Network slices for delay-constrained applications in 5G systems require computing facilities at the edge of the network to guarantee ultra-low latency in processing data flows generated by connected devices, which is challenging with larger volumes of data, and larger distances to the edge of the network. To address this challenge, we propose to extend 5G network slices with Unmanned Aerial Vehicles (UAV) equipped with multi-access edge computing (MEC) facilities. However, onboard computing elements (CE) consume UAV’s battery power thus impacting its flight duration. We propose a framework where a System Controller (SC) can turn on and off UAV's CEs, with the possibility of offloading jobs to other UAVs, to maximize an objective function defined in terms of power consumption, job loss, and incurred delay. Management of this framework is achieved by reinforcement learning. A Markov model of the system is introduced to enable reinforcement learning and provide guidelines for the selection of system parameters. A use case is considered to demonstrate the gain achieved by the proposed framework and discuss numerical results.

In the last decade, the differences in the information communication technology (ICT) infrastructures between urban and rural areas have registered a tremendous increase. ICT infrastructures could strongly help rural communities where many operations are time consuming, labor-intensive and expensive due to limited access and large distances to cover. One of the most attractive solutions, which is widely recognized as promising for filling this gap, is the use of drone fleets. In this context, this paper proposes a video monitoring platform as a service (VMPaaS) for wide rural areas not covered by Internet access. The platform is realized with a Software-Defined Network (SDN)/Network Functions Virtualization (NFV)-based flying ad-hoc network (FANET), whose target is providing a flexible and dynamic connectivity backbone, and a set of drones equipped with high-resolution cameras, each transmitting a video stream of a portion of the considered area. After describing the architecture of the proposed platform, service chains to realize the video delivery service are described, and an analytical model is defined to evaluate the computational load of the platform nodes in such a way so as to allow the network orchestrator to decide the backbone drones where running the virtual functions, and the relative resources to be allocated. Numerical analysis is carried out in a case study.

Disruption of the ground communication infrastructure in emergency scenarios makes post-disaster rescue operations very complicate. This paper proposes to use edge intelligence to support rescue operators in managing these emergency scenarios. A set of Unmanned Aerial Vehicles (UAV), organized as Flying Ad-Hoc network (FANET), autonomously takeoff and land to provide emergency operators with edge computing services. A charging station for batteries is supplied by a renewable-energy generator. The FANET Controller applies model-based Reinforcement Learning to decide how many UAVs have to take off, according to the current edge-computing service requests and the power availability, and a forecast of them. The optimal management policy has to provide the necessary level of edge-computing avoiding wide use of satellite channels in a short-time horizon during low green-energy generation and high service request periods. Results highlight that the optimal policy is an efficient modification of the greedy one, i.e. the policy enabling the takeoff of all the necessary UAVs without being care of challenging events in the future. A deep analysis has revealed that the level of modification depends on the combination of the edge-computing service request and the green power availability.

Internet of Things (IoT) has emerged as a huge paradigm shift by connecting a versatile and massive collection of smart objects to the Internet, coming to play an important role in our daily lives. Data produced by IoT devices can generate a number of computational tasks that cannot be executed locally on the IoT devices. The most common solution is offloading these tasks to external devices with higher computational and storage capabilities, usually provided by centralized servers in remote clouds or on the edge by using the fog computing paradigm. Nevertheless, in some IoT scenarios there are remote or challenging areas where it is difficult to connect an IoT network to a fog platform with appropriate links, especially if IoT devices produce a lot of data that require processing in real-time. To this purpose, in this article, we propose to use unmanned aerial vehicles (UAVs) as fog nodes. Although this idea is not new, this is the first work that considers power consumption of the computing element installed on board UAVs, which is crucial, since it may influence flight mission duration. A System Controller (SC) is in charge of deciding the number of active CPUs at runtime by maximizing an objective function weighing power consumption, job loss probability, and processing latency. Reinforcement Learning (RL) is used to support SC in its decisions. A numerical analysis is carried out in a use case to show how to use the model introduced in the article to decide the computation power of the computing element in terms of number of available CPUs and CPU clock speed, and evaluate the achieved performance gain of the proposed framework.

In the last years, Internet is evolving towards the cloud-computing paradigm complemented by fog-computing in order to distribute computing, storage, control, networking resources and services close to end-user devices as much as possible, while sending heavy jobs to the remote cloud. When fog-computing nodes cannot be powered by the main electric grid, some environmental-friendly solutions, such as the use of solar- or wind-based generators could be adopted. Their relatively unpredictable power output makes it necessary to include an energy storage system in order to provide power when a peak of work occurs during periods of low-power generation. An optimized management of such an energy storage system in a green fog-computing node is necessary in order to improve the system performance, allowing the system to cope with high job arrival peaks even during low-power generation periods. In this perspective, this paper adopts reinforcement learning to choose a server activation policy that ensures the minimum job loss probability. A case study is presented to show how the proposed system works, and an extensive performance analysis of a fog-computing node highlights the importance of optimizing battery management according to the size of the Renewable- Energy Generator system and the number of available servers.