As Next Generation (NextG) networks become more complex, the need to develop a robust, reliable network traffic prediction framework for intelligent network management increases. This study compares the performance of machine learning models in network traffic prediction using a custom Service-Level Agreement (SLA) - based loss function to ensure SLA violation constraints while minimizing overprovisioning. The proposed SLA-based parametric custom loss functions are used to maintain the SLA violation rate percentages the network operators require. Our approach is multivariate, spatiotemporal, and SLA-driven, incorporating 20 Radio Access Network (RAN) features, custom peak traffic time features, and custom mobility-based clustering to leverage spatiotemporal relationships. In this study, five machine learning models are considered: one recurrent neural network (LSTM) model, two encoder-decoder architectures (Transformer and Autoformer), and two gradient-boosted tree models (XGBoost and LightGBM). The prediction performance of the models is evaluated based on different metrics such as SLA violation rate constraints, overprovisioning, and the custom SLA-based loss function parameter. According to our evaluations, Transformer models with custom peak time features achieve the minimum overprovisioning volume at 3% SLA violation constraint. Gradient-boosted tree models have lower overprovisioning volumes at higher SLA violation rates. / Master of Science / As the Next Generation (NextG) networks become more complex, the need to develop a robust, reliable network traffic prediction framework for intelligent network management increases. This study compares the performance of machine learning models in network traffic prediction using a custom loss function to ensure SLA violation constraints. The proposed SLA-based custom loss functions are used to maintain the SLA violation rate percentages required by the network operators while minimizing overprovisioning. Our approach is multivariate, spatiotemporal, and SLA-driven, incorporating 20 Radio Access Network (RAN) features, custom peak traffic time features, and mobility-based clustering to leverage spatiotemporal relationships. We use five machine learning and deep learning models for our comparative study: one recurrent neural network (RNN) model, two encoder-decoder architectures, and two gradient-boosted tree models. The prediction performance of the models was evaluated based on different metrics such as SLA violation rate constraints, overprovisioning, and the custom SLA-based loss function parameter.

The demand for wireless communication is ceaselessly increasing in terms of the number of subscribers and services. Future generations of cellular networks are expected to allow not only humans but also machines to be immersively connected. However, the radio frequency spectrum is already fully allocated. Therefore, developing techniques to increase spectrum efficiency has become necessary. This dissertation analyzes two spectrum sharing techniques that enable efficient utilization of the available radio resources in cellular networks. The first technique, called full-duplex (FD) communication, uses the same spectrum to transmit and receive simultaneously. Using stochastic geometry tools, we derive a closed-form expression of an upper-bound for the maximum achievable uplink ergodic rate in FD cellular networks. We show that the uplink transmission is vulnerable to the new interference introduced by FD communications (interference from the downlink transmission in other cells), especially when the disparity in transmission power between the uplink and downlink is considerable. We further show that adjusting the uplink transmission power according to the interference power level and the channel gain can improve the uplink performance in full-duplex cellular networks. Moreover, we propose an interference management technique that allows a flexible overlap between the spectra occupied by the downlink and uplink transmissions. The flexible overlap is optimized along with the user-to-base station association, the power allocation and the channel allocation in order to maximize a network-wide utility function. The second spectrum sharing technique, called non-orthogonal multiple access (NOMA), allows a transmitter to communicate with multiple receivers through the same frequency-time resource unit. We analyze the implementation of such a scheme in the downlink of cellular networks, more precisely, in the downlink of fog radio access networks (FogRANs). FogRAN is a network architecture that takes full advantage of the edge devices capability to process and store data. We propose managing the interference for NOMA-based FogRAN to improve the network performance by jointly optimizing user scheduling, the power allocated to each resource block and the division of power between the multiplexed users. The simulation results show that significant performance gains can be achieved through proper resource allocation with both studied spectrum sharing techniques.

