Mobile edge computing (MEC) within 5G networks brings the power of cloud computing, storage, and analysis closer to the end user. The increased speeds and reduced delay enable novel applications such as connected vehicles, large-scale IoT, video streaming, and industry robotics. Machine Learning (ML) is leveraged within mobile edge computing to predict changes in demand based on cultural events, natural disasters, or daily commute patterns, and it prepares the network by automatically scaling up network resources as needed. Together, mobile edge computing and ML enable seamless automation of network management to reduce operational costs and enhance user experience. In this paper, we discuss the state of the art for ML within mobile edge computing and the advances needed in automating adaptive resource allocation, mobility modeling, security, and energy efficiency for 5G networks.

Software-defined networking (SDN) logically separates the control and data planes, thus opening the way to more flexible configurations and management of low-Earth orbit (LEO) satellite networks. Since one or, more generally, multiple distributed controllers are needed, a significant challenge in SDN is the controller placement problem (CPP). Due to characteristics such as the dynamic network topology, limited bandwidth and traffic variations, the CPP is quite complex in SDN-based satellite networks. In this paper, we propose solving the CPP by means of a static placement with dynamic assignment (SPDA) method for LEO satellite networks. The SPDA method has two parts: the first is to incorporate SDN controllers into some fixed satellites by formulating a mixed integer programming model; the second is to dynamically assign switches to existing controllers according to the switch-controller latency and the traffic load of controllers. The SPDA method takes the topological dynamics into account by effectively dividing time snapshots, and it has a lower bandwidth consumption compared with methods involving controller migrations. Real satellite constellations are used to evaluate the performance of our controller placement solution. The results show that SPDA outperforms existing methods in terms of reducing the switch-controller latency, and it also has good load balancing performance.

Using satellite constellations to provide global Internet access services has recently drawn increasing attention. A low-Earth orbit (LEO) satellite network with multiple satellites provides global coverage, low latency, and operates independently, by which it effectively complements terrestrial IP networks. Satellite gateways are located on the ground and can serve as data exchange points between satellite networks and the Internet. As the placement scheme can affect network performance, finding appropriate sites for gateways constitutes a fundamental problem. This paper proposes a gateway placement optimization (GPO) method for LEO satellite networks in order to solve this problem by modeling it as a combination optimization problem. We aim to identify the best gateway locations that can balance traffic loads while using as few gateways as possible. The constraints to be satisfied concern the physical links between gateways and satellites: specifically, link interference, satellite bandwidth, and number of satellite antennas. We use a gravity model to estimate the traffic matrix from/to gateways and satellites, then we adopt and modify the discrete particle swarm optimization (PSO) algorithm to solve this problem. Finally, we apply the GPO method to numerical tests on real satellite constellations. The results indicate that our method performs well and effectively.

Rapidly-increasing traffic demands will require the upgrade of optical access networks, namely deployed Passive Optical Networks (PONs), which may soon face capacity exhaustion. Such upgrade options must consider several technical and cost factors for evolution toward a shared multiple-channel PON using Wavelength- Division Multiplexing (WDM). WDM can facilitate the seamless upgrade of PONs, since capacity can be increased by adding new wavelength channels. We study the requirements for optimal migration toward higher bandwidth per user, and examine scenarios and cost-effective solutions for PON evolution.