Predicting performance metrics in edge-cloud networks using Graph Neural Networks.
Christian Maier, Nina Großegesse, Felix Strohmeier (2025): Predicting performance metrics in edge-cloud networks using Graph Neural Networks. In: Proceedings of the 3rd Workshop on Machine Learning in Networking (MaLeNe), co-located with the 6th International Conference on Networked Systems (NetSys 2025).
This paper explores the application of Graph Neural Networks (GNNs) for predicting performance metrics in edge-cloud networks. By modeling the network as a graph, where nodes represent devices, and edges represent communication links, GNNs effectively capture the complex interdependencies and interactions within the network. We demonstrate that GNNs can accurately predict key performance metrics such as latency and jitter, using data from real network conditions. Our findings highlight the potential of GNNs to enhance performance monitoring and optimization in edge-cloud environments, paving the way for more efficient resource management and energy-efficiency.