As the world becomes more globalised, user equipment such as smartphones and Internet of Things devices require increasingly more data, which increases the demand for wireless data traffic. Hence, the acceleration of next-generational networks (5G and beyond) focuses mainly on increasing the bitrate and decreasing the latency. A crucial technology for 5G and beyond is the massive MIMO. In a massive MIMO system, a detector processes the received signals from multiple antennas to decode the transmitted data and extract useful information. This has been implemented in many ways, and one of the most used algorithms is the Zero Forcing (ZF) algorithm. This thesis presents a novel parallel design to accelerate the ZF algorithm using the Cholesky decomposition. This is implemented on a GPU, written in the CUDA programming language, and compared to the existing state-of-the-art implementations regarding latency and throughput. The implementation is also validated from a MATLAB implementation. This research demonstrates promising performance using GPUs for massive MIMO detection algorithms. Our approach achieves a significant speedup factor of 350 in comparison to a serial version of the implementation. The throughput achieved is 160 times greater than a comparable GPU-based approach. Despite this, our approach reaches a 2.4 times lower throughput than a solution that employed application-specific hardware. Given the promising results, we advocate for continued research in this area to further optimise detection algorithms and enhance their performance on GPUs, to potentially achieve even higher throughput and lower latency. / <p>Our examiner Mahdi wants to wait six months before the thesis is published. </p>

With the move of the broadband cellular network towards 5G taking off and the preparatory work on 6G and beyond starting, the need for low-complexity, low-power, and high-performance frequency synthesis using Phase-Locked Loop (PLL)s increases. As we get deeper into the mm-wave frequencies and push towards frequencies in the order of 50-70 GHz design challenges with existing PLL architectures, such as limited technology scaling and limited in-band noise performance become more apparent. Other designs have tried overcoming these problems, for example by using single-bit phase detection at the cost of increased complexity when trying to control the bandwidth, or designing the loop with lower bandwidth to suppress in-band noise at the cost of requiring a lower noise and thus more power hungry oscillator. This thesis proposes a new Phase-locked loop architecture implemented in a 22nm node to combat these issues, utilizing a Pulse-Shrinking Time-To-Digital Converter (PS-TDC) offering sub-pico-second resolution with minimal power consumption in lock. The results found in this thesis have shown the viability of such a design, offering good in-band performance, allowing for wide bandwidth, and the use of a cheaper low-power Digital-Controlled Oscillator (DCO). The PS-TDC architecture combined with control logic implemented in this project can drastically decrease power consumption in lock while being able to compensate for process variations to optimize jitter performance. Additionally, by utilizing a Phase-Frequency Detector (PFD) and gear-shifting logic it has been shown that robust and fast locking can be achieved. / Med övergången till 5G i mobila bredbandsnätverk och förberedelserna för 6G på gång ökar behovet av lågkomplexa, lågeffekts- och högpresterande frekvenssyntes. När vi beger oss djupare in i millimetervågsfrekvenserna och strävar efter frekvenser uppemot 50-70 GHz blir designutmaningar med befintliga faslåsta loopar, såsom begränsad teknologiskalning och dålig prestanda för inband-brus, alltmer tydliga. Andra designer har försökt att övervinna dessa problem genom att till exempel använda enbitars fasdetektion till priset av ökad komplexitet vid styrning av systemets bandbredd, eller genom att designa loopen med lägre bandbredd för att vidare dämpa inband-brus, vilket kommer till priset av en oscillator med lägre brus och därmed högre effektförbrukning. Denna avhandling föreslår en ny arkitektur för faslåsta loopar för att överkomma dessa problem genom att använda en pulskrympande tids-till-digital omvandlare som erbjuder sub-pikosekunds upplösning med minimal effektförbrukning när frekvensen är låst. Resultaten som presenteras i denna avhandling har visat att en sådan design är möjlig, med god in-band prestanda, möjlighet till hög bandbredd och därmed användning av en billigare lågeffekt DCO. Den pulsskalande TDC-arkitekturen i kombination med kontrolllogik implementerad i detta projekt kan dramatiskt minska effektförbrukningen när frekvensen är låst, samtidigt som den kan kompensera för processvariationer för att optimera jitterprestanda. Sist har det visats att en robust och snabb låsning av frekvensen kan uppnås genom att använda en PFD.

