prediction, using LR and Support Vector Regression (SVR) which is a variant of the Support Vector Machine (SVM) algorithm. SVR allows predicting the movements of the vehicles in the network which gives us a decision for the link state at a future time. We study the performance of SVR by comparing the generated prediction values against real movement traces of different vehicles in various mobility scenarios, and to show the effectiveness of the proposed method, we calculate the error rate. Finally, we compare this new SVR method with Lagrange interpolation solution.

Information-Centric Networking is considered as one of the most promising architecture for IoT. The use of content-centric approach may improve the content access & dissemination, reduce the content retrieval latency, and enhance the network performance. The use of in-network caching in ICN enhances the data availability in the network, overcomes the issue of single-point failure, and improves IoT devices power efficiency. In this paper, we present a Near-ICN Cache Placement (NCP) scheme for IoT taking traffic class into consideration. NCP is designed to select the optimal replica cache by minimizing: the cost of moving the data from content producer to replica nodes, the cost of caching the content in the replica and the cost of delivery the content to consumers. Hence, we presented a multi-objective optimization problem, with a heuristic caching selection algorithm. We evaluated NCP with various performance metrics against different caching schemes. The obtained results show improvement in the cache utilization, with fast data retrieval, and enhancement in the network cache distribution & diversity.

Internet of things (IoT) is an ever-growing technological paradigm that is expected to boost the development of a plethora of services and applications like eHealth services. The massive amount of data generated by eHealth applications will be handled by the cellular architecture. Due to the additional eHealth data, cellular networks may suffer from some anomalies which need intelligent and autonomic mechanisms to be avoided. Network operators must integrate to their architecture pro-active tools able to detect and signal these anomalous patterns and then mitigate the issue of overloaded base-stations. We address in this paper the issue of eHealth services by analyzing at first their impact on cellular networks. We propose also an on-line and efficient anomaly detection technique for eHealth data based on support vector regression (SVR). Moreover, we validate our model with a real dataset of cellular call detail records (CDR) combined with semi-synthetic eHealth dataset. A realistic testbed is provided on the context of a Marathon event where mobile users are running eHealth applications.

Sharing between commercial and Federal incumbent users, such as in the 3.5 GHz band, is expected to increase the availability of spectrum for wireless broadband use. However, the spectrum coordination needed between incumbent and commercial users gives rise to several privacy concerns. This paper analyzes the vulnerability of the incumbent's operational center frequency to disclosure from inference attacks. We evaluate the inherent protection provided by two channel assignment schemes in terms of the time required for an attacker to infer the incumbent's frequency. We account for the activity of secondary users in a dynamically-shared environment. This analysis quantifies privacy for a given secondary load. It also provides an analytical framework to quantify the effectiveness of countermeasures such as limiting the query rate of secondaries.

Information-Centric Networking (ICN) is very promising for Hadoop-based distributed computing systems, where the data-centric approach is advantageous in reducing the data retrieval latency as well as the network traffic for Hadoop services. Moreover, the inherent in-network caching and computing features in ICN relaxes the end-to-end connectivity between consumers and producers (this helps networking, computation, and power efficiency as Hadoop nodes will use ICN services). Yet, building such a complex system needs new definitions and mappings on the architecture side. It needs also a flattening of the components and an optimization relative to data flow and computation performance. These issues are presented in this paper. Optimal optimization algorithms are then proposed, implemented and evaluated to improve the overall network performance. Experiments demonstrate that ICN support of Hadoop is a feasible architecture and show to improve the performance of Hadoop systems and reduce the end-to-end consumer delay.

The Information-Centric Network (ICN) is very promising in the area of Complex Active Networks (CANs), where the data-centric approach is useful in reducing the data retrieval latency as well as the network traffic of active networking services. Also, the in-network caching and processing capabilities in ICN limits the massive data access to the data producers and so relaxes the need of continuous E2E connectivity between data producers and data consumers. In this paper, we present an ICN-based architecture in which ICN nodes provide processing/treatment capabilities and caching functions. Service placement algorithms (OPPA and HPPA) in CANs are proposed to choose optimal and near-optimal placement location for ICN nodes. We evaluated the algorithms with respect to several performance metrics and the obtained results show improvement in services consumption latency and network load. Furthermore, we propose a caching strategy that shows to stabilize the network load despite any increase in the number of consumer interests.

In this paper, we present a data-driven solution to address the energy efficient routing problem in a multi-layer femtocell network. The basic idea is to divide problems into categories by the clustering of traffic demand vectors, and solve a problem by a most suitable algorithm, in terms of throughput, energy consumption and computation time, corresponding to its category. The simulation results show that, our proposed approach can achieve a similar performance in throughput and energy saving as the previous JRN algorithm, by reducing 80% computation time.

