1 code implementation • 16 Oct 2019 • Paul Almasan, José Suárez-Varela, Krzysztof Rusek, Pere Barlet-Ros, Albert Cabellos-Aparicio
GNNs are Deep Learning models inherently designed to generalize over graphs of different sizes and structures.
1 code implementation • 3 Oct 2019 • Krzysztof Rusek, José Suárez-Varela, Paul Almasan, Pere Barlet-Ros, Albert Cabellos-Aparicio
Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks.
4 code implementations • 23 Jan 2019 • Krzysztof Rusek, José Suárez-Varela, Albert Mestres, Pere Barlet-Ros, Albert Cabellos-Aparicio
In the paper we show that our model provides accurate estimates of delay and jitter (worst case $R^2=0. 86$) when testing against topologies, routing and traffic not seen during training.
Networking and Internet Architecture
1 code implementation • 29 Dec 2021 • José Suárez-Varela, Paul Almasan, Miquel Ferriol-Galmés, Krzysztof Rusek, Fabien Geyer, Xiangle Cheng, Xiang Shi, Shihan Xiao, Franco Scarselli, Albert Cabellos-Aparicio, Pere Barlet-Ros
Graph neural networks (GNN) have shown outstanding applications in many fields where data is fundamentally represented as graphs (e. g., chemistry, biology, recommendation systems).
1 code implementation • 30 Jul 2021 • David Pujol-Perich, José Suárez-Varela, Albert Cabellos-Aparicio, Pere Barlet-Ros
To this end, we use a graph representation that keeps flow records and their relationships, and propose a novel Graph Neural Network (GNN) model tailored to process and learn from such graph-structured information.
1 code implementation • 22 Sep 2021 • Paul Almasan, Shihan Xiao, Xiangle Cheng, Xiang Shi, Pere Barlet-Ros, Albert Cabellos-Aparicio
In this paper we propose Enero, an efficient real-time TE solution based on a two-stage optimization process.
1 code implementation • 1 Feb 2022 • Carlos Güemes-Palau, Paul Almasan, Shihan Xiao, Xiangle Cheng, Xiang Shi, Pere Barlet-Ros, Albert Cabellos-Aparicio
In the context of DTN, DRL can be leveraged to solve optimization problems without directly impacting the real-world network behavior.
2 code implementations • 22 Dec 2022 • Miquel Ferriol-Galmés, Jordi Paillisse, José Suárez-Varela, Krzysztof Rusek, Shihan Xiao, Xiang Shi, Xiangle Cheng, Pere Barlet-Ros, Albert Cabellos-Aparicio
We have tested RouteNet-Fermi in networks of increasing size (up to 300 nodes), including samples with mixed traffic profiles -- e. g., with complex non-Markovian models -- and arbitrary routing and queue scheduling configurations.
1 code implementation • 3 Sep 2021 • Guillermo Bernárdez, José Suárez-Varela, Albert López, Bo Wu, Shihan Xiao, Xiangle Cheng, Pere Barlet-Ros, Albert Cabellos-Aparicio
In our evaluation, we compare our MARL+GNN system with DEFO, a network optimizer based on Constraint Programming that represents the state of the art in TE.
BIG-bench Machine Learning Multi-agent Reinforcement Learning +1
1 code implementation • 23 Jul 2018 • Albert Mestres, Eduard Alarcón, Yusheng Ji, Albert Cabellos-Aparicio
In this context, ML can be used as a computer network modeling technique to build models that estimate the network performance.
1 code implementation • 26 Jul 2021 • José Suárez-Varela, Miquel Ferriol-Galmés, Albert López, Paul Almasan, Guillermo Bernárdez, David Pujol-Perich, Krzysztof Rusek, Loïck Bonniot, Christoph Neumann, François Schnitzler, François Taïani, Martin Happ, Christian Maier, Jia Lei Du, Matthias Herlich, Peter Dorfinger, Nick Vincent Hainke, Stefan Venz, Johannes Wegener, Henrike Wissing, Bo Wu, Shihan Xiao, Pere Barlet-Ros, Albert Cabellos-Aparicio
During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of control, monitoring and management tasks in real-world deployments.