En la actualidad, la Internet de las Cosas (Internet of Things, IoT) es una tecnología esencial para la próxima generación de sistemas inalámbricos. La conectividad es la base de IoT, y el tipo de acceso requerido dependerá de la naturaleza de la aplicación. Uno de los principales facilitadores del entorno IoT es la comunicación machine-to-machine (M2M) y, en particular, su enorme potencial para ofrecer conectividad ubicua entre dispositivos inteligentes. Las redes celulares son la elección natural para las aplicaciones emergentes de IoT y M2M. Un desafío importante en las redes celulares es conseguir que la red sea capaz de manejar escenarios de acceso masivo en los que numerosos dispositivos utilizan comunicaciones M2M. Por otro lado, los sistemas celulares han experimentado un tremendo desarrollo en las últimas décadas: incorporan tecnología sofisticada y nuevos algoritmos para ofrecer una amplia gama de servicios. El modelado y análisis del rendimiento de estas redes multiservicio es también una tarea desafiante que podría requerir un gran esfuerzo computacional. Para abordar los desafíos anteriores, nos centramos en primer lugar en el diseño y la evaluación de las prestaciones de nuevos mecanismos de control de acceso para hacer frente a las comunicaciones masivas M2M en redes celulares. Posteriormente nos ocupamos de la evaluación de prestaciones de redes multiservicio y proponemos una nueva técnica analítica que ofrece precisión y eficiencia computacional. Nuestro principal objetivo es proporcionar soluciones para aliviar la congestión en la red de acceso radio cuando un gran número de dispositivos M2M intentan conectarse a la red. Consideramos los siguientes tipos de escenarios: (i) los dispositivos M2M se conectan directamente a las estaciones base celulares, y (ii) forman grupos y los datos se envían a concentradores de tráfico (gateways) que les proporcionan acceso a la infraestructura. En el primer escenario, dado que el número de dispositivos añadidos a la red aumenta continuamente, esta debería ser capaz de manejar el considerable incremento en las solicitudes de acceso. El 3rd Generation Partnership Project (3GPP) ha propuesto el access class barring (ACB) como una solución práctica para el control de congestión en la red de acceso radio y la red troncal. El ajuste correcto de los parámetros de ACB de acuerdo con la intensidad del tráfico es crítico, pero cómo hacerlo de forma dinámica y autónoma es un problema complejo cuya solución no está recogida en las especificaciones del 3GPP. Esta tesis doctoral contribuye al análisis del rendimiento y al diseño de nuevos algoritmos que implementen efectivamente este mecanismo, y así superar los desafíos introducidos por las comunicaciones masivas M2M. En el segundo escenario, dado que la heterogeneidad de los dispositivos IoT y las arquitecturas celulares basadas en hardware imponen desafíos aún mayores para permitir una comunicación flexible y eficiente en los sistemas inalámbricos 5G, esta tesis doctoral también contribuye al diseño de software-defined gateways (SD-GWs) en una nueva arquitectura propuesta para redes inalámbricas definidas por software que se denomina SoftAir. Esto permite manejar tanto un gran número de dispositivos como el volumen de datos que estarán vertiendo en la red. Otra contribución de esta tesis doctoral es la propuesta de una técnica novedosa para el análisis de prestaciones de redes multiservicio de alta capacidad que se basa en un nuevo enfoque del modelizado analítico de sistemas que operan a diferentes escalas temporales. Este enfoque utiliza el análisis del transitorio de una serie de subcadenas absorbentes y lo denominamos absorbing Markov chain approximation (AMCA). Nuestros resultados muestran que para un coste computacional dado, AMCA calcula los parámetros de prestaciones habituales de un sistema con mayor precisión, en comparación con los resultados obtenidos por otr / Nowadays, Internet of Things (IoT) is an essential technology for the upcoming generation of wireless systems. Connectivity is the foundation for IoT, and the type of access required will depend on the nature of the application. One of the leading facilitators of the IoT environment is machine-to-machine (M2M) communication, and particularly, its tremendous potential to offer ubiquitous connectivity among intelligent devices. Cellular networks are the natural choice for emerging IoT and M2M applications. A major challenge in cellular networks is to make the network capable of handling massive access scenarios in which myriad devices deploy M2M communications. On the other hand, cellular systems have seen a tremendous development in recent decades; they incorporate sophisticated technology and algorithms to offer a broad range of services. The modeling and performance analysis of these large multi-service networks is also a challenging task that might require high computational effort. To address the above challenges, we first concentrate on the design and performance evaluation of novel access control schemes to deal with massive M2M communications. Then, we focus on the performance evaluation of large multi-service networks and propose a novel analytical technique that features accuracy and computational efficiency. Our main objective is to provide solutions to ease the congestion in the radio access or core network when massive M2M devices try to connect to the network. We consider the following two types of scenarios: (i) massive M2M devices connect directly to cellular base stations, and (ii) they form clusters and the data is forwarded to gateways that provide them with access to the infrastructure. In the first scenario, as the number of devices added to the network is constantly increasing, the network should handle the considerable increment in access requests. Access class barring (ACB) is proposed by the 3rd Generation Partnership Project (3GPP) as a practical congestion control solution in the radio access and core network. The proper tuning of the