Virtual Content Delivery Network (vCDN) orchestration is necessary to optimize the use of resources and improve the performance of the overall SDN/NFV-based CDN function in terms of network operator cost reduction and high streaming quality. It requires intelligent and enticed joint SDN/NFV orchestration algorithm due to the evident huge amount of traffic to be delivered to end customers of the network. In this paper, a global vCDN architecture and an exact approach for finding the optimal path orchestration(s) and vCDN component instantiation(s) (OCPA) are proposed. Moreover, several scenarios are considered to quantify the OCPA behavior and to compare its efficiency in terms of caching and streaming cost, orchestration time, vCDN replication number, and other cost factors. Then, it is implemented and evaluated under different deployment flavors. Several scenarios are considered to study the algorithm's behavior and to quantify the impact of both network and system parameters.

Virtual Content Delivery Network (vCDN) migration is necessary to optimize the use of resources and improve the performance of the overall SDN/NFV-based CDN function in terms of network operator cost reduction and high streaming quality. It requires intelligent and enticed joint SDN/NFV migration algorithms due to the evident huge amount of traffic to be delivered to end customers of the network. In this paper, two approaches for finding the optimal and near optimal path placement(s) and vCDN migration(s) are proposed (OPAC and HPAC). Moreover, several scenarios are considered to quantify the OPAC and HPAC behaviors and to compare their efficiency in terms of migration cost, migration time, vCDN replication number, and other cost factors. Then, they are implemented and evaluated under different network scales. Finally, the proposed algorithms are integrated in an SDN/NFV framework.

Real Call Detail Records (CDR) are analyzed and classified based on Support Vector Machine (SVM) algorithm. The daily classification results in three traffic classes. We use two different algorithms, K-means and SVM to check the classification efficiency. A second support vector regression (SVR) based algorithm is built to make an online prediction of traffic load using the history of CDRs. Then, these algorithms will be integrated to a network planning tool which will help cellular operators on planning optimally their access network.

Software Defined Networking (SDN) is based basically on three features: centralization of the control plane, programmability of network functions and traffic engineering. The network function migration poses interesting problems that we try to expose and solve in this paper. Content Distribution Network virtualization is presented as use case.

Proximity services discovery using LTE-based Device-to-Device (D2D) communications has been recently in the heart of the discussions about the advent of 5G networks. Meanwhile, their related security aspects are of a major concern especially when dealing with direct radio communications and large-scale deployment of D2D. Yet, existing security algorithms and solutions are not adapted to these emerging new types of communications. This paper is focused on D2D communications' security issues in both discovery and communication phases. First, we address the global security stakes and challenges in D2D. Then, a solution based on the Identity-Based Encryption (IBE) mechanism is proposed to secure the exchanged D2D messages during the discovery and communication phases. The proposed solution is discussed under two D2D use cases and is further used to introduce an efficient key management system for group communication. Finally, a security requirements analysis is presented in order to evaluate the scalability and efficiency levels of the proposed solution.

Multi-modal traffic management in Intelligent Transportation Systems (ITS) aims to provide a more efficient traffic regulation to passengers and reduce congestion and obstruction in the roads. In spite of the outstanding progress made in this research filed; traffic management still a very challenging problem regarding the multiple factors that have to be taken into account in any proposed solution. To tackle this problem, this paper introduces a collaborative model based context awareness multi-modal traffic management aiming at providing an efficient way to manage the traffic inside a transportation station. In this model (Multi-Layers Stations: the stations that have different intersections for different means of transport), the traffic management is based on a Q-learning technique that takes into account the context awareness parameters to provide more potent decisions. The learning technique offers the opportunity to the system (transportation station) to adapt dynamically its decision (choice of the best transportation mean) based on feedbacks provided by the passengers traveling from that specified station and thus optimize their journey through the transportation network. The efficacy of our proposed technique is validated through extensive simulations for different layers of transport means like metros, trains, and buses. Our proposal holds for any ITS system decisions provided the availability of real-time traces about the passengers passing by any station.

For several years, works on cognitive radio have been published allowing to reuse TV Whitespaces. On another hand, many new results appear on user and crowd mobility due to big data recent developments, especially from cellular traces. We propose here a method for cellular resource planning taking into account user mobility. Since users move, the bandwidth resource should also move accordingly. We design a score based method using TV Whitespace, and user experience, to determine from which cell it should be removed and to which one it should be added. Combined with traffic history it calculates scores for each cell. Bandwidth is reallocated on a half day basis. Before that, real traces of cellular networks in urban districts are presented which confirm that static network planning is no longer optimal. A dynamic femtocell architecture is then presented. It is based on mesh interconnected elements and designed to serve the score based bandwidth allocation algorithm. The score method along with the architecture are simulated and results are presented. They confirm the expected improvement in bandwidth and delay per user while maintaining a low operation cost at the operator side.

