The growing network density and unprecedented increase in network traffic, caused by the massively expanding number of connected devices and online services, require intelligent network operations. Machine Learning (ML) has been applied in this regard in different types of networks and networking technologies to meet the requirements of future communicating devices and services. In this article, we provide a detailed account of current research on the application of ML in communication networks and shed light on future research challenges. Research on the application of ML in communication networks is described in: i) the three layers, i.e., physical, access, and network layers; and ii) novel computing and networking concepts such as Multi-access Edge Computing (MEC), Software Defined Networking (SDN), Network Functions Virtualization (NFV), and a brief overview of ML-based network security. Important future research challenges are identified and presented to help stir further research in key areas in this direction.

During the New Space era small countries are becoming important players in the space business. While space activities are rapidly increasing globally, it is important to make operations in a sustainable and safe way in order to preserve satellite services for future generations. Unfortunately, the sustainability aspect has been largely overlooked in the existing surveys on space technologies. As a result, in this survey paper, we discuss the multi-layer networking approaches in the 6G era specifically from the sustainability perspective. Moreover, our comprehensive survey includes aspects of some interesting industrial, proprietary, and standardization views. We review the most important regulations and international guidelines and revisit a three-dimensional architecture vision to support the sustainability target for a variety of application areas. We then classify and discuss space safety paradigms that are important sustainability enablers of future satellite communications. These include space traffic management, debris detection, environmental impacts, spectrum sharing, and cyber security aspects. The paper also discusses advances towards a planned European connectivity constellation that could become a third flagship infrastructure along with the Galileo and Copernicus systems. Finally, we define potential research directions into the 2030s.

As communication and computation systems become more complex and target at higher performance, the fundamental limits of nature can be expected to constrain their development and optimization. This calls for intelligent use of basic resources, that is, materials, energy, information, time, frequency, and space. We present a multidisciplinary and historical review on the body of knowledge that can be applied in researching such intelligent and resource-efficient systems. We review general system theory, decision theory, control theory, computer science, and communication theory. While multidisciplinarity has been recognized important, there are no earlier reviews covering all these five disciplines. Based on the review, we build a chronology of intelligent systems and identify connections between the disciplines. Optimization, decision-making, open- and closed-loop control, hierarchy, and degree of centralization turn out as recurring themes in these disciplines, which have converged to similar solutions that are based on remote control, automation, autonomy, and self-organization. We use future wireless networks as an example to illustrate the open questions and how they can be addressed by applying multidisciplinary knowledge. This paper can help researchers to use knowledge outside their own field and avoid repeating the work done already. The resulting consolidated view can speed up research and is especially important when the fundamental limits of nature are approached and new insights are required to overcome the challenges. The general, long-standing problem to be tackled is multiobjective optimization with autonomous and distributed decision-making in an uncertain, dynamic, and nonlinear environment where the objectives are mutually conflicting.

Satellite communications systems provide a means to connect people and devices in hard-to-reach locations. Traditional geostationary orbit (GEO) satellite systems and low Earth orbit (LEO) constellations, having their own strengths and weaknesses, have been used as separate systems serving different markets and customers. In this article, we analyze how satellite systems in different orbits could be integrated together and used as a multi-layer satellite system (MLSS) to improve communication services. The optimization concerns combining the strengths of different layers that include a larger coverage area as one moves up by each layer of altitude and a shorter delay as one moves down by each layer of altitude. We review the current literature and market estimates and use the information to provide a thorough assessment of the economic, regulatory, and technological enablers of the MLSS. We define the MLSS concept and the architecture and describe our testbed and the simulation tools used as a comprehensive engineering proof-of-concept. The validation results confirm that the MLSS approach can intelligently exploit the smaller jitter of GEO and shorter delay of LEO connections, and it can increase the availability and resilience of communication services. As a main conclusion, we can say that multi-layered networks and the integration of satellite and terrestrial segments seem very promising candidates for future 6G systems.

This paper introduces a novel distributed algorithm designed to optimize the deployment of access points within Mobile Ad Hoc Networks (MANETs) for better service quality in infrastructure-less environments. The algorithm operates based on local, independent execution by each network node, thus ensuring a high degree of scalability and adaptability to changing network conditions. The primary focus is to match the spatial distribution of access points with the distribution of client devices while maintaining strong connectivity to the network root. Using autonomous decision-making and choreographed path-planning, this algorithm bridges the gap between demand-responsive network service provision and the maintenance of crucial network connectivity links. The assessment of the performance of this approach is motivated by using numerical results generated by simulations.