ACB parameters according to the traffic intensity is critical, but how to do so dynamically and autonomously is a challenging task that has not been specified. Thus, this dissertation contributes to the performance analysis and optimal design of novel algorithms to implement effectively this barring scheme and overcome the challenges introduced by massive M2M communications. In the second scenario, since the heterogeneity of IoT devices and the hardware-based cellular architectures impose even greater challenges to enable flexible and efficient communication in 5G wireless systems, this dissertation also contributes to the design of software-defined gateways (SD-GWs) in a new architecture proposed for wireless software-defined networks called SoftAir. The deployment of these SD-GWs represents an alternative solution aiming at handling both a vast number of devices and the volume of data they will be pouring into the network. Another contribution of this dissertation is to propose a novel technique for the performance analysis of large multi-service networks. The underlying complexity of the network, particularly concerning its size and the ample range of configuration options, makes the solution of the analytical models computationally costly. However, a typical characteristic of these networks is that they support multiple types of traffic flows operating at different time-scales. This time-scale separation can be exploited to reduce considerably the computational cost associated to determine the key performance indicators. Thus, we propose a novel analytical modeling approach based on the transient regime analysis, that we name absorbing Markov chain approximation (AMCA). For a given computational cost, AMCA finds common performance indicators with greater accuracy, when compared to the results obtained by other approximate methods proposed in the literature. / En l'actualitat, la Internet de les Coses (Internet of Things, IoT) és una tecnologia essencial per a la propera generació de sistemes sense fil. La connectivitat és la base d'IoT, i el tipus d'accés requerit dependrà de la naturalesa de l'aplicació. Un dels principals facilitadors de l'entorn IoT és la comunicació machine-to-machine (M2M) i, en particular, el seu enorme potencial per oferir connectivitat ubiqua entre dispositius intel · ligents. Les xarxes mòbils són l'elecció natural per a les aplicacions emergents de IoT i M2M. Un desafiament important en les xarxes mòbils que actualment está rebent molta atenció és aconseguir que la xarxa siga capaç de gestionar escenaris d'accés massiu en què una gran quantitat de dispositius utilitzen comunicacions M2M. D'altra banda, els sistemes mòbils han experimentat un gran desenvolupament en les últimes dècades: incorporen tecnologia sofisticada i nous algoritmes per oferir una àmplia gamma de serveis. El modelatge i análisi del rendiment d'aquestes xarxes multiservei és també un desafiament important que podria requerir un gran esforç computacional. Per abordar els desafiaments anteriors, en aquesta tesi doctoral ens centrem en primer lloc en el disseny i l'avaluació de les prestacions de nous mecanismes de control d'accés per fer front a les comunicacions massives M2M en xarxes cel · lulars. Posteriorment ens ocupem de l'avaluació de prestacions de xarxes multiservei i proposem una nova tècnica analítica que ofereix precisió i eficiència computacional. El nostre principal objectiu és proporcionar solucions per a alleujar la congestió a la xarxa d'accés ràdio quan un gran nombre de dispositius M2M intenten connectar-se a la xarxa. Considerem els dos tipus d'escenaris següents: (i) els dispositius M2M es connecten directament a les estacions base cel · lulars, i (ii) formen grups i les dades s'envien a concentradors de trànsit (gateways) que els proporcionen accés a la infraestructura. En el primer escenari, atès que el nombre de dispositius afegits a la xarxa augmenta contínuament, aquesta hauria de ser capaç de gestionar el considerable increment en les sol · licituds d'accés. El 3rd Generation Partnership Project (3GPP) ha proposat l'access class barring (ACB) com una solució pràctica per al control de congestió a la xarxa d'accès ràdio i la xarxa troncal. L'ajust correcte dels paràmetres d'ACB d'acord amb la intensitat del trànsit és crític, però com fer-ho de forma dinàmica i autònoma és un problema complex, la solució del qual no està recollida en les especificacions del 3GPP. Aquesta tesi doctoral contribueix a l'anàlisi del rendiment i al disseny de nous algoritmes que implementen efectivament aquest mecanisme, i així superar els desafiaments introduïts per les comunicacions massives M2M en les xarxes mòbils actuals i futures. En el segon escenari, atès que l'heterogeneïtat dels dispositius IoT i les arquitectures cel · lulars basades en hardware imposen desafiaments encara més grans per permetre una comunicació flexible i eficient en els sistemes sense fil 5G, aquesta tesi doctoral també contribueix al disseny de software-defined gateways (SD-GWS) en una nova arquitectura proposada per a xarxes sense fils definides per programari que s'anomena SoftAir. Això permet gestionar tant un gran nombre de dispositius com el volum de dades que estaran abocant a la xarxa. Una altra contribució d'aquesta tesi doctoral és la proposta d'una tècnica innovadora per a l'anàlisi de prestacions de xarxes multiservei d'alta capacitat que es basa en un nou enfocament del modelitzat analític de sistemes que operen a diferents escales temporals. Aquest enfocament utilitza l'anàlisi del transitori d'una sèrie de subcadenes absorbents i l'anomenem absorbing Markov chain Approximation (AMCA). Els nostres resultats mostren que per a un cost computacional donat, AMCA calcula els paràmetres de prestacions habituals d / Tello Oquendo, LP. (2018). Design and Performance Analysis of Access Control Mechanisms for Massive Machine-to-Machine Communications in Wireless Cellular Networks [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/107946