This paper aims at using the novel concept of LTE-based Device-to-Device communications (D2D) as a new alternative for Intelligent Transportation Systems (ITS) vehicular communications in advanced 4G networks and beyond. We propose the Cellular Vehicular Network (CVN) solution as a reliable and scalable operator-assisted opportunistic architecture that supports hyper-local ITS services as 3GPP Proximity Services (ProSe). A distributed D2D architecture is proposed based on a hybrid clustering approach to organize vehicles into dynamic clusters. The proposed solution includes a network setup phase based on enhanced LTE authorization and authentication procedures for ITS nodes, and an LTE direct discovery phase. A BCMP queuing network is used to model the CVN core network and to evaluate the impact of core network entities load on the network setup delay. The results are validated with Matlab and compared to the network setup delays of an existing solution.

We study the problem of information dissemination in vehicular networks in this paper. Crucial information, such as traffic jamming status, is usually broadcasted inside the network. Each vehicle in the network has its own choice to either forward or drop packets for others. Although the energy consumption in general is not an issue in vehicular networks, forwarding every received packets is still not preferred as it may result in congestion in transmission. We model this problem via evolutionary game theory to investigate the cooperative behavior among vehicles. Simulation results show that, the cooperation ratio in the network is proportional to the setting of synergy factor for the evolutionary game. When nodes change their strategies according to the evolutionary game, information can be disseminated as fast as flooding scheme, while more bandwidth can be reserved.

LTE-based Device-to-Device (D2D) communications have been envisioned as a new key feature for short range wireless communications in advanced and beyond 4G networks. We propose in this work to exploit this novel concept of D2D as a new alternative for Intelligent Transportation Systems (ITS) Vehicle-to-Vehicle/Infrastructure (V2X) communications in next generation cellular networks. A 3GPP standard architecture has been recently defined to support Proximity Services (ProSe) in the LTE core network. Taking into account the limitations of this latter and the requirements of ITS services and V2X communications, we propose the CVN solution as an enhancement to the ProSe architecture in order to support hyper-local ITS services. CVN provides a reliable and scalable LTE-assisted opportunistic model for V2X communications through a distributed ProSe architecture. Using a hybrid clustering approach, vehicles are organized into dynamic clusters that are formed and managed by ProSe Cluster Heads which are elected centrally by the CVN core network. ITS services are deemed as Proximity Services and benefit from the basic ProSe discovery, authorization and authentication mechanisms. The CVN solution enhances V2V communication delays and overhead by reducing the need for multi-hop geo-routing. Preliminary simulation results show that the CVN solution provides short setup times and improves ITS communication delays.

Sensor networks suffer from limited capabilities such as bandwidth, low processing power, and memory size. There is therefore a need for protocols that deliver sensor data in an energy-efficient way to the sink. One of those techniques, it gathers sensors' data in a small size packet suitable for transmission. In this paper, we propose a new Effective Data Aggregation Protocol (DAP) to reduce the energy consumption in Wireless Sensor Networks (WSNs), which prolongs the network lifetime. This work uses in-network aggregation approach to distribute the processing all over the aggregation path to avoid unbalanced power consumption on specific nodes until they run out. Simulation results prove that DAP, compared to other protocols, achieves more data aggregation percentage and less power consumption for a one data harvesting round.

Cloud computing is very useful for improving distributed applications performance. However, it is difficult to manage risks related to trust when collaborating with unknown and potentially malicious peers. Besides, trust evaluation is the target of dishonest behaviors trying to disturb the control

Users' satisfaction is the service providers' aim to reduce the churn, promote new services and improve ARPU (Average Revenue per User). In this work, a novel hybrid assessment technique is presented. It refines known mathematical models for quality assessment using both context information and subjectives tests. The model is then enriched with new features such as content characteristics, device type and network status, and compared to the state of the art. The effect of application parameters (startup time and buffering ratio) on user perceived quality is also analyzed in this article.

Data Collection is considered as an inherent challenging problem to Vehicular Ad-Hoc networks. Here, an Adaptive Data cOllection Protocol using rEinforcement Learning (ADOPEL) is proposed for VANETs. It is based on a distributed Qlearning technique making the collecting operation more reactive to nodes mobility and topology changes. A reward function is provided and defined to take into account the delay and the number of aggregatable packets. Simulations results confirm the efficiency of our technique compared to a non-learning version and demonstrate the trade-off achieved between delay and collection ratio.

User-centric services present a new paradigm in next generation networks. The IP Multimedia Subsystem (IMS) is an access-independent IP based service control architecture proposing a new platform for user-centric services. Security and data privacy aspects observe a lot of attention in the IMS global objectives. Besides the authentication solutions proposed by the third Generation Partnership Project (3GPP), research contributions consider authentication protocols and mechanisms to enforce the security and to enhance users' access personalization for IMS based services. Performance is an important factor to be considered when designing authentication protocols. In this paper we use Open BCMP queuing network as a mathematical model to evaluate the performance of an authentication method aiming to personalize each user access. We also propose an algorithm based on clustering to improve the performance of the authentication solution. Through BCMP modeling, we present and analyze the performance of the proposed authentication solution as a first step, and then we show the performance improvement of this solution when applying the clustering algorithm.

