Multi-Wireless Access Technology (WAT) Radio Access Networks (RANs) are becoming a key enabler in 5G and beyond networks due to the public spectrum scarcity, the level of signal confinement and security offered by some wireless technologies (e.g., Light Fidelity (Li-Fi)), and the reduction of the deployment and operational costs. For instance, Wireless Fidelity (Wi-Fi) technology is cheaper and easier to manage than 5G, and leveraging their already deployed infrastructures contributes to capital expenditures saving. Developing autonomous radio resource provisioning (RRP) solutions is fundamental to cost-effectively achieve the zero-touch management in private 5G networks while fulfilling the service requirements. However, modelling the Key Performance Indicators of the radio interface in 5G and beyond is a complex task that requires high-domain knowledge. Furthermore, the resulting models, as well as solving the respective RRP optimization problem using exact methods usually offer a high computational complexity, especially in multi-WAT scenarios. In order to cope with these issues, in this work, we propose an initial design of a Deep Reinforcement Learning-assisted solution for the RRP in a multi-WAT private 5G network. Furthermore, we contex-tualize the solution in the Open RAN architecture framework. A simulation-based proof-of-concept validates the proposal’s proper design and operation considering a realistic private 5G network scenario.

Network Functions Virtualization facilitates the automation of the scaling of softwarized network services (SNSs). However, the realization of such a scenario requires a way to determine the needed amount of resources so that the SNSs performance requisites are met for a given workload. This problem is known as resource dimensioning, and it can be efficiently tackled by performance modeling. In this vein, this paper describes an analytical model based on an open queuing network of G/G/m queues to evaluate the response time of SNSs. We validate our model experimentally for a virtualized Mobility Management Entity (vMME) with a three-tiered architecture running on a testbed that resembles a typical data center virtualization environment. We detail the description of our experimental setup and procedures. We solve our resulting queueing network by using the Queueing Networks Analyzer (QNA), Jackson's networks, and Mean Value Analysis methodologies, and compare them in terms of estimation error. Results show that, for medium and high workloads, the QNA method achieves less than half of error compared to the standard techniques. For low workloads, the three methods produce an error lower than 10 percent. Finally, we show the usefulness of the model for performing the dynamic resource provisioning of the vMME experimentally.

The Internet of Things is one of the hottest topics in communications today, with current revenues of $151B, around 7 billion connected devices, and an unprecedented growth expected for next years. A massive number of sensors and actuators are expected to emerge, requiring new wireless technologies that can extend their battery life and can cover large areas. LoRaWAN is one of the most outstanding technologies which fulfill these demands, attracting the attention of both academia and industry. In this paper, the design of a LoRaWAN testbed to support critical situations, such as emergency scenarios or natural disasters, is proposed. This self-healing LoRaWAN network architecture will provide resilience when part of the equipment in the core network may become faulty. This resilience is achieved by virtualizing and properly orchestrating the different network entities. Different options have been designed and implemented as real prototypes. Based on our performance evaluation, we claim that the usage of microservice orchestration with several replicas of the LoRaWAN network entities and a load balancer produces an almost seamless recovery which makes it a proper solution to recover after a system crash caused by any catastrophic event.

Requirements for 5G mobile networks includes a higher flexibility, scalability, cost effectiveness and energy efficiency. Towards these goals, Software Defined Networking (SDN) and Network Functions Virtualization have been adopted in recent proposals for future mobile networks architectures because they are considered critical technologies for 5G. In this paper, we propose an X2-based handover implementation in an SDN-based and partially virtualized LTE architecture. Moreover, the architecture considered operates at link level, which provides lower latency and higher scalability. In our implementation, we use MPLS tunnels for user plane instead of GTP-U protocol, which introduces a significant overhead. To verify the correct operation of our system, we developed a simulator. It implements the messages exchange and processing of the primary network entities. Using this tool we measured the handover preparation and completion times, whose estimated values were roughly 6.94 ms and 8.31 ms, respectively, according to our experimental setup. These latencies meet the expected requirements concerning control plane delay budgets for 5G networks.

Abstract Interleaving has shown to be a useful technique to provide robustdistributed speech recognition over IP networks. This is due toits ability to disperse consecutive losses. However, this ability isrelated to the delay introduced by the interleaver. In this work,we propose a novel multi-flow block interleaver which exploitsthe presence of several streams and allows to reduce the involveddelay. Experimental results have shown that this interleaver ap-proximates the performance of end-to-end interleavers but with afraction of their delay. As disadvantage, this interleaver must beplaced in a common node where more than one flow are available. Index Terms : distributed speech recognition, IP networks, inter-leaving, active networks. 1. Introduction Since its beginning, Internet has been growing in size, incorporat-ing many new networks, as well as in functionality, adding newservices. As many other features have been integrated into In-ternet, such as mailing, instant messaging, telephony and so on,speech enabled services (SES) are also being incorporated. Theseservices provide ubiquitous speech recognition, allowing multipleusers to remotely access and share high performance recognitionengines.A very attractive approach to speech recognition over IP net-works is the distributed speech recognition (DSR) solution [1]. Asmany other services over Internet, it is based on a client-serverarchitecture. On one hand, a simple and low power client (