{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"id":[{"id":"https:\/\/ror.org\/03mb6wj31","id-type":"ROR","asserted-by":"publisher"},{"id":"https:\/\/www.isni.org\/000000041937028X","id-type":"ISNI","asserted-by":"publisher"},{"id":"https:\/\/www.wikidata.org\/entity\/Q1640731","id-type":"wikidata","asserted-by":"publisher"}],"name":"Universitat Polit\u00e8cnica de Catalunya","acronym":["UPC"]}],"indexed":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T23:44:18Z","timestamp":1770680658900,"version":"3.49.0"},"reference-count":0,"publisher":"Universitat Polit\u00e8cnica de Catalunya","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>(English) In the wake of a digital revolution, contemporary society finds itself entrenched in an era where network applications' demands surpass the capabilities of conventional network management solutions. This dissertation navigates through the intricacies of modern networked environments, where traditional management approaches are falling short due to emerging applications like augmented and virtual reality, holographic telepresence, and vehicular networks, demanding ultra-low latency and robust adaptability. These evolving networks form the backbone of modern society, sustaining numerous vital services but posing elevated complexity and operational hurdles for Internet Service Providers (ISPs) and network operators.\r\n\r\nAmidst this complexity, the need for innovative solutions to optimize and manage today's networks is more pronounced than ever. A central proposition of this dissertation is the MAGNNETO framework, a groundbreaking Machine Learning (ML) based initiative that stands for Multi-Agent Graph Neural Network Optimization. This framework is at the heart of the endeavour to facilitate distributed optimization in networked scenarios. By integrating a Graph Neural Network (GNN) architecture into a Multi-Agent Reinforcement Learning (MARL) setting, it instigates a fully distributed optimization process and capitalizes on the inherent distributed nature of networked environments, hence potentially addressing scalability issues and facilitating real-time applications. This initiative is adaptable, offering versatility in addressing various use cases and showcasing robustness to meet the challenging requisites of real-world applications.\r\n\r\nA substantial contribution of this work is the successful implementation of MAGNNETO across different relevant networked cases, prominently focusing on two highly impactful scenarios within the computer network field. Initially, it re-examines the pivotal issue of Traffic Engineering (TE) optimization in ISP networks. With the goal of curtailing network congestion, MAGNNETO-TE is introduced, a variant of the framework specifically devised to minimize maximum link utilization in these networks. Remarkably, this adaptation heralds a paradigm shift by equalling the performance of traditional state-of-the-art TE optimizers but at a fraction of the execution cost.\r\n\r\nMoreover, the research explores the complex sphere of Congestion Control (CC) in Datacenter Networks (DCN), another critical service in our current digital world that is characterized by dynamic traffic patterns and stringent low-latency prerequisites. Here, MAGNNETO-CC emerges as a potent solution, offering an offline, distributed strategy that harmonizes with widely deployed CC protocols, surpassing other state-of-the-art ML-based CC methodologies and prevailing static CC configurations in performance.\r\n\r\nLooking ahead, the dissertation also delineates potential avenues to enhance MAGNNETO, particularly addressing challenges tied to current GNN architectures (e.g. over-smoothing and over-squashing). It envisions integrating Topological Deep Learning (TDL) techniques to foster a novel, promising approach to distributed optimization that has the potential to exploit arbitrary multi-element correlations, going beyond the traditional graph domain. By addressing the urgent need for efficient network traffic storage on networks with multiple vantage points, the proposed topological-inspired methodology reveals itself as a robust ML-based baseline for lossy data compression.\r\n\r\nIn summation, this dissertation embarks on a pioneering journey to confront the elemental challenges of optimizing networked, graph-based systems. It unfurls the innovative MAGNNETO solution as a beacon of versatility and adaptability, displays its multifaceted applications, and heralds promising directions for future research, aiming to redefine the landscape of distributed network optimization and management in this digitally transformative era.