Unmanned aerial vehicles are gaining a lot of popularity among an ever growing community of amateurs as well as service providers. Emerging technologies, such as LTE 4G/5G networks and mobile edge computing, will widen the use case scenarios of UAVs. In this article, we discuss the potential of UAVs, equipped with IoT devices, in delivering IoT services from great heights. A high-level view of a UAV-based integrative IoT platform for the delivery of IoT services from large height, along with the overall system orchestrator, is presented in this article. As an envisioned use case of the platform, the article demonstrates how UAVs can be used for crowd surveillance based on face recognition. To evaluate the use case, we study the offloading of video data processing to a MEC node compared to the local processing of video data onboard UAVs. For this, we developed a testbed consisting of a local processing node and one MEC node. To perform face recognition, the Local Binary Pattern Histogram method from the Open Source Computer Vision is used. The obtained results demonstrate the efficiency of the MEC-based offloading approach in saving the scarce energy of UAVs, reducing the processing time of recognition, and promptly detecting suspicious persons.

Internet of Things security is attracting a growing attention from both academic and industry communities. Indeed, IoT devices are prone to various security attacks varying from Denial of Service (DoS) to network intrusion and data leakage. This paper presents a novel machine learning (ML) based security framework that automatically copes with the expanding security aspects related to IoT domain. This framework leverages both Software Defined Networking (SDN) and Network Function Virtualization (NFV) enablers for mitigating different threats. This AI framework combines monitoring agent and AIbased reaction agent that use ML-Models divided into network patterns analysis, along with anomalybased intrusion detection in IoT systems. The framework exploits the supervised learning, distributed data mining system and neural network for achieving its goals. Experiments results demonstrate the efficiency of the proposed scheme. In particular, the distribution of the attacks using the data mining approach is highly successful in detecting the attacks with high performance and low cost. Regarding our anomalybased intrusion detection system (IDS) for IoT, we have evaluated the experiment in a real Smart building scenario using one-class SVM. The detection accuracy of anomalies achieved 99.71%. A feasibility study is conducted to identify the current potential solutions to be adopted and to promote the research towards the open challenges.

Unmanned aerial vehicles (UAVs) have recently attracted both academia and industry representatives due to their utilization in tremendous emerging applications. Most UAV applications adopt visual line of sight (VLOS) due to ongoing regulations. There is a consensus between industry for extending UAVs’ commercial operations to cover the urban and populated area-controlled airspace beyond VLOS (BVLOS). There is ongoing regulation for enabling BVLOS UAV management. Regrettably, this comes with unavoidable challenges related to UAVs’ autonomy for detecting and avoiding static and mobile objects. An intelligent component should either be deployed onboard the UAV or at a multiaccess-edge computing (MEC) that can read the gathered data from different UAV’s sensors, process them, and then make the right decision to detect and avoid the physical collision. The sensing data should be collected using various sensors but not limited to Lidar, depth camera, video, or ultrasonic. This article proposes probabilistic and deep-reinforcement-learning (DRL)-based algorithms for avoiding collisions while saving energy consumption. The proposed algorithms can be either run on top of the UAV or at the MEC according to the UAV capacity and the task overhead. We have designed and developed our algorithms to work for any environment without a need for any prior knowledge. The proposed solutions have been evaluated in a harsh environment that consists of many UAVs moving randomly in a small area without any correlation. The obtained results demonstrated the efficiency of these solutions for avoiding the collision while saving energy consumption in familiar and unfamiliar environments.

Unmanned Aerial Vehicles (UAVs) are gaining much momentum due to the vast number of their applications. In addition to their original missions, UAVs can be used simultaneously for offering Value Added Internet of Things Services (VAIoTS) from the sky. VAIoTS can be achieved by equipping UAVs with suitable IoT payloads and organizing UAVs’ flights using a central System Orchestrator (SO). SO holds the complete information about UAVs, such as their current positions, their amount of energy, their intended use-cases or flight missions, and their onboard IoT device(s). To ensure efficient VAIoTSs, there is a need for developing a smart mechanism that would be executed at the SO in order to take into account two major factors: i) the UAVs’ energy consumption and ii) the UAVs’ operation time. To effectively implement this mechanism, this paper presents three complementary solutions, named Energy Aware UAV Selection (EAUS), Delay Aware UAV Selection (DAUS), and Fair Trade-off UAV Selection (FTUS), respectively. These solutions use Linear Integer Problem (LIP) optimizations. While the EAUS solution aims to reduce the energy consumption of UAVs, the DAUS solution aims to reduce the operational time of UAVs. Meanwhile, FTUS uses a bargaining game to ensure a fair trade-off between the energy consumption and the operation time. The results obtained from the performance evaluations demonstrate the efficiency and the robustness of the proposed schemes. Each solution demonstrates its efficiency at achieving its planned goals.

The research and development (R&D) and the standardization of the 5th Generation (5G) mobile networking technologies are proceeding at a rapid pace all around the world. In this paper, we introduce the emerging concept of network slicing that is considered one of the most significant technology challenges for 5G mobile networking infrastructure, summarize our preliminary research efforts to enable end-to-end network slicing for 5G mobile networking, and finally discuss application use cases that should drive the designs of the infrastructure of network slicing.

Cloud offerings represent a promising solution for mobile network operators to cope with the surging mobile traffic. The concept of carrier cloud has therefore emerged as an important topic of inquiry. For a successful carrier cloud, algorithms for optimal placement of Virtual Network Functions (VNFs) on federated cloud are of crucial importance. In this paper, we introduce different VNF placement algorithms for carrier cloud with two main design goals: i) minimizing path between users and their respective data anchor gateways and ii) optimizing their sessions' mobility. The two design goals effectively represent two conflicting objectives, that we deal with considering the mobility features and service usage behavioral patterns of mobile users, in addition to the mobile operators' cost in terms of the total number of instantiated VNFs to build a Virtual Network Infrastructure (VNI). Different solutions are evaluated based on different metrics and encouraging results are obtained.