The evolution in the generations of smart applications has led to great challenges in terms of providing low latency and high computing efficiency. One of the most important of these applications is for smart homes, through which various connected devices can be controlled by smart and efficient systems to achieve high service quality. In this paper, we propose a smart home controller based on fog computing, where home services are migrated from the cloud to the fog servers at the edge of the network. We propose an exact algorithm called Optimal Migration Algorithm (OMA) that allocates unified fog computing servers to different services. Moreover, to deal with large-scale networks, we propose an efficient algorithm called Efficient Migration Algorithm (EMA). The performance evaluation shows that the proposed optimization solutions are efficient in terms of migration cost, time, and end-to-end latency.

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.

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.

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.

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.

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 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.

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.

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.