During the last decade, optical networks have become "smart networks". Software-defined networks, software-defined optical networks, and elastic optical networks are some emerging technologies that provide a basis for promising innovations in the functioning and operation of optical networks. Machine learning algorithms are providing the possibility to develop this promising study area. Since machine learning can learn from a large amount of data available from the network elements. They can find a suitable solution for any environment and thus create more dynamic and flexible networks that improve the user experience. This paper performs a systematic mapping that provides an overview of machine learning in optical networks, identifies opportunities, and suggests future research lines. The study analyzed 96 papers from the 841 publications on this topic to find information about the use of machine learning techniques to solve problems related to the functioning and operation of optical networks. It is concluded that supervised machine learning techniques are mainly used for resource management, network monitoring, fault management, and traffic classification and prediction of an optical network. However, specific challenges need to be solved to successfully deploy this type of method in real communication systems since most of the research has been carried out in controlled experimental environments.

Ever-increasing energy consumption, the depletion of non-renewable resources, the climate impact associated with energy generation, and finite energy-production capacity are important concerns that drive the urgent creation of new solutions for energy management. In this regard, by leveraging the massive connectivity provided by emerging 5G communications, this paper proposes a long-term sustainable Demand-Response (DR) architecture for the efficient management of available energy consumption for Internet of Things (IoT) infrastructures. The proposal uses Network Functions Virtualization (NFV) and Software Defined Networking (SDN) technologies as enablers and promotes the primary use of energy from renewable sources. Associated with architecture, this paper presents a novel consumption model conditioned on availability and in which the consumers are part of the management process. To efficiently use the energy from renewable and non-renewable sources, several management strategies are herein proposed, such as prioritization of the energy supply and workload scheduling using time-shifting capabilities. The complexity of the proposal is analyzed in order to present an appropriate architectural framework. The energy management solution is modeled as an Integer Linear Programming (ILP) and, to verify the improvements in energy utilization, an algorithmic solution and its evaluation are presented. Finally, open research problems and application scenarios are discussed.

The fifth generation of mobile networks (5G) is expected to provide diverse and stringent improvements such as greater connectivity, bandwidth, throughput, availability, improved coverage, and lower latency. Considering this, drones or Unmanned Aerial Vehicles (UAVs) and Internet of Things (IoT) devices are perfect examples of existing technology that can take advantage of the capabilities provided by 5G technology. In particular, UAVs are expected to be an important component of 5G networks implementations and support different communication requirements and applications. UAVs working together with 5G can potentially facilitate the deployment of standalone or complementary communications infrastructures, and, due to its rapid deployment, these solutions are suitable candidates to provide network services in emergency scenarios, natural disasters, and search and rescue missions. An important consideration in the deployment of a programmable drone fleet is to guarantee the reliability and performance of the services through consistent monitoring, control, and management scheme. In this regard, the Network Functions Virtualization (NFV) paradigm, a key technology within the 5G ecosystem, can be used to perform automation, management, and orchestration tasks. In addition, to ensure the coordination and reliability in the communications systems, considering that the UAVs have a finite lifetime and that eventually they must be replaced, a scheduling scheme is needed to guarantee the availability of services and efficient resource utilization. To this end, in this paper is presented an UAV scheduling scheme which leverages the potential offered by NFV. The proposed strategy, based on a brute-force search combinatorial algorithm, allows obtaining the optimal scheduling of UAVs in time, in order to efficiently deploy network services. Simulation results validate the performance of the proposed strategy, by providing the number of drones needed to meet certain levels of service availability. Furthermore, the strategy allows knowing the sequence of replacement of UAVs to ensure the optimal resource utilization.

The new generation of communication networks can provide massive connectivity of devices, extremely low latency, higher capacity, and increased bandwidth. These features enable the deployment of management systems in different sectors such as energy and in a wide variety of environments such as agriculture, surveillance or home systems. In this regard, this paper proposes a self-powered adaptive and automated home energy control system enabled by the Internet of Things (IoT) technologies. The system aims to adapt the consumption patterns to the availability of self-generated renewable energy (produced from solar panels, wind-mills, etc.). Therefore, the renewable and non-renewable supply from the power grid is considered a secondary power source. As part of the proposal, this paper presents the consumption negotiation scheme for IoT devices, the management mechanisms to optimize the use of the available energy, and the related model. Given the complexity of the adaptive management process, the proposal also presents a heuristic strategy based on a prepartitioning method to obtain feasible solutions in a reasonable running time. The simulation results for offline and online scenarios validate the advantages of the proposed strategy, and the numerical improvements are presented.

Unmanned aerial vehicles (UAVs) have seen remarkable improvements in their flight capabilities and computational power. Their applications span various domains, such as agriculture, military, and communications. To improve communication quality and coverage in UAV-enabled systems, understanding effective placement techniques is crucial. While research has explored optimal UAV placement in two dimensions, there is a need for a comprehensive three-dimensional (3D) analysis, particularly for resource optimization. This article presents a systematic mapping study on 3D placement in UAV-enabled communication systems, incorporating a threat analysis for the reliability of the results. It provides valuable insights for future research on 3D placement optimization techniques, specifically examining optimization objectives, model system features, problem types, and solution strategies. Our research reveals, on one hand, an emphasis on optimizing data rate throughput, power transmission, and ground coverage, and a predominant use of large-scale fading in the air-to-ground channel model; on the other hand, heuristic algorithms prevail as the solution strategy. Moreover, we identify gaps in achieving critical objectives such as the probability of outage, deployment costs, quality of experience, and spectrum optimization. This highlights the need for further exploration in the formulation aspects of the system, which includes small-scale fading, access techniques, and interference management.

Nowadays, Unmanned Aerial Vehicles (UAV) are frequently present in the civilian environment. However, proper implementations of different solutions based on these aircraft still face important challenges. This article deals with multi-UAV systems, forming aerial networks, mainly employed to provide Internet connectivity and different network services to ground users. However, the mission duration (hours) is longer than the limited UAVs’ battery life-time (minutes). This paper introduces the UAV replacement procedure as a way to guarantee ground users’ connectivity over time. This article also formulates the practical UAV replacements problem in moderately large multi-UAV swarms and proves it to be an NP-hard problem in which an optimal solution has exponential complexity. In this regard, the main objective of this article is to evaluate the suitability of heuristic approaches for different scenarios. This paper proposes betweenness centrality heuristic algorithm (BETA), a graph theory-based heuristic algorithm. BETA not only generates solutions close to the optimal (even with 99% similarity to the exact result) but also improves two ground-truth solutions, especially in low-resource scenarios.