<\/jats:p>\n                <jats:p>(Espa\u00f1ol) En el contexto de una revoluci\u00f3n digital, la sociedad contempor\u00e1nea se encuentra inmersa en una era donde las demandas de las aplicaciones en red superan las capacidades de las soluciones de gesti\u00f3n convencionales. Precisamente, esta tesis navega a trav\u00e9s de las complejidades de los entornos de redes modernas, donde los enfoques de gesti\u00f3n tradicionales se est\u00e1n quedando cortos debido a aplicaciones emergentes como la realidad aumentada, la realidad virtual o la telepresencia hologr\u00e1fica, las cuales exigen ultra baja latencia y adaptabilidad din\u00e1mica. Estas redes en evoluci\u00f3n conforman la columna vertebral de la sociedad moderna, manteniendo numerosos servicios vitales pero planteando una complejidad elevada para los Proveedores de Servicios de Internet (ISP) y los operadores de red.\r\n\r\nEn medio de esta complejidad, la necesidad de soluciones innovadoras para optimizar y gestionar las redes actuales es m\u00e1s evidente que nunca. Una proposici\u00f3n central de esta tesis es el marco MAGNNETO (Optimizaci\u00f3n Multiagente con Redes Neuronales Gr\u00e1ficas, en sus siglas en ingl\u00e9s), una iniciativa revolucionaria basada en Aprendizaje Autom\u00e1tico (ML). Su objetivo principal es facilitar la optimizaci\u00f3n distribuida en escenarios de redes. Al integrar una arquitectura de Redes Neuronales Gr\u00e1ficas (GNN) en un entorno de Aprendizaje por Refuerzo Multiagente (MARL), da pie a un proceso de optimizaci\u00f3n completamente distribuido y aprovecha la naturaleza distribuida inherente de los entornos de red, abordando problemas de escalabilidad y facilitando aplicaciones en tiempo real. Esta iniciativa es adaptable, ofreciendo versatilidad para abordar varios casos de uso y mostrando robustez para cumplir con los desafiantes requisitos de aplicaciones reales.\r\n\r\nUna contribuci\u00f3n sustancial de este trabajo es la implementaci\u00f3n exitosa de MAGNNETO en diferentes casos relevantes de redes, centr\u00e1ndose prominentemente en dos escenarios altamente impactantes en el campo de las redes de computadores. En primer lugar, se aborda el problema crucial de la optimizaci\u00f3n de la Ingenier\u00eda de Tr\u00e1fico (TE) en redes de ISP. Con el objetivo de reducir la congesti\u00f3n de la red, se introduce MAGNNETO-TE, una variante del marco espec\u00edficamente dise\u00f1ada para minimizar la utilizaci\u00f3n m\u00e1xima del enlace en estas redes. Notablemente, esta adaptaci\u00f3n marca un cambio de paradigma al igualar el rendimiento de optimizadores TE tradicionales l\u00edderes en el estado del arte, pero a una fracci\u00f3n de su coste de ejecuci\u00f3n.\r\n\r\nAdem\u00e1s, la investigaci\u00f3n explora el complejo \u00e1mbito del Control de Congesti\u00f3n (CC) en Redes de Centros de Datos (DCN), otro servicio cr\u00edtico en nuestro mundo digital actual caracterizado por patrones de tr\u00e1fico din\u00e1micos y estrictos requisitos de baja latencia. Aqu\u00ed, MAGNNETO-CC emerge como una soluci\u00f3n potente, ofreciendo una estrategia distribuida que armoniza con protocolos de CC ampliamente desplegados, superando a las m\u00e1s avanzadas metodolog\u00edas basadas en ML y a las configuraciones de CC est\u00e1ticas m\u00e1s usadas actualmente.\r\n\r\nMirando hacia el futuro, la tesis tambi\u00e9n delinea posibles v\u00edas para mejorar MAGNNETO, abordando especialmente los desaf\u00edos asociados a las arquitecturas GNN actuales. Visualiza la integraci\u00f3n de t\u00e9cnicas de aprendizaje profundo topol\u00f3gico para fomentar un enfoque novedoso y prometedor para la optimizaci\u00f3n distribuida que tiene el potencial de explotar correlaciones arbitrarias entre m\u00faltiples elementos, yendo m\u00e1s all\u00e1 del dominio de grafos tradicional. Al abordar la necesidad urgente de almacenamiento eficiente del tr\u00e1fico de red, la metodolog\u00eda propuesta se revela como una soluci\u00f3n robusta basada en ML para la compresi\u00f3n de datos con p\u00e9rdida.\r\n\r\nEn resumen, esta tesis enfrenta los desaf\u00edos fundamentales de optimizar sistemas de redes basados en grafos, tratando de redefinir el panorama de la optimizaci\u00f3n y gesti\u00f3n distribuida de redes en esta era de transformaci\u00f3n digital.<\/jats:p>","DOI":"10.5821\/dissertation-2117-405942","type":"dissertation","created":{"date-parts":[[2024,4,5]],"date-time":"2024-04-05T01:22:24Z","timestamp":1712280144000},"approved":{"date-parts":[[2024,3,15]]},"source":"Crossref","is-referenced-by-count":0,"title":["Multi-agent graph learning-based optimization and its applications to computer networks"],"prefix":"10.5821","author":[{"sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guillermo","family":"Bern\u00e1rdez Gil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"3865","container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T06:33:44Z","timestamp":1770618824000},"score":1,"resource":{"primary":{"URL":"https:\/\/hdl.handle.net\/2117\/405942"}},"subtitle":[],"editor":[{"given":"Pere","family":"Barlet Ros","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Alberto","family":"Cabellos Aparicio","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":0,"URL":"https:\/\/doi.org\/10.5821\/dissertation-2117-405942","relation":{},"subject":[]}}