The advances in IPTV (Internet Protocol Television) technology enable new user-centric and interactive TV model, in which context-awareness is promising in making users' interaction with the TV dynamic and transparent. This paper deals with the problem of achieving user-centric personalized IPTV services applying context-awareness. We present a solution for enriched IPTV services personalization introducing context-awareness on top of IPTV architecture on one hand to gather different information on the user and his environment and allowing each user to be distinguished to the system in a unique and real-time manner on the other hand. We implemented the proposed solution on top of an IPTV platform considering the NGN IPTV architecture as a proof of concept and as a means to evaluate the performance.

Inter-vehicle communication is considered as a major problem to vehicular environment. Here, an analytical framework is developed to investigate the reliability of end-to-end information relay process along a platoon of vehicles. The reliability of inter-vehicle communication is measured by the probability of success for information to travel to a known destination and by the required number of hops. In the models, recursive formulations are derived for the two previous criteria. Lower and upper bounds for our models are provided and computed by dynamic programming techniques. Simulation results match very well the mathematical expressions and show that the gap between lower and upper bounds is very small.

A beamforming-based broadcast technique is proposed here for VANETs. It is based on two key information: the direction to the destination and the beamforming angle θ. Simulations demonstrate the efficiency of our proposal in terms of probability of transmission success, ratio of implicated nodes and bandwidth gain. An analytical model is derived to calculate the forwarding transmission area. Simulation results match very well the mathematical expressions and show that the analytical model is precise.

Cooperative communication for wireless networks has been extensively investigated from the perspective of physical-layer design. However, the impact of physical-layer cooperation on the network-layer routing design still remains unclear. In this paper, we examine the potential benefit of radio coverage extension from cooperation, and present how to incorporate this feature into the routing design. Specifically, with a series of mathematical formulations and derivations, we quantitatively identify direct and cooperative radio coverages based on the average symbol error rate (SER) performance requirement, elucidating how cooperative diversity gain can be translated into radio coverage extension. We then propose a cooperative geographic routing protocol with cross-layer design, namely the Relay-Aware Cooperative Routing (RACR) protocol, that exploits the merit of radio coverage extension for improving the non-cooperative geographic routing. Simulation results show that the RACR protocol performs significantly better than the non-cooperative geographic routing in terms of the average path length in dense ad hoc networks.

The advances in Internet Protocol Television (IPTV) technology enable new user-centric and interactive TV model, in which context-awareness is promising in making users' interaction with the TV dynamic and transparent. This paper considers user-centric personalized IPTV services applying context-awareness. We present a solution for enriched IPTV services personalization introducing context-awareness on top of IPTV architecture to gather different information on the user and his environment allowing each user to be distinguished by the system in a unique and real-time manner. Based on the different context information gathered, a novel solution for content recommendation is presented allowing to customize IPTV content according to the context of each user and his environment and hence guaranteeing better users' experience. We implemented the proposed solution on top of an IPTV platform considering the NGN IPTV architecture as a proof of concept and as a mean to evaluate the performance.

Cooperative relaying has been proposed as a promising transmission technique that effectively creates spatial diversity through cooperation among spatially distributed nodes. However, to achieve efficient communications while gaining full benefits from cooperation, more interactions at higher protocol layers, particularly the MAC (Medium Access Control) and network layers, are vitally required. This is ignored in most existing articles that mainly focus on physical (PHY)-layer relaying techniques. In this paper, we propose a novel cross-layer framework involving two levels of joint design-a MAC-network cross-layer design for forwarder selection (or termed routing) and a MAC-PHY for relay selection-over symbol-wise varying channels. Based on location knowledge and contention processes, the proposed cross-layer protocol, CoopGeo, aims at providing an efficient, distributed approach to select next hops and optimal relays to form a communication path. Simulation results demonstrate that CoopGeo not only operates properly with varying densities of nodes, but performs significantly better than the existing protocol BOSS in terms of the packet error rate, transmission error probability, and saturated throughput.

IMS is the new approach adopted by 3GPP towards networks convergence. It was designed to be access independent and ubiquitous. IMS already provides personal mobility for nomadic users, but still needs to deal with service continuity within non 3GPP networks. In this paper we propose a novel hybrid mobility management scheme, based on tight cooperation between fast handovers for mobile IPv6 (FMIPv6) and session initiation protocol (SIP) to ensure an uninterrupted real-time service. Moreover, the new Media Independent Handover (MIH) service is integrated into the IMS architecture in order to perform intelligent and accurate horizontal and vertical handovers. The handover is managed in two phases. The first one or the fast phase is handled by FMIPv6 protocol to preserve as soon as possible packets of the ongoing communication. The second one or the slow phase is handled by the SIP protocol to optimize packet delivery route. By doing so, we exploit the benefits of both layer 3 and application mobility protocols to ensure a continuous session over the two networks without imposing new elements to the network. Through a comparison with other mobility mechanisms, we show in the analytic analysis that our hybrid scheme presents better results in terms of handover latency and packet loss.

