We focus on the problem of managing the energy consumption of a cellular network tailored to cover rural and low-income areas. The considered architecture exploits Unmanned Aerial Vehicles (UAVs) to ensure wireless coverage, as well as Solar Panels (SPs) and batteries installed in a set of ground sites, which provide the energy required to recharge the UAVs. We then target the maximization of the energy stored in the UAVs and in the ground sites, by ensuring the coverage of the territory through the scheduling of the UAV missions over space and time. After providing the problem formulation, we face its complexity, by proposing a decomposition-based approach and by designing a brand-new genetic algorithm. Results, obtained over a set of representative case studies, reveal that there exists a trade-off between the UAVs battery level, the ground sites battery level and the level of coverage. In addition, both the decomposed version and the genetic algorithm perform sufficiently close to the integrated model, with a strong improvement in the computation times.

The Internet-of-Things (IoT) paradigm offers applications the potential of automating real-world processes. Applying IoT to intensive domains comes with strict Quality-of-Service (QoS) requirements, such as very short response times. To achieve these goals, the first option is to distribute the computational workload throughout the infrastructure (edge, fog, cloud). In addition, integration of the infrastructure with enablers, such as software-defined networks (SDNs) can further improve the QoS experience, thanks to the global network view of the SDN controller and the execution of optimization algorithms. Therefore, the best placement for both the computation elements and the SDN controllers must be identified to achieve the best QoS. While it is possible to optimize the computing and networking dimensions separately, this results in a suboptimal solution. Thus, it is crucial to solve the problem in a single effort. In this work, the influence of both dimensions on the response time is analyzed in fog computing environments powered by SDNs. DADO, a framework to identify the optimal deployment for distributed applications is proposed and implemented through the application of mixed-integer linear programming. An evaluation of an IIoT case study shows that our proposed framework achieves scalable deployments over topologies of different sizes and growing user bases. In fact, the achieved response times are up to 37.89% lower than those of alternative solutions and up to 15.42% shorter than those of state-of-the-art benchmarks.

The advent of the Internet of Things (IoT) paradigm to intensive domains, such as industry, is a key enabler for the automation of critical, real-world processes. The strict Quality of Service (QoS) requirements of these domains make low-latency computing paradigms, such as fog computing, very attractive for meeting these requirements. Moreover, the requirements of scalability and flexibility in the underlying network communications motivate the use of Software-Defined Networking (SDN) in the infrastructure. To enable these fog-SDN environments, fog nodes that have both computing and SDN capabilities can be deployed, thus easing the deployment of fog in SDN networks. However, the exact placement of these fog nodes is key to the latency of the hosts that make use of them, and thus, must be carefully assessed to meet the stringent QoS requirements of critical, time-strict IoT applications. This paper focuses on this fog node placement problem by formalizing it and solving it through both optimal and approximated methods, including comparisons with state-of-the-art benchmarks. In particular, we analyze the performance of each of these methods in terms of latency and execution time in both SDN Internet topologies and Industrial IoT infrastructures. Our proposed heuristic provides placements with near-optimal latencies, with smaller optimality gaps than the benchmark, and computes them in tractable times.

The irruption of the Internet of Things (IoT) has attracted the interest of both the industry and academia for their application in intensive domains, such as healthcare. The strict Quality of Service (QoS) requirements of the next generation of intensive IoT applications require the QoS to be optimized considering the interplay of three key dimensions: 1) computing; 2) networking; and 3) application. This optimization requirement motivates the use of paradigms that provide virtualization, flexibility, and programmability to IoT applications. In the computing dimension, paradigms, such as edge or fog computing, software-defined networks in the networking dimension, along with micro-services architectures for the application dimension, are suitable for QoS-strict IoT scenarios. In this work, we present a framework, named Next-gen IoT Optimization (NIoTO), that considers these three dimensions and their interplay to place microservices and networking resources over an infrastructure, optimizing the deployment in terms of average response time and deployment cost. The evaluation of NIoTO in a healthcare case study reveals a response time speed up of up to 5.11 and a reduction in cost of up to 9% with respect to other state-of-the-art techniques.

Software-defined networking (SDN) is a paradigm that provides flexibility and programmability to computer networks. By introducing SDN nodes in a legacy IP network topology, network operators can benefit on higher control over the infrastructure. However, this migration is not a fast or straightforward process. Furthermore, to provide an adequate quality of service in hybrid IP/SDN networks, the coordination of both IP and SDN paradigm is fundamental. In this paper, this coordination is used to solve two optimization problems that are typically solved separately: (i) traffic load balancing and (ii) power consumption minimization. Each of these problems has opposing objectives, and thus, their joint consideration implies striking a balance between them. Therefore, this paper proposes the Hybrid Spreading Load Algorithm (HSLA) heuristic that jointly faces the problems of balancing traffic by minimizing link utilization and network’s power consumption in a hybrid IP/SDN network. HSLA is evaluated over differently sized topologies using different methods to select which nodes are migrated from IP to SDN. These evaluations reveal that alternative approaches that only address one of the objectives are outperformed by HSLA.