Search

Future applications to be supported by 6G networks are envisaged to be realized by loosely-coupled and independent microservices. In order to achieve an optimal deployment of applications, smart resource management strategies will be required, working in a cost-effective and resource-efficient manner. Current cloud computing services are challenged to meet the explosive growth and demand of future use cases such as virtual/augmented/mixed reality (VR/AR/MR). The purpose of edge computing (EC) is to better address latency and transmission requirements of those future stringent applications. However, a high flexibility and a rapid decision-making will be required since EC suffers from limited resources availability. For this reason, this work proposes an artificial intelligence (AI) technique, based on reinforcement learning (RL), to make intelligent decisions on the optimal tier and edge-site selection to serve any request according to the application's category, constraints, and conflicting costs. In addition, when deployed at the edge-network, a heuristic has been proposed for the mapping of microservices within the selected edge-site. That heuristic will exploit a ranking methodology based on the network topology and available network and compute resources while preserving the revenue of the mobile network operator (MNO). Simulation results show that the performance of the proposed RL approach is close to the optimal solution by reaching the cost minimization objective within a 8.3% margin; moreover, RL outperforms considered benchmark algorithms in most of the conducted experiments. [ABSTRACT FROM AUTHOR]

The transition to beyond fifth generation (B5G) and sixth generation (6G) networks will lead to the support of new and future services, like virtual reality, vehicle collision avoidance or Internet-of-Things applications, among others. Such applications will be deployed based on loosely-coupled and independent microservices under different Quality of Service (QoS) requirements. Moreover, future applications will be either delay-tolerant or delay-sensitive, resulting in different application categories. Therefore, any provisioning technique will have to meet a large range of requirements, with flexibility and optimally, to accommodate the different service demands onto a common network. This is a major challenge for current networks, having to provide such services under strict QoS requirements, at minimum cost, and in a reasonable time. Currently, multi-access edge computing (MEC) has been proposed to deploy time-sensitive microservice-based applications, increasing the complexity of an optimal deployment in resource-constrained systems. Moreover, traditional heuristic algorithms do follow static solving strategies, resulting in sub-optimal provisioning decisions. To address this problem, we propose a combined heuristic and artificial intelligence technique that minimizes the cost of deployment at the edge of the network, optimally provisioning, in reasonable time, different types of applications with different requirements, to be done on single or multiple MECs, according to the category of the requested application and current MEC state features. Extensive simulation results show that the use of an intelligent algorithm significantly improves most of the performance metrics used, especially the minimization deployment cost, compared to other baseline techniques. [ABSTRACT FROM AUTHOR]

The transition towards full network virtualization will see services for smart ecosystems including smart metering, healthcare and transportation among others, being deployed as Service Function Chains (SFCs) comprised of an ordered set of virtual network functions. However, since such services are usually deployed in remote cloud networks, the SFCs may transcend multiple domains belonging to different Infrastructure Providers (InPs), possibly with differing policies regarding billing and Quality-of-service (QoS) guarantees. Therefore, efficiently allocating the exhaustible network resources to the different SFCs while meeting the stringent requirements of the services such as delay and QoS among others, remains a complex challenge, especially under limited information disclosure by the InPs. In this work, we formulate the SFC deployment problem across multiple domains focusing on delay constraints, and propose a framework for SFC orchestration which adheres to the privacy requirements of the InPs. Then, we propose a reinforcement learning (RL)-based algorithm for partitioning the SFC request across the different InPs while considering service reliability across the participating InPs. Such RL-based algorithms have the intelligence to infer undisclosed InP information from historical data obtained from past experiences. Simulation results, considering both online and offline scenarios, reveal that the proposed algorithm results in up to 10% improvement in terms of acceptance ratio and provisioning cost compared to the benchmark algorithms, with up to more than 90% saving in execution time for large networks. In addition, the paper proposes an enhancement to a state-of-the-art algorithm which results in up to 5% improvement in terms of provisioning cost. [ABSTRACT FROM AUTHOR]

Agriculture is the largest user of water worldwide by using about 70 percent of total consumption. The world food production depends on the availability of water, considering factors such as demographic and climate change, so the use of efficient irrigation is necessary to apply the correct amount of water to crops. The traditional irrigation systems generally program their scheme based on measurements made at Class A evaporimeter pan. In this paper an irrigation scheme defined by an algorithm that automates the amount of water supplied is presented, it considers the consumption of habanero pepper crop, and a fuzzy system evaluates the necessary duration of irrigation. The climatic variables considered are temperature, relative humidity, and soil moisture. The algorithm was programmed in a microcontroller Atmel 328p included in Arduino platform, with the addition of a ZigBee wireless system that allows for monitoring through a PC. The climatic variables were inserted into the fuzzy system by sets of trapezoidal and triangular form and a Mamdani type inference mechanism in which the knowledge of an expert is registered through the fuzzy rules. The system was applied to a habanero pepper crop at Conkal Institute of Technology in Yucatan, Mexico. [ABSTRACT FROM AUTHOR]