This paper provides a performance study for securing media streaming based on hash chain methodology. We introduce a new technique that combines the signature of window-based hash chain with redundancy codes for achieving high reliability and robustness against many attacks. Also, the Window technique integrates the Time-Stamped which strongly eliminates the anti-replay attack. It will also control the management of many users accessing the same video in different instant times. The Window-Based algorithm with redundancy code will be compared against Packet-Based or just Block-Based video streaming security. The analytical and simulation results indicate that, the Window-Based Hash Chain Signature combine with Redundancy Code (WB & RC) is a good solution for video streaming security in terms of reliability and robustness. The times of signature creation and verification are accepted under the standard delay recommendations of real time applications. Our case study provides You Tube as a successful scenario over Internet. The privacy of You Tube will relay on a secure email in user access which represents an efficient way in mobility issue.

The prospection of video streaming security has been changed considerably during the last years. With the new generation of hand healed devices and the delivery rate up to 2 Mb/s, the new prospection searched for fast security measures that have no great effects on the streaming fluidity. The hash chain has been largely used for such applications. The benefits from this deployment are the fast and the light calculations. But, the hash chain still suffers from some drawbacks related to chain link and robustness. This work studies different methods for achieving resynchronisation state for hash chain link. It also proposes a hybrid algorithm based on redundancy codes and windows flow which called Redundancy Code Synchronization Recovery State (RC-SRS). This technique merges the pros of all methods and avoids the cons of them. In the end, analytical and simulation results for the hybrid algorithm have been made. The results indicate that, that proposal has a good overall performance in terms of complexity and calculation time.

Most of geographic routing approaches in wireless ad hoc and sensor networks do not take into consideration the medium access control (MAC) and physical layers when designing a routing protocol. In this paper, we focus on a cross-layer framework design that exploits the synergies between network, MAC, and physical layers. In the proposed CoopGeo, we use a beaconless forwarding scheme where the next hop is selected through a contention process based on the geographic position of nodes. We optimize this Network-MAC layer interaction using a cooperative relaying technique with a relay selection scheme also based on geographic information in order to improve the system performance in terms of reliability.

International audience

Identity-Based Cryptography (IBC) offers the very interesting property that the user's public key is related directly to her/his identity. However, IBC suffers from key escrow because the user private key is generated by an external entity called the Private Key Generator (PKG). To resolve this problem, the Certificateless Cryptography CL-PKC was proposed. This mechanism uses a different method to generate the public key. Although CL-PKC resolves the IBC problem, it removes the IBC attractive advantage of easy public key generation. This system is also the target of Denial of Decryption attack (DoD) when an adversary replaces the user's public key. To overcome these weaknesses, we propose a new solution that merges these two cryptographic systems into only one in order to keep their advantages and to resolve their problems. We prove that our system is secure by using the random oracle model and we demonstrate that it offers a self-generated certificate. This solution can be used to secure object-centric systems that are expected to compose the future internet.

Since 2006, many countries, all over the world, begin to issue e-passports containing biometric data for their citizens. The International Civil Aviation Organization (ICAO) specification for cryptography in e-passport is proven to be insecure and has many threats. The European Union (EU) has defined an extended access control (EAC) mechanism for e-passports. But, even this solution presents many threats especially in security and privacy. In this paper, we present a new method for securing the exchange between an e-passport and the inspection system IS. We propose an on-line authentication mechanism based on elliptic curve Diffie-Hellman key agreement protocol. We create elliptic curve based on biometric data to validate the identity of the user. Our proposal uses a shorter key than others solutions.

Wireless Internet service providers need to secure their networks. Establishing a secure link between an access point and a client's Wi-Fi enabled device is a challenging issue. This paper provides an efficient cross-layer pairing protocol for internet WI-FI networks. The protocol uses information-theoretic security. We also present how to establish secure communication between clients' devices. Besides, we propose a mechanism to enforce the communication security by encrypting the MAC addresses at each frame.

Physical layer encryption is taking a significant importance in securing wireless networks. In this paper, an efficient physical layer encryption is proposed. It relies on the implementation of OFB mode just after the error coding process. The significant advantage of this implementation is that it hides the entire Mac frame. In order to reduce the overhead power consumption at the receiver, an identification mechanism is presented. This security solution is valuable in terms of location privacy and attack prevention. The provided results in this paper prove that this solution does not have any influence on the encoder/decoder functionalities.

