A Mobile Networks Digital Twin (MNDT) is a virtual replica of a mobile communication network that accurately models the devices, the communication links, the operating environment, and the applications that run on the physical network. By replicating different environments in a laboratory and running multiple scenarios, Digital Twins provide a cost-effective way to evaluate performance, predict the effects of network changes, optimize network management, and make appropriate decisions. This paper presents a methodology for automatically creating and using Network Digital Twins, along with a proposed architecture for performing this implementation. This work is framed in the context of the B5GEMINI project, whose goal is to develop an MNDT applied to a 5G core environment and its evolution towards 6G, being able to apply it to use cases in advanced scenarios such as cybersecurity or Industry 4.0. The proposed methodology covers the entire lifecycle of the MNDT, from the initial phases of data acquisition and modeling to the phases of use and bidirectional connection between physical and digital elements.

Security in IoT networks is currently mandatory, due to the high amount of data that has to be handled. These systems are vulnerable to several cybersecurity attacks, which are increasing in number and sophistication. Due to this reason, new intrusion detection techniques have to be developed, being as accurate as possible for these scenarios. Intrusion detection systems based on machine learning algorithms have already shown a high performance in terms of accuracy. This research proposes the study and evaluation of several preprocessing techniques based on traffic categorization for a machine learning neural network algorithm. This research uses for its evaluation two benchmark datasets, namely UGR16 and the UNSW-NB15, and one of the most used datasets, KDD99. The preprocessing techniques were evaluated in accordance with scalar and normalization functions. All of these preprocessing models were applied through different sets of characteristics based on a categorization composed by four groups of features: basic connection features, content characteristics, statistical characteristics and finally, a group which is composed by traffic-based features and connection direction-based traffic characteristics. The objective of this research is to evaluate this categorization by using various data preprocessing techniques to obtain the most accurate model. Our proposal shows that, by applying the categorization of network traffic and several preprocessing techniques, the accuracy can be enhanced by up to 45%. The preprocessing of a specific group of characteristics allows for greater accuracy, allowing the machine learning algorithm to correctly classify these parameters related to possible attacks.

Internet growth has generated new types of services where the use of sensors and actuators is especially remarkable. These services compose what is known as the Internet of Things (IoT). One of the biggest current challenges is obtaining a safe and easy access control scheme for the data managed in these services. We propose integrating IoT devices in an access control system designed for Web-based services by modelling certain IoT communication elements as resources. This would allow us to obtain a unified access control scheme between heterogeneous devices (IoT devices, Internet-based services, etc.). To achieve this, we have analysed the most relevant communication protocols for these kinds of environments and then we have proposed a methodology which allows the modelling of communication actions as resources. Then, we can protect these resources using access control mechanisms. The validation of our proposal has been carried out by selecting a communication protocol based on message exchange, specifically Message Queuing Telemetry Transport (MQTT). As an access control scheme, we have selected User-Managed Access (UMA), an existing Open Authorization (OAuth) 2.0 profile originally developed for the protection of Internet services. We have performed tests focused on validating the proposed solution in terms of the correctness of the access control system. Finally, we have evaluated the energy consumption overhead when using our proposal.

One of the biggest challenges in modern societies is to solve vehicular traffic problems. Sensor networks in traffic environments have contributed to improving the decision-making process of Intelligent Transportation Systems. However, one of the limiting factors for the effectiveness of these systems is in the deployment of sensors to provide accurate information about the traffic. Our proposal is using the centrality measurement of a graph as a base to locate the best locations for sensor installation in a traffic network. After integrating these sensors in a simulation scenario, we define a Multi-Agent Systems composed of three types of agents: traffic light management agents, traffic jam detection agents, and agents that control the traffic lights at an intersection. The ultimate goal of these Multi-Agent Systems is to improve the trip duration for vehicles in the network. To validate our solution, we have developed the needed elements for modelling the sensors and agents in the simulation environment. We have carried out experiments using the Simulation of Urban MObility (SUMO) traffic simulator and the Travel and Activity PAtterns Simulation (TAPAS) Cologne traffic scenario. The obtained results show that our proposal allows to reduce the sensor network while still obtaining relevant information to have a global view of the environment. Finally, regarding the Multi-Agent Systems, we have carried out experiments that show that our proposal is able to improve other existing solutions such as conventional traffic light management systems (static or dynamic) in terms of reduction of vehicle trip duration and reduction of the message exchange overhead in the sensor network.

Nowadays, companies and official bodies are using the data as a principal asset to take strategic decisions. The advances in big data processing, storage and analysis techniques have allowed to manage the continuous increase in the volume of data. This increase in the volume of data together with its high variability and the large number of sources lead to a constant growing of the complexity of the data management environment. Data governance is the key for simplifying that complexity: it is the element that controls the decision making and responsibilities for all the processes related to data management. This paper discusses an approach to data governance based on ontological reasoning to reduce data management complexity. The proposed data governance system is built over an autonomous system based on distributed components. It implements semantic techniques and automatic ontology-based reasoning. The different components use a Shared Knowledge Plane to interact. Its fundamental piece is an ontology that represents all the data management processes included in data governance. A prototype of such a system has been implemented and tested for Telefonica’s global video service. The results obtained show the feasibility of using this type of technology to reduce the complexity of managing big data environments.

New computational and technological paradigms that currently guide developments in the information society, i.e., Internet of things, pervasive technology, or Ubicomp, favor the appearance of new intrusion vectors that can directly affect people’s daily lives. This, together with advances in techniques and methods used for developing new cyber-attacks, exponentially increases the number of cyber threats which affect the information society. Because of this, the development and improvement of technology that assists cybersecurity experts to prevent and detect attacks arose as a fundamental pillar in the field of cybersecurity. Specifically, intrusion detection systems are now a fundamental tool in the provision of services through the internet. However, these systems have certain limitations, i.e., false positives, real-time analytics, etc., which require their operation to be supervised. Therefore, it is necessary to offer architectures and systems that favor an efficient analysis of the data handled by these tools. In this sense, this paper presents a new model of data preprocessing based on a novel distributed computing architecture focused on large-scale datasets such as UGR’16. In addition, the paper analyzes the use of machine learning techniques in order to improve the response and efficiency of the proposed preprocessing model. Thus, the solution developed achieves good results in terms of computer performance. Finally, the proposal shows the adequateness of decision tree algorithms for training a machine learning model by using a large dataset when compared with a multilayer perceptron neural network.