no code implementations • 15 Jul 2020 • Hamidreza Taghvaee, Akshay Jain, Xavier Timoneda, Christos Liaskos, Sergi Abadal, Eduard Alarcón, Albert Cabellos-Aparicio
Concretely, we show that this method is able to learn and predict the parameters governing the reflected wave radiation pattern with an accuracy of a full wave simulation (98. 8%-99. 8%) and the time and computational complexity of an analytical model.
no code implementations • 13 Oct 2020 • Miquel Ferriol-Galmés, José Suárez-Varela, Pere Barlet-Ros, Albert Cabellos-Aparicio
Recent advances in Machine Learning (ML) have shown a great potential to build data-driven solutions for a plethora of network-related problems.
no code implementations • 12 Jun 2021 • Hamidreza Taghvaee, Akshay Jain, Sergi Abadal, Gabriele Gradoni, Eduard Alarcón, Albert Cabellos-Aparicio
We analyze the performance for indoor and outdoor scenarios, given the broadcast mode of operation.
no code implementations • 14 Sep 2021 • David Pujol-Perich, José Suárez-Varela, Miquel Ferriol, Shihan Xiao, Bo Wu, Albert Cabellos-Aparicio, Pere Barlet-Ros
In this article, we present IGNNITION, a novel open-source framework that enables fast prototyping of GNNs for networking systems.
no code implementations • 4 Oct 2021 • Miquel Ferriol-Galmés, José Suárez-Varela, Krzysztof Rusek, Pere Barlet-Ros, Albert Cabellos-Aparicio
Graph Neural Networks (GNN) have shown a strong potential to be integrated into commercial products for network control and management.
no code implementations • 18 Jan 2022 • Krzysztof Rusek, Agnieszka Kleszcz, Albert Cabellos-Aparicio
In the paper, we propose two models of Artificial Intelligence (AI) patents in European Union (EU) countries addressing spatial and temporal behaviour.
no code implementations • 28 Feb 2022 • Miquel Ferriol-Galmés, Krzysztof Rusek, José Suárez-Varela, Shihan Xiao, Xiangle Cheng, Pere Barlet-Ros, Albert Cabellos-Aparicio
Network modeling is a fundamental tool in network research, design, and operation.
no code implementations • 23 Dec 2022 • Ángela López-Cardona, Guillermo Bernárdez, Pere Barlet-Ros, Albert Cabellos-Aparicio
We propose a novel architecture based on the Proximal Policy Optimization algorithm with Graph Neural Networks to solve the Optimal Power Flow.
no code implementations • 31 Mar 2023 • Guillermo Bernárdez, José Suárez-Varela, Albert López, Xiang Shi, Shihan Xiao, Xiangle Cheng, Pere Barlet-Ros, Albert Cabellos-Aparicio
In this paper, we present MAGNNETO, a distributed ML-based framework that leverages Multi-Agent Reinforcement Learning and Graph Neural Networks for distributed TE optimization.
no code implementations • 9 Aug 2023 • Guillermo Bernárdez, José Suárez-Varela, Xiang Shi, Shihan Xiao, Xiangle Cheng, Pere Barlet-Ros, Albert Cabellos-Aparicio
The ECN configuration is thus a crucial aspect on the performance of CC protocols.
no code implementations • 21 Aug 2023 • Guillermo Bernárdez, Lev Telyatnikov, Eduard Alarcón, Albert Cabellos-Aparicio, Pere Barlet-Ros, Pietro Liò
Recently emerged Topological Deep Learning (TDL) methods aim to extend current Graph Neural Networks (GNN) by naturally processing higher-order interactions, going beyond the pairwise relations and local neighborhoods defined by graph representations.
no code implementations • 18 Oct 2023 • Carlos Güemes-Palau, Miquel Ferriol Galmés, Albert Cabellos-Aparicio, Pere Barlet-Ros
In this paper we propose a Graph Neural Network (GNN)-based solution specifically designed to better capture the complexities of real network scenarios.
no code implementations • 11 Dec 2023 • Hamid Latif-Martínez, José Suárez-Varela, Albert Cabellos-Aparicio, Pere Barlet-Ros
Detecting anomalies on network traffic is a complex task due to the massive amount of traffic flows in today's networks, as well as the highly-dynamic nature of traffic over time.