In this paper, we propose SBRM (Score-Based Routing Mechanism), a hybrid forwarding protocol based on the use of a modified contention-based forwarding coupled with carry then forward mechanism. Our solution combines different forwarding schemes and takes profit from advantages of each mechanism. Every node calculates its own Score to decide if it will be the next forwarder. The Score computation takes into account the sender and destination locations, the location of the forwarder node itself, its direction, speed and the road traffic density. A score function is defined to minimize the packet delay and to avoid spatial and temporal holes.

Typically, VoIP traffic is deployed as best-effort traffic over Internet links. This voice traffic lacks effective and scalable end-to-end congestion control. We propose a new VoIP congestion control scheme called Voice-TFCC (voice TCP-friendly congestion control), that tries to keep the transmission protocol overhead to a minimum while maintaining a TCP-friendly throughput. Voice-TFCC adjusts packet and codec rate in order to reduce the traffic load non Internet routers and the overall header bandwidth used by VoIP. We used analytical results to show the bandwidth efficiency obtained through our proposal. Voice-TFCC scheme is scalable because no changes are needed at core routers and minimal control messages are used and thus can be easily implemented and deployed in todaypsilas Internet.

Radio Frequency identification (RFID) raises privacy concerns such as malicious traceability and clandestine information collection. In this paper, we consider the need for scalable privacy protecting scheme as RFID technology will grow more prevalent. Our contribution is twofold: First we propose a lightweight privacy protecting scheme that aims at reducing the calculation burden on the back-end database. Our protocol achieves more scalable tag identification by taking advantage of the characteristics of some current RFID applications; Second, we evaluate the performance of our protocol in terms of computational load for the database and we examine how this performance varies according to applications. Moreover we analyze our protocol against various attacks and demonstrate the security of our proposed scheme.

This work presents an architecture for resource sharing in personal networks (PNs). Resources are not necessarily in the same authentication domain and the group that uses them is called a federation. The architecture is based on two components: a signaling protocol and a group key management system. Federation architecture, different interactions with the protocols and an efficient group key algorithm are explained in this work. The performance evaluation of different procedures has concluded and presented.

In this paper we propose the Mobile Party protocol, a new scheme for mobility management in the context of mesh networks. While most of proposed solutions for mobility management issue are routing protocol-independent mechanisms, our proposal integrates routing and mobility management functionalities together in the same scheme. This enhances considerably the performance of our proposal as shown in this paper. Through simulations and performance studies, we demonstrate that the proposed scheme provides a viable solution for mobility and routing management, assuring scalability and seamless communications.

In this paper we propose two algorithms for efficient data-centric storage in wireless sensor networks without the support of any location information system. These algorithms are intended to be applied in environments with large number of sensors where the scalability of the network has great issue. During the first algorithm, each sensor obtains a unique temporary address according to its current relative location in the network. The second algorithm is used to route data from one sensor to another, this routing algorithm only depends on the sensor's neighborhood, i.e. in order to implement the routing table each sensor needs only to exchange local information with its first hop neighbors. The forwarding process used in this algorithm resembles the one found in Pastry peer-to-peer protocol.

In this paper we study a self organizing network architecture, party. Party is a new routing protocol intended to be applied in environments with large number of nodes where the scalability of the routing protocol plays an important role. Party's routing is unique and only depends on the current node's neighborhood. Routing tables are created on the basis of the first hop neighborhood only. We will show the protocol performance with a large number of nodes in the network, and compare it to the legacy ad hoc routing protocols. Results show a large improvement in terms of overhead and throughput.

Securing ad hoc networks is a challenging task due to their specific characteristics. One of the major challenges is that ad hoc networks typically lack a fixed infrastructure both inform of physical nodes such as routers, servers, and stable communication links and in the form of an organizational or administrative infrastructure. New nodes can hence, join and leave the network at any time, which appeals to an efficient and flexible trust establishment mechanism. We propose in this paper an efficient protocol for key management in ad hoc networks relying on the routing mechanism itself.

Abstract — In this paper, we present an analytical model for VoIP capacity in IEEE 802.11e WLAN. We illustrate performance results relative to typical codec rates of G.711 PCM (64 kbit/s),

Supporting QoS for VoIP is a topic that clearly remain of importance. Existing QoS mechanisms for voice over IP need to be adapted. This is essentially due to the high dynamicity and variability of subjective voice quality perception, particularly in some critical conditions (ex. mobile networks). In this paper, we present an architecture, called "MOSQoS", that integrates subjective voice quality assessment into a dynamic QoS loop control. This QoS loop control is based on a subjective and dynamic voice quality evaluation (MOS score). It maintains as constant as possible, a predefined target MOS score during the entire voice session. To achieve this approach, we implement "PE-Model" for subjective voice quality evaluation and combine it with a signaling protocol to dynamically control and optimize network resources such as: queuing allocation and congestion thresholds. Tests and measures obtained through an implementation of the "MOSQoS" approach, show that results in terms of feasibility and performance, are globally satisfactory.