Network virtualisation promises to lead to better manageability of the future Internet by allowing for adaptable sharing of physical network resources among different virtual networks. However, the sharing of resources is not trivial as virtual nodes and links should first be mapped onto substrate nodes and links, and thereafter the allocated resources managed throughout the lifetime of the virtual network. In this paper, we design and evaluate reinforcement learning-based neuro-fuzzy algorithms that perform dynamic, decentralised and coordinated self-management of substrate network resources. The objective is to achieve better efficiency in the utilisation of substrate network resources while ensuring that the quality of service requirements of the virtual networks are not violated. The proposed algorithms are evaluated through comparisons with a Q-learning-based approach as well as two static resource allocation schemes. [ABSTRACT FROM AUTHOR]

NFV continues to draw immense attention from researchers in both industry and academia. By decoupling NFs from the physical equipment on which they run, NFV promises to reduce CAPEX and OPEX, make networks more scalable and flexible, and lead to increased service agility. However, despite the unprecedented interest it has gained, there are still obstacles that must be overcome before NFV can advance to reality in industrial deployments, let alone delivering on the anticipated gains. While doing so, important challenges associated with network and function MANO need to be addressed. In this article, we introduce NFV and give an overview of the MANO framework that has been proposed by ETSI. We then present representative projects and vendor products that focus on MANO, and discuss their features and relationship with the framework. Finally, we identify open MANO challenges as well as opportunities for future research. [ABSTRACT FROM PUBLISHER]

The coordinated development of big data, Internet of Things, cloud computing and other technologies has led to an exponential growth in Internet business. However, the traditional Internet architecture gradually shows a rigid phenomenon due to the binding of the network structure and the hardware. In a high-traffic environment, it has been insufficient to meet people's increasing service quality requirements. Network virtualization is considered to be an effective method to solve the rigidity of the Internet. Among them, virtual network embedding is one of the key problems of network virtualization. Since virtual network mapping is an NP-hard problem, a large number of research has focused on the evolutionary algorithm's masterpiece genetic algorithm. However, the parameter setting in the traditional method is too dependent on experience, and its low flexibility makes it unable to adapt to increasingly complex network environments. In addition, link-mapping strategies that do not consider load balancing can easily cause link blocking in high-traffic environments. In the IoT environment involving medical, disaster relief, life support and other equipment, network performance and stability are particularly important. Therefore, how to provide a more flexible virtual network mapping service in a heterogeneous network environment with large traffic is an urgent problem. Aiming at this problem, a virtual network mapping strategy based on hybrid genetic algorithm is proposed. This strategy uses a dynamically calculated cross-probability and pheromone-based mutation gene selection strategy to improve the flexibility of the algorithm. In addition, a weight update mechanism based on load balancing is introduced to reduce the probability of mapping failure while balancing the load. Simulation results show that the proposed method performs well in a number of performance metrics including mapping average quotation, link load balancing, mapping cost-benefit ratio, acceptance rate and running time. [ABSTRACT FROM AUTHOR]

Network slicing is one of the key enabling technologies for 5G networks. It allows infrastructure owners to assign resources to service providers (tenants), which will afterwards use them to satisfy their end-user demands. This paradigm, which changes the way networks have been traditionally managed, was initially proposed in the wired realm (core networks). More recently, the scientific community has paid attention to the integration of network slicing in wireless cellular technologies (LTE). However, there are not many works addressing the challenges that appear when trying to exploit slicing techniques over WiFi networks, in spite of their growing relevance. In this paper we propose a novel method of proportionally distributing resources in WiFi networks, by means of the airtime. We develop an analytical model, which shed light on how such resources could be split. The validity of the proposed model is assessed by means of simulation-based evaluation over the ns-3 framework [ABSTRACT FROM AUTHOR]

This article contains the report on AIMS 2013, which was held on June 25-28, 2013 at the Universitat Politècnica de Catalunya (UPC), Spain and was driven by the theme 'Emerging Management Mechanisms for the Future Internet'. It covers the three main parts that formed the event program: the keynote and technical sessions of the main track, the PhD workshop and the hands-on tutorials. Finally, the report highlights the evolutions that would shape the future version of AIMS. [ABSTRACT FROM AUTHOR]