Multi-access edge computing (MEC) has been regarded as one of the essential technologies for mobile networks, by providing computing resources and services close to users, thereby, avoiding extra energy consumption and fitting the low-latency ultra-reliable requirements for emerging 5G applications. Task offloading policy plays a pivotal role in handling offloading requests and maximizing the network computing performance. Most recently developed offloading solutions are designed for instant rewards, therefore, neglecting the long-term computing resource optimization at the edge, which fail to deliver optimized network performance when a significant increase of computing requests appears. In this paper, with the objective of maximizing long-term offloading benefits on delay and energy consumption, task offloading policies are proposed to firstly avoid resource over-distribution through deep reinforcement learning (DRL) based resource reservation and server cooperation, and secondly maximize the average instant reward and the utilization of reserved resources by an optimization-based joint policy consisting of offloading decision, transmission power allocation and resource distribution. The DRL-based joint policy is evaluated in a simulated multi-server edge computing network. Compared to previous solutions, the DRL-based algorithms achieve higher and more reliable overall rewards. Of the implemented three DRL-based algorithms, fully cooperative multi-agent DRL accounts for cooperation between servers, achieving a 70.5% reduction in reward variance and a 13.4% increase in average rewards over 500 continuous operations. Resource balanced policies on long-term rewards help edge networks handle the explosive growth of 5G computing-intensive applications in the future.

The adoption of private 5G networks or Non-Public Networks (NPN) by industry verticals is igniting a digital transformation across various sectors and also leading to industry 4.0. This impetus comes from the integration of private wireless networks with 5G capabilities. Currently, a range of innovative applications and use cases are emerging and resulting in improved enterprise performance and solutions. The potential to boost revenue, stimulate cost reduction, and accelerate Return Of Investment (ROI) makes 5G NPN adoption attractive to industry verticals, network operators and other third-party stakeholders. However, a significant infrastructure upgrade is required, which demands understanding of the complexities of 5G NPN deployment scenarios and their economic implications. This paper addresses these needs by conducting a detailed techno-economic analysis on 5G NPN deployment. The study formulates a techno-economic model that focuses on; (i) Cost savings in support of ROI achieved by enabling Network Function Virtualization (NFV) technology and Neutral Host (NH) concept; (ii) The trade-off study between enterprise goals (cost vs deployment technologies) with a multi-objective sensitive analysis; And (iii) the trends of 5G NPN adoption worldwide. Analytical results confirm savings of up to 53% in Total Cost of Ownership (TCO) reflecting a significant reduction in Capital and Operation Expenditures (Capex and Opex). Simulation analysis identifies a ranking order of deployment parameters, which prioritise the use of Cost saving strategies and Deployment type. And finally, it offers a prediction of a starting annual average worldwide adoption rate of 82.2% with an expected height by 2026.

With network virtualization, the physical infrastructure can be partitioned into multiple parallel virtual networks for sharing purposes. However, different transport technologies or quality of service (QoS) levels may impact both the requested amount of resources and the characteristics of different virtual instances that can be built on top of a single physical infrastructure. In this paper we propose a novel mixed integer linear programming (MILP) formulation for different schemes of protection in scenarios where multiple virtual topologies run over an elastic optical network. The proposed MILP formulation uses the concept of bandwidth squeezing to guarantee a minimum bandwidth for surviving virtual topologies. It achieves a high level of survivability for traffic that is subject to a different committed service profile for each virtual topology. Case studies are carried out in order to analyze the basic properties of the formulation in small networks, and three heuristics are proposed for larger networks.

The use of Wireless Sensor Networks (WSN) in smart agriculture has emerged in recent years. LoRaWAN (Long Range Wide Area Networks) is widely recognized as one of the most suitable technologies for this application, due to its capacity to transmit data over long distances while consuming little energy. Determining the number and location of gateways (GWs) in a production setting is one of the most challenging tasks of planning and building this type of network. Various solutions to the LoRaWAN gateway placement problem have been proposed in the literature, utilizing clustering algorithms; however, few works have compared the performance of various strategies. Considering all these facts, this paper proposes a strategy for planning the number and localization of LoRaWAN GWs, to cover a vast agricultural region. Four clustering algorithms were used to deploy the network GWs: K-Means and its three versions: Minibatch K-Means; Bisecting K-Means; and Fuzzy c-Means (FCM). As performance metrics, uplink delivery rate (ULDR) and energy consumption were used, to provide subsidies for the network designer and the client, with which to choose the best setup. A stochastic energy model was used to evaluate power consumption. Simulations were performed, considering two scenarios: Scenario 1 with lower-medium concurrence, and Scenario 2 with higher-medium concurrence. The simulations showed that the use of more than two GWs in Scenario 1 did not lead to significant improvements in ULDR and energy consumption, whereas, in Scenario 2, the suggested number of GWs was between 11 and 15. The results showed that for Scenario 1, the FCM algorithm was superior to all alternatives, regarding the ULDR and mean energy consumption, while the K-Means algorithm was superior with respect to maximum energy consumption. In relation to Scenario 2, K-Means caused the best ULDR and mean consumption, while FCM produced the lowest maximum consumption.

In spectrum-sliced elastic optical path networks (SLICE), the lightpath bandwidth is variable, and the virtual topology overlay on a physical topology shall be designed to optimize the spectrum utilization. Under static traffic, SLICE networks are typically designed through a mixed integer linear programming (MILP) with the aim of minimizing the spectrum utilization. In this paper, a new MILP formulation for protection in SLICE networks is proposed, which uses the concept of bandwidth squeezing and grooming to guarantee a minimum agreed bandwidth for each source–destination pair in the surviving bandwidth. The route for each demand on the physical topology is determined by balance equations together with physical layer constraints in the formulation, so that no pre-calculated routes are required and the modulation format of each established lightpath may be chosen with enough quality of transmission and to save network spectrum. Therefore, the proposed formulation jointly solves the virtual topology design and physical topology design problems. The first results evaluate the effectiveness of the MILP formulation for two small networks when connections are under different service-level agreement (SLA) requirements and are provisioned by an appropriate protection scheme and different modulation formats. Due to the NP-hard nature of the proposed MILP formulation, a heuristic algorithm for moderately large networks is also proposed. Case studies are carried out to analyze the basic properties of the formulation and the performance of the proposed heuristic. With the proposed formulation, it is possible to identify the configurations that ensure minimum spectrum occupation with different kinds of protection for each lightpath. Different kinds of modulation formats are considered and contrasted to the benchmark case of a single modulation format and using the same kind of protection for all lightpaths.

Open Radio Access Network (Open RAN) has gained tremendous attention from industry and academia with decentralized baseband functions across multiple processing units located at different places. However, the ever-expanding scope of RANs, along with fluctuations in resource utilization across different locations and timeframes, necessitates the implementation of robust function management policies to minimize network energy consumption. Most recently developed strategies neglected the activation time and the required energy for the server activation process, while this process could offset the potential energy savings gained from server hibernation. Furthermore, user plane functions, which can be deployed on edge computing servers to provide low-latency services, have not been sufficiently considered. In this paper, a multi-agent deep reinforcement learning (DRL) based function deployment algorithm, coupled with a heuristic method, has been developed to minimize energy consumption while fulfilling multiple requests and adhering to latency and resource constraints. In an 8-MEC network, the DRL-based solution approaches the performance of the benchmark while offering up to 51% energy savings compared to existing approaches. In a larger network of 14-MEC, it maintains a 38% energy-saving advantage and ensures real-time response capabilities. Furthermore, this paper prototypes an Open RAN testbed to verify the feasibility of the proposed solution.