Different QoS requirements of different applications can result in different preferences of the gateway that should be used by the mobile network to access the global Internet. In this context, automated solutions should be proposed offering a minimum complexity and maximum transparency to end users while being always best connected. In this paper, we propose a novel architecture that addresses the following issues and hence enforce the mobile network to Internet connectivity.

The wireless world is a new paradigm driven by both the growing market for higher-quality higher-speed wireless services, and the ubiquitous nature of both the Internet and the PC. In order to offer uninterrupted IP service, transparent mobility and fast re-authentication are important issues for the success of wide-area wireless IP infrastructures. In this work, we describe the design of a new architecture for secure and seamless mobility (SeSMo) support in heterogeneous environments. Our proposal introduces the use of an intelligent handoff decision mechanism for the discovery and the prediction of future access routers (ARs) and the generation of new session keys. An analytical analysis of the performance of SeSMo in terms of total signalling cost is also presented

In emerging personal area networks (PANs), consisting of heterogeneous devices and nodes, dynamic intra-PAN and PAN-to-infrastructure connectivity should be achieved transparently to end users and applications. This paper proposes a distributed virtual network interface (DVNI) solution for PAN device discovery, seamless handover and routing. DVNI is an extension of the VNI concept designed for seamless vertical handover in the case of a single device with multiple interfaces. The DVNI concept consists of making all PAN interfaces available via a common distributed virtual interface to mask changes in the PAN dynamics and connectivity

Networking and computing have become so tied and have naturally integrated our daily life and are evolving to a ubiquitous and transparent interaction between users and information. Distributed and collaborative architectures particularly P2P solutions, proved to be the most efficient way to meet the requirements of pervasive computing. However, many security and mobility issues have to be considered. In this paper, we propose a secure architecture for location management in mobile environments. It inherits from the P2P paradigm features, such as scalability, flexibility and fault-tolerance; thus adapting to dynamic changes of information context.

With the rapid increase of wireless technologies and ubiquitous mobile computing devices, it is becoming a pressing need for developing new functionalities to support seamless handoff. However, developing and deploying new networking infrastructure is often a long and enduring process. In this paper, we present VIP (virtual interface prototype) a simple and efficient micro-mobility solution. The architecture requires very few changes to existing protocol stacks. In particular, no changes to non-mobile hosts are required. Moreover, the protocol adds no overhead to normal IP routing and delivery

Home networking has come in wider use, thus appealing to an increasing need for security. Emerging social concepts such as telecommutation brought a new kind of security threats to the home environment. Besides, low-capacity devices in the home domain may need a central entity dedicated to security enforcement. As SSL-based VPN solutions don’t provide end-to-end tunnels, we have extended TLS protocol to delegate trust establishment between a home network server and an external client to a security gateway, acting as a reverse proxy. Moreover, we formally validated it using automatic protocol analyzer AVISPA.

Although there currently exists several technologies for wireless communication, nothing is available for automatic handover between them. Current solutions to the handover problem just focus on the changing cell within the same system. In this paper we try to analyze the performance of the link-layer handover in IEEE 802.11 and Bluetooth systems. Then, we propose a new virtual interface architecture as a solution to the vertical handover problem. We show how the handover can be achieved when the IP subnet is changed.

This paper presents a security scheme that aims at automating the PIN exchange procedure with the help of the AAA infrastructure in WiFi-overlapped WPAN (wireless personal access network). The proposed security scheme contributes to providing an automatic set-up for the security channel, particularly between a pair of unknown Bluetooth devices.

The rapid growth of wireless technology and the increasing use of such technologies in coordination with the Internet demand a very careful look at issues related to security. As more and more users attempt to utilize such technologies in the context of providing security demanding services, it is essential to recognize the potential threats in wireless technologies. This paper focuses on authentication as part of the significant issues related to security and proposes a new authentication method combining the AAA framework and the UMTS security. As for that, this work presents results that show how the concepts of AAA and the USIM mechanism can be combined for the adaptability of mobile environment as well as for the efficient authentication. It also presents the specification and the implementation of the combination of diameter of the AAA protocols and USIM. In addition to the design implementation, this work reports on the performance results showing that this combination can be a good solution to authentication in a mobile environment.

An authentication model using secured smart cards implementing IP services is presented. In this model, some authentication functions usually found in the access network are moved inside the smart card. This innovative architecture simplifies current authentication schemes and helps to design new services.

Quality of service for Voice over IP on wireless links (WiFi) has to be measured by the perceptual speech quality. How can this subjective measures be "captured" by models that rely on objective measures based on transmission delays and packet losses monitoring. These parameters which are common on such links can affect dramatically speech quality. In this paper, The ITU-T legacy e-Model, recently proposed to qualify audio and well adapted to circuit switched networks is adapted for packet switched networks. A new model to automatically quantify or measure the speech quality perception for voice/audio communications over IP. named here "packet-e-Model", adapts the e-Model to packet networks in general with a special emphasis on WiFi.

Traditionally, QoS has been addressed by using network measurements (e.g., loss rates and delays), and little attention has been paid to the quality perceived by end-users of the applications running over the network. Here, we address the issue of integrating speech quality subjective scores and network parameters measurements, for designing control algorithms that would yield the best QoS that could be delivered under a given communications network situation. First, we build a neural network based automaton to measure speech quality in real time, at the style of a group of human subjects when participating in an MOS test. We consider the effects of changes in network parameters (e.g., packetization interval, packet loss rate and their pattern distribution) and encoding on speech signals transmitted over the network. Our database includes transmitted speech signals in different languages. Then, we outline a control mechanism which, based on the application performance within a session (i.e., MOS speech quality scores generated by the neural networks), dynamically adjusts parameters (codec and packetization interval). Finally, we analyze preliminary results to show two main benefits: first, a better use of bandwidth, and second, delivery of the best possible speech quality given the network current situation.

Integrated services in the Internet require dynamic and efficient usage of resources. This paper describes a mediation platform architecture developed to control resources and to perform the interface between generic clients and servers in ISPs environments. It offers the QoS required by the client through ABT connections. An experimental platform relying on HTTP transactions is described and performance issues including scalability are discussed. We show the trade off between the relevant parameters and their effect on the overall performance.

The future Internet networks are expected to use IPv6 version rather than the IPv4 one. This is mainly due to the limitations of IPv4 in terms of addresses, routing and security QoS issues developed by the Internet community are also tailored for both versions and will be easily deployed in both sides. Since a huge amount of sub-networks are already installed for the v4 version, it is difficult to imagine ISPs starting deploying the v6 version without some assurance that old legacy networks will still be able to connect to the Internet. In this paper we present some mechanisms that have been proposed to ease this transition especially for v4 users that still want to communicate with their old applications. We present also an IPv6 tunneling mechanism that has some advantages over the other models. We show how one could use such a mechanism to transparently establish hybrid communications between two worlds in both ways and discuss some important issues like scalability and performance.

TCP/IP performance in asymmetric networks can be affected by the reverse data path throughput. This could be naturally due the low bandwidth available on that link or because of some background traffic. We present some solutions to improve TCP performance in such conditions. These solutions need a minimal number of modifications in the actual network configuration.

Congestion avoidance algorithms considering the network as a black-box model detect congestion through packet loss and variation in the throughput or in the round trip delay. In this paper we show, by means of analysis and simulation, an undesirable effect acting on delay and throughput based congestion avoidance algorithms. This effect is caused by congestion experienced by acknowledgements. We propose to change these algorithms by dividing the round trip time into a forward trip time and backward trip time. We show the performance improvement using this distinction. Finally, we describe a possible implementation in the TCP protocol.

The emphasis in the paper is on the traffic control at an ATM end source. The purpose of locally controlling a source is the improvement of the TCP performances over ATM. The authors argue the need of a policing mechanism less stringent than the generic cell rate algorithm proposed by the ITU. A more flexible method which is suitable for providing performance guarantees in high speed networks is proposed in the paper. They present the results obtained by the implementation of this method in a multi-task environment. They show how one can obtain reasonable bandwidth utilization while remaining conform to the traffic contract limitations. Moreover they show how this method achieves simplicity of implementation as well as flexibility in the allocation of bandwidth to different connections.

The paper describes the Prism distributed multimedia platform. The paper is divided in three parts. The first part resumes the main components of the platform. The authors show the different planes that interact with both multimedia applications and network resources. The second part describes a different approach being developed for the platform to ease the distribution of multimedia objects. It is based on fragmented objects. The third part enumerates two different applications that have been developed for and on that platform. The first is a specific multimedia protocol and the second is a whiteboard used for tele-teaching.

The OSI (Open Systems Interconnection) X.500 directory system and other distributed naming systems use name caching to minimize the cost of name lookups for nonlocal names. The authors evaluate the impact of name caching on the performance of the OSI directory system. They consider the issues of cache sizing and cache replacement policies. It was found that a locality of reference property holds in name resolution requests, and hence name caching does increase performance significantly. Using trace-driven simulation, it is shown that small caches (smaller than 30 items) yield hit ratios up to 60% and decrease the average name resolution time by 60%. For small caches, the LRU (least recently used) replacement policy is better than other implementable policies. Large caches yield predictably larger hit ratios. For large caches, however, the LRU policy is not better than a random replacement policy. It was also found that partitioning the cache buffer into a small number of independent caches, each one associated with a different kind of name request, further decreases the average name resolution time.>